ReinforcementLearning.jl Versions Save

ReinforcementLearningEnvironments ReinforcementLearningEnvironments-v0.9.1

Diff since ReinforcementLearningEnvironments-v0.9.0

Merged pull requests:

• Add missing Flux compat (#1059) (@jeremiahpslewis)
• Fix docs / website build (#1064) (@jeremiahpslewis)
• Correct Pendulum x-y coordinates (#1065) (@HenriDeh)
• Make QBasedPolicy general for AbstractLearner s (#1069) (@dharux)
• Fix hooks for multiplayer case (#1071) (@jeremiahpslewis)
• Fix doc build errors (#1072) (@jeremiahpslewis)
• bump rlcore version (#1073) (@jeremiahpslewis)
• Make FluxApproximator work with QBasedPolicy (#1075) (@jeremiahpslewis)
• Fix RLEnvs version (#1076) (@jeremiahpslewis)

Closed issues:

• Next Release Plan (v0.11) (#614)
• Package Stabilization Plan (#792)
• test/runtests.jl empty (+ arch discussion) (#843)
• policy(env) returns no legal action -inf initialized Q-table (#852)
• Refactor CI into separate Workflows per package (and separate codecov projects per package) (#869)
• Add deprecation warnings to non-refactored policies (#892)
• Vectorized environments (#908)
• Loading a Gym Environment (#912)
• PPO with MaskedPPOTrajectory (#917)
• Devmode is not working (#918)
• TD3 Policy unable to handle environments with multidimensional action spaces (#951)
• Spin off core packages (#960)
• experiments failed (#982)
• Breaking the tutorial by getting TotalRewardPerEpisode out of sync with the stopping condition in a run call (#1000)
• Transfer Algorithms to RLFarm (#1028)
• Update Buildkite script for gpu testing so it's sub package compatible (#1030)
• Website: A practical introduction to RL: Does not introduce, source code is broken (#1036)
• ElasticArraySARTSTraces does not record the trajectories of MountainCarEnv() correctly (#1067)
• Algorithm implementations (#1070)
• No method matching iterate ArrayProductDomain (#1074)

ReinforcementLearningCore ReinforcementLearningCore-v0.15.3

Diff since ReinforcementLearningCore-v0.15.2

Merged pull requests:

• Make FluxApproximator work with QBasedPolicy (#1075) (@jeremiahpslewis)

ReinforcementLearningBase ReinforcementLearningBase-v0.13.1

Diff since ReinforcementLearningBase-v0.13.0

Merged pull requests:

• Add missing Flux compat (#1059) (@jeremiahpslewis)
• Fix docs / website build (#1064) (@jeremiahpslewis)
• Correct Pendulum x-y coordinates (#1065) (@HenriDeh)
• Make QBasedPolicy general for AbstractLearner s (#1069) (@dharux)
• Fix hooks for multiplayer case (#1071) (@jeremiahpslewis)
• Fix doc build errors (#1072) (@jeremiahpslewis)
• bump rlcore version (#1073) (@jeremiahpslewis)
• Make FluxApproximator work with QBasedPolicy (#1075) (@jeremiahpslewis)

Closed issues:

• Next Release Plan (v0.11) (#614)
• Package Stabilization Plan (#792)
• test/runtests.jl empty (+ arch discussion) (#843)
• policy(env) returns no legal action -inf initialized Q-table (#852)
• Refactor CI into separate Workflows per package (and separate codecov projects per package) (#869)
• Add deprecation warnings to non-refactored policies (#892)
• Vectorized environments (#908)
• Loading a Gym Environment (#912)
• PPO with MaskedPPOTrajectory (#917)
• Devmode is not working (#918)
• TD3 Policy unable to handle environments with multidimensional action spaces (#951)
• Spin off core packages (#960)
• experiments failed (#982)
• Breaking the tutorial by getting TotalRewardPerEpisode out of sync with the stopping condition in a run call (#1000)
• Transfer Algorithms to RLFarm (#1028)
• Update Buildkite script for gpu testing so it's sub package compatible (#1030)
• Website: A practical introduction to RL: Does not introduce, source code is broken (#1036)
• ElasticArraySARTSTraces does not record the trajectories of MountainCarEnv() correctly (#1067)
• Algorithm implementations (#1070)

ReinforcementLearningCore ReinforcementLearningCore-v0.15.2

Diff since ReinforcementLearningCore-v0.15.1

Merged pull requests:

• Make QBasedPolicy general for AbstractLearner s (#1069) (@dharux)
• bump rlcore version (#1073) (@jeremiahpslewis)

ReinforcementLearningCore ReinforcementLearningCore-v0.15.1

Diff since ReinforcementLearningCore-v0.15.0

Merged pull requests:

• Add missing Flux compat (#1059) (@jeremiahpslewis)
• Fix docs / website build (#1064) (@jeremiahpslewis)
• Correct Pendulum x-y coordinates (#1065) (@HenriDeh)
• Fix hooks for multiplayer case (#1071) (@jeremiahpslewis)
• Fix doc build errors (#1072) (@jeremiahpslewis)

Closed issues:

• Next Release Plan (v0.11) (#614)
• Package Stabilization Plan (#792)
• test/runtests.jl empty (+ arch discussion) (#843)
• policy(env) returns no legal action -inf initialized Q-table (#852)
• Refactor CI into separate Workflows per package (and separate codecov projects per package) (#869)
• Add deprecation warnings to non-refactored policies (#892)
• Vectorized environments (#908)
• Loading a Gym Environment (#912)
• PPO with MaskedPPOTrajectory (#917)
• Devmode is not working (#918)
• TD3 Policy unable to handle environments with multidimensional action spaces (#951)
• Spin off core packages (#960)
• experiments failed (#982)
• Breaking the tutorial by getting TotalRewardPerEpisode out of sync with the stopping condition in a run call (#1000)
• Transfer Algorithms to RLFarm (#1028)
• Update Buildkite script for gpu testing so it's sub package compatible (#1030)
• Website: A practical introduction to RL: Does not introduce, source code is broken (#1036)
• ElasticArraySARTSTraces does not record the trajectories of MountainCarEnv() correctly (#1067)
• Algorithm implementations (#1070)

ReinforcementLearning v0.11.0

Diff since v0.10.2

Merged pull requests:

• Reactivate some tests for RLExperiments (#790) (@jeremiahpslewis)
• Drop RL.jl as dependency from Experiments (#795) (@jeremiahpslewis)
• Fix compat for RLBase (#796) (@jeremiahpslewis)
• Fix RLCore version, prep for bump (#797) (@jeremiahpslewis)
• Add reexport compat (#798) (@jeremiahpslewis)
• Bump compat helper (#799) (@jeremiahpslewis)
• Fix IntervalSets compat for RLEnvironments (#800) (@jeremiahpslewis)
• Bump RLZoo.jl version for release (#815) (@jeremiahpslewis)
• Fix RLExperiments compat (#816) (@jeremiahpslewis)
• Expand RLZoo compat (#817) (@jeremiahpslewis)
• Bump RLExperiments, require 0.11 (#818) (@jeremiahpslewis)
• Pin ReinforcementLearningZoo.jl to 0.6 in RLExperiments (#819) (@jeremiahpslewis)
• Drop RL.jl from CompatHelper (until refactor complete) (#824) (@jeremiahpslewis)
• Bump Github Actions cache version (#825) (@jeremiahpslewis)
• Basic allocation fixes for RandomWalk / RandomPolicy (#827) (@jeremiahpslewis)
• Bump CI.yml GitHub action versions (#828) (@jeremiahpslewis)
• Add tests, improve performance of RewardsPerEpisode (#829) (@jeremiahpslewis)
• Refactor and add tests to TotalBatchRewardPerEpisode (#830) (@jeremiahpslewis)
• Tests, refactor for TimePerStep (#831) (@jeremiahpslewis)
• DoEveryNStep tests, performance tweaks (#832) (@jeremiahpslewis)
• Add DoOnExit test (#833) (@jeremiahpslewis)
• Expand PR Template (#835) (@jeremiahpslewis)
• Fix branch name (master -> main) (#837) (@jeremiahpslewis)
• Add test_noop! to remaining hooks (#840) (@jeremiahpslewis)
• Make TimePerStep test robust (#841) (@jeremiahpslewis)
• Reactivate docs (#842) (@jeremiahpslewis)
• Add activate_devmode!() explanation to tips.md (#845) (@jeremiahpslewis)
• Bump compat of RL.jl to 0.11.0-dev (#846) (@jeremiahpslewis)
• add kwargs to agent (#847) (@HenriDeh)
• Gaussian network refactor and tests (#849) (@HenriDeh)
• Agent Refactor (#850) (@jeremiahpslewis)
• Bump RLCore (#851) (@jeremiahpslewis)
• Include codecov in CI (#854) (@HenriDeh)
• Fix a typo in MPO (#855) (@HenriDeh)
• DoEvery should not trigger on t = 1 (#856) (@HenriDeh)
• update CI Julia version (#857) (@jeremiahpslewis)
• Tweak CI to check on dep changes (#858) (@HenriDeh)
• CompatHelper: bump compat for FillArrays to 1 for package ReinforcementLearningCore, (keep existing compat) (#859) (@github-actions[bot])
• MultiAgent Proposal (#861) (@jeremiahpslewis)
• CompatHelper: add new compat entry for ReinforcementLearningCore at version 0.9 for package ReinforcementLearningEnvironments, (keep existing compat) (#865) (@github-actions[bot])
• Multiplayer Fixes (Clean up errors) (#867) (@jeremiahpslewis)
• Added a section to the home page about getting help for Reinforcement… (#868) (@LooseTerrifyingSpaceMonkey)
• Bump StatsBase compat (#873) (@jeremiahpslewis)
• ComposedHooks, MultiHook fixes (#874) (@jeremiahpslewis)
• Fix RLEnvs compat (#875) (@jeremiahpslewis)
• Add back ComposedStop (#876) (@jeremiahpslewis)
• Bump RLBase to v0.11.1 (#877) (@jeremiahpslewis)
• Further refinements (#879) (@jeremiahpslewis)
• Use multiple dispatch / methods plan! and act! (#880) (@jeremiahpslewis)
• RLCore.update! -> Base.push! API change (#884) (@jeremiahpslewis)
• Add compat for CommonRLInterface (#886) (@jeremiahpslewis)
• Fix hook issues (#887) (@jeremiahpslewis)
• CompatHelper: bump compat for ReinforcementLearningZoo to 0.6 for package ReinforcementLearningExperiments, (keep existing compat) (#888) (@github-actions[bot])
• Stacknamespace (#889) (@HenriDeh)
• allow more recent versions (#890) (@HenriDeh)
• Fix stack (#891) (@HenriDeh)
• CompatHelper: add new compat entry for DelimitedFiles at version 1 for package ReinforcementLearningEnvironments, (keep existing compat) (#894) (@github-actions[bot])
• Update implement new alg docs (#896) (@jeremiahpslewis)
• NFQ (#897) (@CasBex)
• fixed problem with sequential multi agent envs (#898) (@Mytolo)
• Sketch out optimise! refactor (#899) (@jeremiahpslewis)
• Bug fix optimise! (#902) (@jeremiahpslewis)
• Breaking changes to optimise! interface: Bump RLCore to v0.11 and RLZoo to v0.8 (#903) (@jeremiahpslewis)
• Swap out rng code (#905) (@jeremiahpslewis)
• CompatHelper: bump compat for NNlib to 0.9 for package ReinforcementLearningZoo, (keep existing compat) (#906) (@github-actions[bot])
• Fix dispatch and update documentation (#907) (@HenriDeh)
• QBasedPolicy optimise! forwards to learner. (#909) (@HenriDeh)
• Bump RLZoo version for NNlib (#911) (@jeremiahpslewis)
• Add performance testing run loop (#914) (@jeremiahpslewis)
• Fix Timer bug (#915) (@jeremiahpslewis)
• couple of improvements to MPO (#919) (@HenriDeh)
• Rework the run loop (#921) (@HenriDeh)
• adjusted pettingzoo to PettingZooEnv simultaneous environment more co… (#925) (@Mytolo)
• fixed devmode / project files (#932) (@Mytolo)
• fixed DQNLearner Gpu isse (#933) (@Mytolo)
• fixing prob. /w symbol/ string correspondence (#934) (@Mytolo)
• Bump flux compat (#935) (@jeremiahpslewis)
• Reduce find_all_max allocations and increase speed based on chatgpt s… (#938) (@jeremiahpslewis)
• Add Buildkite / GPU tests (#942) (@jeremiahpslewis)
• Add RLZoo and RLExperiments to Buildkite (#943) (@jeremiahpslewis)
• Drop deprecated @provide interface (#944) (@jeremiahpslewis)
• CI Improvements (#946) (@jeremiahpslewis)
• Github Actions Fixes (#947) (@jeremiahpslewis)
• gpu updates RLExperiments, RLZoo (#949) (@jeremiahpslewis)
• Bump RLCore version (#950) (@jeremiahpslewis)
• Refactor TRPO and VPG with EpisodesSampler (#952) (@HenriDeh)
• Fix TotalRewardPerEpisode bug (#953) (@jeremiahpslewis)
• update docs to loop refactor (#955) (@HenriDeh)
• CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningEnvironments, (keep existing compat) (#956) (@github-actions[bot])
• CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningZoo, (keep existing compat) (#957) (@github-actions[bot])
• CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningExperiments, (keep existing compat) (#958) (@github-actions[bot])
• CompatHelper: add new compat entry for cuDNN at version 1 for package ReinforcementLearningCore, (keep existing compat) (#962) (@github-actions[bot])
• CompatHelper: add new compat entry for cuDNN at version 1 for package ReinforcementLearningZoo, (keep existing compat) (#963) (@github-actions[bot])
• CompatHelper: add new compat entry for cuDNN at version 1 for package ReinforcementLearningExperiments, (keep existing compat) (#964) (@github-actions[bot])
• TargetNetwork (#966) (@HenriDeh)
• CompatHelper: bump compat for GPUArrays to 9 for package ReinforcementLearningCore, (keep existing compat) (#969) (@github-actions[bot])
• Prioritised DQN GPU (#974) (@CasBex)
• CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningZoo, (keep existing compat) (#975) (@github-actions[bot])
• CompatHelper: bump compat for ReinforcementLearningZoo to 0.8 for package ReinforcementLearningExperiments, (keep existing compat) (#976) (@github-actions[bot])
• CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningExperiments, (keep existing compat) (#977) (@github-actions[bot])
• Nfq refactor (#980) (@CasBex)
• Fix and refactor SAC (#985) (@HenriDeh)
• CompatHelper: bump compat for DomainSets to 0.7 for package ReinforcementLearningBase, (keep existing compat) (#986) (@github-actions[bot])
• remove rlenv dep for tests (#989) (@HenriDeh)
• CompatHelper: add new compat entry for CUDA at version 5 for package ReinforcementLearningExperiments, (keep existing compat) (#991) (@github-actions[bot])
• CompatHelper: add new compat entry for IntervalSets at version 0.7 for package ReinforcementLearningExperiments, (keep existing compat) (#994) (@github-actions[bot])
• Conservative Q-Learning (#995) (@HenriDeh)
• CompatHelper: add new compat entry for Parsers at version 2 for package ReinforcementLearningCore, (keep existing compat) (#997) (@github-actions[bot])
• CompatHelper: add new compat entry for MLUtils at version 0.4 for package ReinforcementLearningZoo, (keep existing compat) (#998) (@github-actions[bot])
• CompatHelper: add new compat entry for Statistics at version 1 for package ReinforcementLearningCore, (keep existing compat) (#999) (@github-actions[bot])
• Update CQL_SAC.jl (#1003) (@HenriDeh)
• Bump tj-actions/changed-files from 35 to 41 in /.github/workflows (#1006) (@dependabot[bot])
• Make it compatible with Adapt 4 and Metal 1 (#1008) (@joelreymont)
• Bump RLCore, RLEnv (#1012) (@jeremiahpslewis)
• Fix PPO per #1007 (#1013) (@jeremiahpslewis)
• Fix RLCore version (#1018) (@jeremiahpslewis)
• Add Devcontainer, handle DomainSets 0.7 (#1019) (@jeremiahpslewis)
• Initial GPUArray transition (#1020) (@jeremiahpslewis)
• Update TagBot.yml for subprojects (#1021) (@jeremiahpslewis)
• Fix offline agent test (#1025) (@joelreymont)
• Fix spell check CI errors (#1027) (@joelreymont)
• GPU Code Migration Part 2.1 (#1029) (@jeremiahpslewis)
• Bump RLZoo to v0.8 (#1031) (@jeremiahpslewis)
• Fix RLZoo version (#1032) (@jeremiahpslewis)
• Drop devmode, prepare RL.jl v0.11 for release (#1035) (@jeremiahpslewis)
• Update docs script for new 'limited' RL.jl release (#1038) (@jeremiahpslewis)
• Tabular Approximator fixes (pre v0.11 changes) (#1040) (@jeremiahpslewis)
• Swap RLZoo for RLFarm in CI, drop RLExperiments (#1041) (@jeremiahpslewis)
• Buildkite tweaks for monorepo (#1042) (@jeremiahpslewis)
• Drop archived projects (#1043) (@jeremiahpslewis)
• Simplify Experiment code after dropping RLExperiment (#1044) (@jeremiahpslewis)
• Fix code coverage scope so it ignores test dir (#1045) (@jeremiahpslewis)
• Fix reset and stop conditions (#1046) (@jeremiahpslewis)
• Drop Functors and use Flux.@layer (#1048) (@jeremiahpslewis)
• Fix naming consistency and add missing hook tests (#1049) (@jeremiahpslewis)
• Add SARS tdlearning back to lib (#1050) (@jeremiahpslewis)
• Update FluxModelApproximator references to FluxApproximator (#1051) (@jeremiahpslewis)
• Epsilon Speedy Explorer (#1052) (@jeremiahpslewis)
• Add TotalRewardPerEpisodeLastN hook (#1053) (@jeremiahpslewis)
• Fix abstract_learner for multiplayer games (#1054) (@jeremiahpslewis)
• Update versions (#1055) (@jeremiahpslewis)
• Update Docs for v0.11 release (#1056) (@jeremiahpslewis)
• Update Katex version, fix vulnerability (#1058) (@jeremiahpslewis)

Closed issues:

• A3C (#133)
• Implement TRPO/ACER (#134)
• ViZDoom is broken (#130)
• bullet3 environment (#128)
• Box2D environment (#127)
• Add MAgent (#125)
• Regret Policy Gradients (#131)
• Add MCTS related algorithms (#132)
• bsuite (#124)
• Implement Fully Parameterized Quantile Function for Distributional Reinforcement Learning. (#135)
• Experimental support of Torch.jl (#136)
• Add Game 2048 (#122)
• add CUDA accelerated Env (#121)
• Unify common network architectures and patterns (#139)
• Asynchronous Methods for Deep Reinforcement Learning (#142)
• R2D2 (#143)
• Recurrent Models (#144)
• Cross language support (#103)
• Add an example running in K8S (#100)
• Flux as service (#154)
• Change clip_by_global_norm! into a Optimizer (#193)
• Derivative-Free Reinforcement Learning (#206)
• Support Tables.jl and PrettyTables.jl for Trajectories (#232)
• Reinforcement Learning and Combinatorial Optimization (#250)
• Model based reinforcement learning (#262)
• Support CircularVectorSARTTrajectory RLZoo (#316)
• Rename some functions to help beginners navigate source code (#326)
• Support multiple discrete action space (#347)
• Combine transformers and RL (#392)
• How to display/render AtariEnv? (#546)
• Refactor of DQN Algorithms (#557)
• JuliaRL_BasicDQN_CartPole example fails (#568)
• Gain in VPGPolicy does not account for terminal states? (#578)
• Question: Can ReinforcementLearning.jl handle Partially Observed Markov Processes (POMDPs)? (#608)
• Explain current implementation of PPO in detail (#620)
• Make documentation on trace normalization (#633)
• TDLearner time step parameter (#648)
• estimate v.s. basis in policies (#677)
• Q-learning update timing (#702)
• various eligibility trace-equipped TD methods (#709)
• Improve the logging mechanism during training (#725)
• questions while looking at implementation of VPG (#729)
• SAC example experiment does not work (#736)
• Custom environment action and state space explanation (#738)
• how to load a saved model and test it? (#755)
• Bounds Error at UPDATE_FREQ Step (#758)
• StopAfterEpisode returns 1 more episode using StepsPerEpisode() hook (#759)
• Move basic definition of environment wrapper into RLBase (#760)
• Precompilation error - DomainSets not in dependencies (#761)
• How to set RLBase.state_space() if the number of state space is uncertain (#762)
• how to use MultiAgentManager on different algorithms? (#764)
• Example run of Offline RL that totally depends on dataset without online environment (#765)
• Deep RL example for LSTM (#772)
• MonteCarloLearner incorrect PreActStage behavior (#779)
• Prioritised Experience Replay (#780)
• Outdated dependencies (#781)
• Running experiments throws a "UndefVarError: params not defined" message (#784)
• Failing MPOCovariance experiment (#791)
• Logo image was not found (#836)
• Reactivate docs on CI/CD (#838)
• update docs: Tips for developers (#844)
• Package dependencies not compatible (#860)
• need help from an expert (#862)
• Installing ReinforcementLearning.jl downgrades Flux.jl (#864)
• Fix Experiment type setup (#881)
• LoadError: UndefVarError: params not defined (#882)
• Rename update! to push! (#883)
• Contribute Neural Fitted Q-iteration algorithm (#895)
• PPo policy experiments failing (#910)
• Executing RLBase.plan! after end of experiment (#913)
• EpisodeSampler in Trajectories (#927)
• Hook RewardsPerEpisode broken (#945)
• Can implement this ARZ algorithm ? (#965)
• AssertionError: action in env.action_space (#967)
• Fixing SAC Policy (#970)
• Prioritized DQN experiment nonfunctional (#971)
• Prioritised DQN failing on GPU (#973)
• An error (#983)
• params() is no longer supported in Flux (#996)
• GPU Compile error on PPO with MaskedPPOTrajectory (#1007)
• RL Core tests fail sporadically (#1010)
• RL Env tests fail with latest OpenSpiel patches (#1011)
• Tutorial OpenSpiel KuhnOpenNSFP fails (#1024)
• CI: Should spell check be dropped or fixed? (#1026)
• Simple ReinforcementLearning example crashes (#1034)
• Website: How do implement a new algorithm is outdated (#1037)
• Review TabularApproximator (#1039)

ReinforcementLearningEnvironments ReinforcementLearningEnvironments-v0.9.0

Diff since ReinforcementLearningEnvironments-v0.8.8

Merged pull requests:

• Bump RLZoo to v0.8 (#1031) (@jeremiahpslewis)
• Fix RLZoo version (#1032) (@jeremiahpslewis)
• Drop devmode, prepare RL.jl v0.11 for release (#1035) (@jeremiahpslewis)
• Update docs script for new 'limited' RL.jl release (#1038) (@jeremiahpslewis)
• Tabular Approximator fixes (pre v0.11 changes) (#1040) (@jeremiahpslewis)
• Swap RLZoo for RLFarm in CI, drop RLExperiments (#1041) (@jeremiahpslewis)
• Buildkite tweaks for monorepo (#1042) (@jeremiahpslewis)
• Drop archived projects (#1043) (@jeremiahpslewis)
• Simplify Experiment code after dropping RLExperiment (#1044) (@jeremiahpslewis)
• Fix code coverage scope so it ignores test dir (#1045) (@jeremiahpslewis)
• Fix reset and stop conditions (#1046) (@jeremiahpslewis)
• Drop Functors and use Flux.@layer (#1048) (@jeremiahpslewis)
• Fix naming consistency and add missing hook tests (#1049) (@jeremiahpslewis)
• Add SARS tdlearning back to lib (#1050) (@jeremiahpslewis)
• Update FluxModelApproximator references to FluxApproximator (#1051) (@jeremiahpslewis)
• Epsilon Speedy Explorer (#1052) (@jeremiahpslewis)
• Add TotalRewardPerEpisodeLastN hook (#1053) (@jeremiahpslewis)
• Fix abstract_learner for multiplayer games (#1054) (@jeremiahpslewis)
• Update versions (#1055) (@jeremiahpslewis)
• Update Docs for v0.11 release (#1056) (@jeremiahpslewis)
• Update Katex version, fix vulnerability (#1058) (@jeremiahpslewis)

Closed issues:

• Simple ReinforcementLearning example crashes (#1034)
• Website: How do implement a new algorithm is outdated (#1037)
• Review TabularApproximator (#1039)

ReinforcementLearningCore ReinforcementLearningCore-v0.15.0

Diff since ReinforcementLearningCore-v0.14.0

Merged pull requests:

• Bump RLZoo to v0.8 (#1031) (@jeremiahpslewis)
• Fix RLZoo version (#1032) (@jeremiahpslewis)
• Drop devmode, prepare RL.jl v0.11 for release (#1035) (@jeremiahpslewis)
• Update docs script for new 'limited' RL.jl release (#1038) (@jeremiahpslewis)
• Tabular Approximator fixes (pre v0.11 changes) (#1040) (@jeremiahpslewis)
• Swap RLZoo for RLFarm in CI, drop RLExperiments (#1041) (@jeremiahpslewis)
• Buildkite tweaks for monorepo (#1042) (@jeremiahpslewis)
• Drop archived projects (#1043) (@jeremiahpslewis)
• Simplify Experiment code after dropping RLExperiment (#1044) (@jeremiahpslewis)
• Fix code coverage scope so it ignores test dir (#1045) (@jeremiahpslewis)
• Fix reset and stop conditions (#1046) (@jeremiahpslewis)
• Drop Functors and use Flux.@layer (#1048) (@jeremiahpslewis)
• Fix naming consistency and add missing hook tests (#1049) (@jeremiahpslewis)
• Add SARS tdlearning back to lib (#1050) (@jeremiahpslewis)
• Update FluxModelApproximator references to FluxApproximator (#1051) (@jeremiahpslewis)
• Epsilon Speedy Explorer (#1052) (@jeremiahpslewis)
• Add TotalRewardPerEpisodeLastN hook (#1053) (@jeremiahpslewis)
• Fix abstract_learner for multiplayer games (#1054) (@jeremiahpslewis)
• Update versions (#1055) (@jeremiahpslewis)
• Update Docs for v0.11 release (#1056) (@jeremiahpslewis)
• Update Katex version, fix vulnerability (#1058) (@jeremiahpslewis)

Closed issues:

• Simple ReinforcementLearning example crashes (#1034)
• Website: How do implement a new algorithm is outdated (#1037)
• Review TabularApproximator (#1039)

ReinforcementLearningBase ReinforcementLearningBase-v0.13.0

Diff since ReinforcementLearningBase-v0.12.2

Merged pull requests:

• Fix offline agent test (#1025) (@joelreymont)
• Fix spell check CI errors (#1027) (@joelreymont)
• GPU Code Migration Part 2.1 (#1029) (@jeremiahpslewis)
• Bump RLZoo to v0.8 (#1031) (@jeremiahpslewis)
• Fix RLZoo version (#1032) (@jeremiahpslewis)
• Drop devmode, prepare RL.jl v0.11 for release (#1035) (@jeremiahpslewis)
• Update docs script for new 'limited' RL.jl release (#1038) (@jeremiahpslewis)
• Tabular Approximator fixes (pre v0.11 changes) (#1040) (@jeremiahpslewis)
• Swap RLZoo for RLFarm in CI, drop RLExperiments (#1041) (@jeremiahpslewis)
• Buildkite tweaks for monorepo (#1042) (@jeremiahpslewis)
• Drop archived projects (#1043) (@jeremiahpslewis)
• Simplify Experiment code after dropping RLExperiment (#1044) (@jeremiahpslewis)
• Fix code coverage scope so it ignores test dir (#1045) (@jeremiahpslewis)
• Fix reset and stop conditions (#1046) (@jeremiahpslewis)
• Drop Functors and use Flux.@layer (#1048) (@jeremiahpslewis)
• Fix naming consistency and add missing hook tests (#1049) (@jeremiahpslewis)
• Add SARS tdlearning back to lib (#1050) (@jeremiahpslewis)
• Update FluxModelApproximator references to FluxApproximator (#1051) (@jeremiahpslewis)
• Epsilon Speedy Explorer (#1052) (@jeremiahpslewis)
• Add TotalRewardPerEpisodeLastN hook (#1053) (@jeremiahpslewis)
• Fix abstract_learner for multiplayer games (#1054) (@jeremiahpslewis)
• Update versions (#1055) (@jeremiahpslewis)
• Update Docs for v0.11 release (#1056) (@jeremiahpslewis)
• Update Katex version, fix vulnerability (#1058) (@jeremiahpslewis)

Closed issues:

• RL Core tests fail sporadically (#1010)
• Tutorial OpenSpiel KuhnOpenNSFP fails (#1024)
• CI: Should spell check be dropped or fixed? (#1026)
• Simple ReinforcementLearning example crashes (#1034)
• Website: How do implement a new algorithm is outdated (#1037)
• Review TabularApproximator (#1039)

ReinforcementLearningExperiments ReinforcementLearningExperiments-v0.4.0

Merged pull requests:

• Fix deprecations (#10) (@femtocleaner[bot])
• implement epsilon-greedy policy with parametric type (#12) (@jbrea)
• improve docs (#13) (@jbrea)
• refactor policies (#15) (@jbrea)
• Add ReinforcementLearningBase as dependent (#16) (@jbrea)
• fix examples (#18) (@jbrea)
• refactor existing components (#26) (@findmyway)
• Prioritized dqn (#29) (@findmyway)
• add double dqn (#30) (@findmyway)
• add rainbow (#31) (@findmyway)
• use new api in ReinforcementLearningEnvironments.jl (#33) (@findmyway)
• bugfix and api simplification (#34) (@findmyway)
• Switch Tracker.jl to Zygote.jl (#37) (@findmyway)
• Support both Knet and Flux(with Zygote) (#38) (@findmyway)
• add docs (#39) (@findmyway)
• export AbstractActionSelector and add more comments (#42) (@findmyway)
• Refactor buffer (#45) (@findmyway)
• fix example in doc && update examples (#46) (@findmyway)
• fix a performance bug in rainbow (#47) (@findmyway)
• update dependencies (#48) (@findmyway)
• update dependencies and docs (#49) (@findmyway)
• update benchmark for circular_array_buffer (#50) (@findmyway)
• Install TagBot as a GitHub Action (#53) (@JuliaTagBot)
• clean up code (#54) (@findmyway)
• add compat (#55) (@findmyway)
• CompatHelper: add new compat entry for "Reexport" at version "0.2" (#56) (@github-actions[bot])
• add documentation stage in travis (#57) (@findmyway)
• Add doc in travis (#58) (@findmyway)
• Fix link in docs/src/index.md (#60) (@amanbh)
• Update doc (#61) (@findmyway)
• Update README.md & website link (#70) (@findmyway)
• Update dependency (#78) (@findmyway)
• MassInstallAction: Install the CompatHelper workflow on this repository (#99) (@findmyway)
• CompatHelper: bump compat for "Reexport" to "1.0" (#172) (@github-actions[bot])
• update dependency (#177) (@findmyway)
• Add Dockerfile (#187) (@findmyway)
• Update readme (#188) (@findmyway)
• docs: add findmyway as a contributor (#189) (@allcontributors[bot])
• docs: add drozzy as a contributor (#195) (@allcontributors[bot])
• docs: add rcnlee as a contributor (#199) (@allcontributors[bot])
• docs: add norci as a contributor (#200) (@allcontributors[bot])
• docs: add xiruizhao as a contributor (#203) (@allcontributors[bot])
• docs: add metab0t as a contributor (#204) (@allcontributors[bot])
• docs: add albheim as a contributor (#207) (@allcontributors[bot])
• docs: add michelangelo21 as a contributor (#214) (@allcontributors[bot])
• docs: add pilgrimygy as a contributor (#216) (@allcontributors[bot])
• docs: add Mobius1D as a contributor (#218) (@allcontributors[bot])
• docs: add ilancoulon as a contributor (#224) (@allcontributors[bot])
• docs: add pilgrimygy as a contributor (#230) (@allcontributors[bot])
• docs: add JinraeKim as a contributor (#243) (@allcontributors[bot])
• Prepare v0.9 (#252) (@findmyway)
• docs: add luigiannelli as a contributor (#254) (@allcontributors[bot])
• docs: add JBoerma as a contributor (#255) (@allcontributors[bot])
• CompatHelper: bump compat for "ReinforcementLearningEnvironments" to "0.5" (#260) (@github-actions[bot])
• Fix inconsitencies in wrappers (#263) (@albheim)
• setup CI for each subpackages (#264) (@findmyway)
• Fix atari experiments (#265) (@Mobius1D)
• Add timeperstep hook to qrdqn to fix test error (#266) (@albheim)
• Update Flux version (#267) (@findmyway)
• Setup docs generation pipeline (#269) (@findmyway)
• Misc doc related fixes (#270) (@findmyway)
• Update README.md (#271) (@findmyway)
• docs: add JinraeKim as a contributor (#272) (@allcontributors[bot])
• Improve docs GitHub action (#273) (@findmyway)
• Fix docs pipeline (#275) (@findmyway)
• update readme (#276) (@findmyway)
• CompatHelper: add new compat entry for "UnicodePlots" at version "1.3" for package ReinforcementLearningCore (#277) (@github-actions[bot])
• CompatHelper: bump compat for "Distributions" to "0.25" for package ReinforcementLearningCore (#278) (@github-actions[bot])
• CompatHelper: bump compat for "Distributions" to "0.25" for package ReinforcementLearningZoo (#279) (@github-actions[bot])
• docs: add plu70n as a contributor (#282) (@allcontributors[bot])
• Fix bug in CI (#283) (@findmyway)
• Use Weave.jl to generate RLExperiments (#284) (@findmyway)
• QRDQN experiment reproducibility fix (#294) (@ashwani-rathee)
• Add Manifest.toml (#295) (@findmyway)
• docs: add ashwani-rathee as a contributor (#296) (@allcontributors[bot])
• Add basic doc structure (#300) (@findmyway)
• Update guide (#302) (@findmyway)
• Update experiments (#303) (@findmyway)
• fix figs (#304) (@findmyway)
• Fix some simple experiments (#308) (@findmyway)
• add plotting for cartpole and mountaincar with Plots.jl (#309) (@jamblejoe)
• Remove GR in RLEnvs (#310) (@findmyway)
• docs: add jamblejoe as a contributor (#311) (@allcontributors[bot])
• Add compat of [email protected] in ReinforcementLearningExperiments (#312) (@findmyway)
• Add example of SimplexSpace (#313) (@findmyway)
• Improve tutorial (#314) (@findmyway)
• Fix Atari related experiments (#315) (@findmyway)
• CompatHelper: add new compat entry for "ImageTransformations" at version "0.8" for package ReinforcementLearningExperiments (#317) (@github-actions[bot])
• CompatHelper: add new compat entry for "ArcadeLearningEnvironment" at version "0.2" for package ReinforcementLearningExperiments (#318) (@github-actions[bot])
• CompatHelper: add new compat entry for "CUDA" at version "3" for package ReinforcementLearningExperiments (#319) (@github-actions[bot])
• update tips (#321) (@findmyway)
• CompatHelper: bump compat for "GPUArrays" to "7" for package ReinforcementLearningCore (#322) (@github-actions[bot])
• docs: add albheim as a contributor for doc (#323) (@allcontributors[bot])
• Fix broken test (#325) (@Mobius1D)
• Add a warning in docstring of state (#327) (@findmyway)
• Update doc string of PrioritizedDQNLearner (#329) (@findmyway)
• Expand DDPG to multi action spaces (#330) (@Mobius1D)
• CompatHelper: bump compat for "StructArrays" to "0.6" for package ReinforcementLearningZoo (#331) (@github-actions[bot])
• fix 332 (#333) (@findmyway)
• correct spelling in FAQ (#334) (@ultradian)
• docs: add ultradian as a contributor for doc (#335) (@allcontributors[bot])
• fix typo (#338) (@findmyway)
• docs: add eltociear as a contributor for doc (#339) (@allcontributors[bot])
• CompatHelper: bump compat for "FillArrays" to "0.12" for package ReinforcementLearningCore (#340) (@github-actions[bot])
• Add copyto function (#345) (@pilgrimygy)
• add Base.:(==) and Base.hash for AbstractEnv and test nash_conv on KuhnPokerEnv (#348) (@peterchen96)
• Fix legal_actions_mask indexing error in CircularSLART (#350) (@findmyway)
• bump version of RLCore (#351) (@findmyway)
• bump version of RLBae (#352) (@findmyway)
• add LICENSE in RLBase (#353) (@findmyway)
• bump version of RLZoo (#355) (@findmyway)
• docs: add 00krishna as a contributor for bug (#356) (@allcontributors[bot])
• Add the tuning entropy component (#365) (@pilgrimygy)
• Make general components (#370) (@pilgrimygy)
• add weighted_softmax_explorer in the explorers.jl (#382) (@peterchen96)
• Supplement functions in ReservoirTrajectory and BehaviorCloningPolicy (#390) (@peterchen96)
• Update Flux version (#391) (@findmyway)
• AddSequentialEnv (#394) (@findmyway)
• Throw error in MultiAgentManager if it is applied to a SIMULTANEOUS env (#395) (@findmyway)
• docs: add pkienscherf as a contributor for bug (#396) (@allcontributors[bot])
• Implementation of NFSP and NFSP_KuhnPoker experiment (#402) (@peterchen96)
• Updated RLDatasets.jl (#403) (@Mobius1D)
• Gym d4rl extension (#405) (@Mobius1D)
• updates as per GridWorlds v0.5.0 (#406) (@Sid-Bhatia-0)
• Reduce allocations and update docstring for GaussianNetwork (#414) (@albheim)
• Fix a bug (#415) (@pilgrimygy)
• Expand to d4rl-pybullet (#416) (@Mobius1D)
• docs: add pilgrimygy as a contributor for bug (#417) (@allcontributors[bot])
• Fix 418 (#420) (@findmyway)
• docs: add Krastanov as a contributor for doc (#422) (@allcontributors[bot])
• Make SAC policy use internal rng (#423) (@albheim)
• Add wrapped_env[!] to access env inside wrappers (#426) (@albheim)
• add stock trading env (#428) (@findmyway)
• Add Atari datasets released by Google Research (#429) (@Mobius1D)
• add kwargs to plot(env::) (#430) (@jamblejoe)
• Unify parameter names (#437) (@pilgrimygy)
• docs: add albheim as a contributor for maintenance (#438) (@allcontributors[bot])
• correct nfsp implementation (#439) (@peterchen96)
• update the nfsp experiment's parameters (#440) (@peterchen96)
• Tiny text typo (#441) (@Nthman)
• docs: add LaarsOman as a contributor for doc (#442) (@allcontributors[bot])
• Add pre-train step; VAE component; CRR and PLAS algorithms (#443) (@pilgrimygy)
• add MADDPG algorithm (#444) (@peterchen96)
• add_Graph_Shortest_Path (#445) (@findmyway)
• try to fix bugs of ActionTransformedEnv (#447) (@peterchen96)
• Update report (#448) (@pilgrimygy)
• Summer ospp project 210370190 mid-term report (#449) (@peterchen96)
• add maxdepth kwarg to remove print_tree() deprecation warning (#450) (@burmecia)
• docs: add burmecia as a contributor for code (#451) (@allcontributors[bot])
• RL unplugged implementation with tests (#452) (@Mobius1D)
• Update report (#453) (@Mobius1D)
• disable notebook generation (#454) (@johnnychen94)
• Revert "Update report" (#456) (@findmyway)
• Update report (#457) (@pilgrimygy)
• fix installation docs (#458) (@Mobius1D)
• docs: add peterchen96 as a contributor for code, doc (#459) (@allcontributors[bot])
• Create LICENSE (#461) (@Mobius1D)
• Add docs (#462) (@Mobius1D)
• Fix make.jl (#463) (@Mobius1D)
• Delete LICENSE (#465) (@Mobius1D)
• fix CI (#466) (@findmyway)
• Fix RLDatasets.jl documentation (#467) (@Mobius1D)
• update report (#468) (@peterchen96)
• Fix ci (#469) (@Mobius1D)
• Update maddpg and the report (#470) (@peterchen96)
• Report (#474) (@pilgrimygy)
• Control whether run displays description of experiment (#477) (@ShuhuaGao)
• docs: add ShuhuaGao as a contributor for code, question (#478) (@allcontributors[bot])
• Chancestyle doc update (#479) (@ShuhuaGao)
• FisherBRC algorithm and update docs (#480) (@pilgrimygy)
• Add the experiment of MADDPG. (#481) (@peterchen96)
• Add bsuite datasets (#482) (@Mobius1D)
• update report and add reward bonus (#483) (@pilgrimygy)
• Update manifest (#484) (@Mobius1D)
• add GPU support for GaussianNetwork, fix #455 (#486) (@burmecia)
• Update experiments of maddpg (#487) (@peterchen96)
• Update prob function of QBasedPolicy. (#488) (@peterchen96)
• Update report. (#489) (@peterchen96)
• Fix gsutil for windows and fix docs (#491) (@Mobius1D)
• add vmpo algorithm (#492) (@burmecia)
• update vae (#494) (@pilgrimygy)
• Add dm datasets (#495) (@Mobius1D)
• Play OpenSpiel envs with NFSP and try to add ED algorithm. (#496) (@peterchen96)
• fix bug (#497) (@pilgrimygy)
• Update BEAR algorithm (#498) (@pilgrimygy)
• More efficient float32 randn (#499) (@albheim)
• Add support for deep ope in RLDatasets.jl (#500) (@Mobius1D)
• update BCQ (#501) (@pilgrimygy)
• update discrete BCQ (#502) (@pilgrimygy)
• update offline RL experiment (#507) (@pilgrimygy)
• Update ED algorithm and the report. (#508) (@peterchen96)
• cpu and gpu test (#509) (@pilgrimygy)
• Fix dispatch for is_discrete_space (#510) (@johannes-fischer)
• docs: add johannes-fischer as a contributor for code (#511) (@allcontributors[bot])
• update report (#512) (@pilgrimygy)
• update report (#513) (@peterchen96)
• Fix random net init in sac example (#514) (@albheim)
• WIP to implement FQE (#515) (@Mobius1D)
• OSPP Report for RLDatasets.jl (#516) (@Mobius1D)
• Update report (#518) (@Mobius1D)
• Update reward wrappers to be more consistent (#519) (@albheim)
• fixed findmax unconsistency (#521) (@3rdCore)
• docs: add 3rdCore as a contributor for bug, code (#522) (@allcontributors[bot])
• close #493 (#523) (@findmyway)
• Update compat & version (#524) (@findmyway)
• Fix rlexps (#525) (@findmyway)
• Bump rlenvs (#526) (@findmyway)
• close #527 (#528) (@bhatiaabhinav)
• docs: add bhatiaabhinav as a contributor for bug, code (#529) (@allcontributors[bot])
• Refine the doc and make minor changes of TabularApproximator (#532) (@ShuhuaGao)
• Fix bug in MaskedPPOTrajectory (#533) (@findmyway)
• bugfix with ZeroTo (#534) (@findmyway)
• Revert unexpected change in PPO (#535) (@findmyway)
• Fix 530 (#536) (@findmyway)
• Improves plotting for classical control experiments (#537) (@harwiltz)
• Fix rldatasets (#538) (@findmyway)
• docs: add harwiltz as a contributor for code, doc (#539) (@allcontributors[bot])
• Bump version (#540) (@findmyway)
• fix RLIntro#63 (#541) (@findmyway)
• fix RLIntro#64 (#542) (@findmyway)
• Added a continuous option for CartPoleEnv (#543) (@dylan-asmar)
• docs: add dylan-asmar as a contributor for code (#544) (@allcontributors[bot])
• Bump version (#545) (@findmyway)
• Fix bug in cart pole float32 (#547) (@findmyway)
• Update links to RLIntro (#548) (@findmyway)
• Make experiments GPU compatible (#549) (@findmyway)
• Add compat (#550) (@findmyway)
• Bugfix with cart pole env (#552) (@findmyway)
• make bc gpu compatable (#553) (@findmyway)
• docs: add andreyzhitnikov as a contributor for bug (#554) (@allcontributors[bot])
• Small typo (#555) (@kir0ul)
• docs: add kir0ul as a contributor for doc (#556) (@allcontributors[bot])
• Fix/rand dummy action (#559) (@mo8it)
• Fix warning about kwargs.data (#560) (@mo8it)
• docs: add Mo8it as a contributor for code (#561) (@allcontributors[bot])
• Fix dummy action for continuous action spaces (#562) (@mo8it)
• Fix/rand interval (#563) (@mo8it)
• Remove unneeded method (#564) (@mo8it)
• Fix typo in ospp_final_term_report_210370741/index.md (#565) (@eltociear)
• Fix 566 (#567) (@findmyway)
• Fix documentation for environments (#570) (@blegat)
• docs: add blegat as a contributor for doc (#571) (@allcontributors[bot])
• fix #569 (#573) (@findmyway)
• CompatHelper: bump compat for "ArrayInterface" to "4" for package ReinforcementLearningCore (#574) (@github-actions[bot])
• bump version of RLCore and RLZoo (#576) (@findmyway)
• Update EpsilonGreedyExplorer example (#577) (@kir0ul)
• CompatHelper: bump compat for "FillArrays" to "0.13" for package ReinforcementLearningCore (#583) (@github-actions[bot])
• Default qnetwork initializer (#586) (@HenriDeh)
• docs: add HenriDeh as a contributor for code, doc (#587) (@allcontributors[bot])
• using act_limit parameter in target_actor (#588) (@NPLawrence)
• docs: add NPLawrence as a contributor for code (#589) (@allcontributors[bot])
• CompatHelper: bump compat for "ArrayInterface" to "5" for package ReinforcementLearningCore (#590) (@github-actions[bot])
• Fix documentation typo (#591) (@kir0ul)
• Fixing and generalizing GaussianNetwork (#592) (@HenriDeh)
• Fix typos in docs (#593) (@bileamScheuvens)
• docs: add bileamScheuvens as a contributor for doc (#594) (@allcontributors[bot])
• Add CovGaussianNetwork to work with covariance (#597) (@HenriDeh)
• Fixing Gaussian Network gradient (#598) (@HenriDeh)
• Update Supporting (#599) (@findmyway)
• docs: add harwiltz as a contributor for bug (#601) (@allcontributors[bot])
• Rewrite initialization of StackFrames (#602) (@findmyway)
• fix test logdetLorU with Float64 (#603) (@HenriDeh)
• WIP: Add MPO in zoo (#604) (@HenriDeh)
• fix #605 (#606) (@findmyway)
• docs: add jarbus as a contributor for bug (#607) (@allcontributors[bot])
• Add a reward normalizer (#609) (@HenriDeh)
• Episode reset condition (#621) (@HenriDeh)
• cspell add Optimise (#622) (@HenriDeh)
• Add a categorical Network (#625) (@HenriDeh)
• write doc (#627) (@HenriDeh)
• fix #624 (#628) (@findmyway)
• docs: add tyleringebrand as a contributor for bug (#629) (@allcontributors[bot])
• Update How_to_implement_a_new_algorithm.md (#630) (@HenriDeh)
• add a new notebook (#631) (@findmyway)
• Use Trajectories.jl instead (#632) (@findmyway)
• created fallback implementation for legal_action_space_mask (#644) (@baedan)
• update node version (#645) (@findmyway)
• docs: add baedan as a contributor for code (#646) (@allcontributors[bot])
• Tag the latest code as v0.10.1 (#647) (@findmyway)
• added basic doc for TDLearner (#649) (@baedan)
• Add JuliaRL_DQN_CartPole (#650) (@findmyway)
• enable OpenSpiel (#691) (@findmyway)
• Small improvements for TicTacToeEnv (#692) (@jonathan-laurent)
• Update the "how to implement a new algorithm" (#695) (@HenriDeh)
• Fix typo in algorithm implementation docs (#697) (@mplemay)
• add PrioritizedDQN (#698) (@findmyway)
• add QRDQN (#699) (@findmyway)
• add REMDQN (#708) (@findmyway)
• add IQN (#710) (@findmyway)
• checkin Mainifest.toml (#711) (@findmyway)
• CompatHelper: bump compat for "ReinforcementLearningCore" to "0.8" (#712) (@github-actions[bot])
• CompatHelper: bump compat for "ReinforcementLearningEnvironments" to "0.6" (#713) (@github-actions[bot])
• CompatHelper: bump compat for "ReinforcementLearningZoo" to "0.5" (#714) (@github-actions[bot])
• CompatHelper: bump compat for "AbstractTrees" to "0.4" for package ReinforcementLearningBase (#715) (@github-actions[bot])
• CompatHelper: bump compat for "Functors" to "0.3" for package ReinforcementLearningCore (#717) (@github-actions[bot])
• CompatHelper: bump compat for "UnicodePlots" to "3" for package ReinforcementLearningCore (#718) (@github-actions[bot])
• CompatHelper: bump compat for "ReinforcementLearningCore" to "0.8" for package ReinforcementLearningZoo (#720) (@github-actions[bot])
• CompatHelper: bump compat for "Functors" to "0.3" for package ReinforcementLearningZoo (#721) (@github-actions[bot])
• CompatHelper: add new compat entry for "StableRNGs" at version "1" for package ReinforcementLearningExperiments (#722) (@github-actions[bot])
• CompatHelper: bump compat for "ReinforcementLearning" to "0.10" for package ReinforcementLearningExperiments (#723) (@github-actions[bot])
• add rainbow (#724) (@findmyway)
• Adapted SAC to support MultiThreadedEnv (#726) (@BigFood2307)
• Add the number of episodes (#727) (@ll7)
• docs: add ll7 as a contributor for doc (#728) (@allcontributors[bot])
• Add struct view (#732) (@findmyway)
• add VPG (#733) (@findmyway)
• CompatHelper: add new compat entry for "Distributions" at version "0.25" for package ReinforcementLearningZoo (#734) (@github-actions[bot])
• CompatHelper: add new compat entry for "Distributions" at version "0.25" for package ReinforcementLearningExperiments (#735) (@github-actions[bot])
• fixed hyperlink in readme (#742) (@mplemay)
• docs: add mplemay as a contributor for doc (#743) (@allcontributors[bot])
• Create FUNDING.yml (#746) (@findmyway)
• TRPO (#747) (@baedan)
• CompatHelper: bump compat for "CommonRLSpaces" to "0.2" for package ReinforcementLearningBase (#748) (@github-actions[bot])
• Fix parameter names for AsyncTrajectoryStyle (#749) (@ludvigk)
• Update DoEveryNEpisode hook to new api (#750) (@ludvigk)
• docs: add ludvigk as a contributor for code (#751) (@allcontributors[bot])
• Update TwinNetwork (#752) (@ludvigk)
• Typo in hooks docs (#754) (@kir0ul)
• CommonRLSpace -> DomainSets (#756) (@findmyway)
• Fix typo (#767) (@jeremiahpslewis)
• Fix typo (#768) (@jeremiahpslewis)
• Fix TD Learner so that it handles MultiAgent/Simultaneous with NoOp (#769) (@jeremiahpslewis)
• Bump RLBase compat to 0.11 (#771) (@HenriDeh)
• Remove manifest from the repo (#773) (@HenriDeh)
• import params and gradient (#774) (@HenriDeh)
• fix compat (#775) (@HenriDeh)
• Trying to reimplement experiments (#776) (@HenriDeh)
• Add a developer mode (#777) (@HenriDeh)
• added pettingzoo and one single agent example (#782) (@Mytolo)
• Update mpo.jl (#783) (@HenriDeh)
• Reduce unnecessary array allocations (#785) (@jeremiahpslewis)
• Temporarily disable failing experiment so project tests pass (#787) (@jeremiahpslewis)
• Fix spellcheck errors (#788) (@jeremiahpslewis)
• Bug fixes and dependency bump (#789) (@jeremiahpslewis)
• Reactivate some tests for RLExperiments (#790) (@jeremiahpslewis)
• Pin ReinforcementLearning.jl to pre-refactor versions (#793) (@jeremiahpslewis)
• Update TagBot.yml (#794) (@jeremiahpslewis)
• Drop RL.jl as dependency from Experiments (#795) (@jeremiahpslewis)
• Fix compat for RLBase (#796) (@jeremiahpslewis)
• Fix RLCore version, prep for bump (#797) (@jeremiahpslewis)
• Add reexport compat (#798) (@jeremiahpslewis)
• Bump compat helper (#799) (@jeremiahpslewis)
• Fix IntervalSets compat for RLEnvironments (#800) (@jeremiahpslewis)
• Bump RLZoo.jl version for release (#815) (@jeremiahpslewis)
• Fix RLExperiments compat (#816) (@jeremiahpslewis)
• Expand RLZoo compat (#817) (@jeremiahpslewis)
• Bump RLExperiments, require 0.11 (#818) (@jeremiahpslewis)
• Pin ReinforcementLearningZoo.jl to 0.6 in RLExperiments (#819) (@jeremiahpslewis)
• Drop RL.jl from CompatHelper (until refactor complete) (#824) (@jeremiahpslewis)
• Bump Github Actions cache version (#825) (@jeremiahpslewis)
• Basic allocation fixes for RandomWalk / RandomPolicy (#827) (@jeremiahpslewis)
• Bump CI.yml GitHub action versions (#828) (@jeremiahpslewis)
• Add tests, improve performance of RewardsPerEpisode (#829) (@jeremiahpslewis)
• Refactor and add tests to TotalBatchRewardPerEpisode (#830) (@jeremiahpslewis)
• Tests, refactor for TimePerStep (#831) (@jeremiahpslewis)
• DoEveryNStep tests, performance tweaks (#832) (@jeremiahpslewis)
• Add DoOnExit test (#833) (@jeremiahpslewis)
• Expand PR Template (#835) (@jeremiahpslewis)
• Fix branch name (master -> main) (#837) (@jeremiahpslewis)
• Add test_noop! to remaining hooks (#840) (@jeremiahpslewis)
• Make TimePerStep test robust (#841) (@jeremiahpslewis)
• Reactivate docs (#842) (@jeremiahpslewis)
• Add activate_devmode!() explanation to tips.md (#845) (@jeremiahpslewis)
• Bump compat of RL.jl to 0.11.0-dev (#846) (@jeremiahpslewis)
• add kwargs to agent (#847) (@HenriDeh)
• Gaussian network refactor and tests (#849) (@HenriDeh)
• Agent Refactor (#850) (@jeremiahpslewis)
• Bump RLCore (#851) (@jeremiahpslewis)
• Include codecov in CI (#854) (@HenriDeh)
• Fix a typo in MPO (#855) (@HenriDeh)
• DoEvery should not trigger on t = 1 (#856) (@HenriDeh)
• update CI Julia version (#857) (@jeremiahpslewis)
• Tweak CI to check on dep changes (#858) (@HenriDeh)
• CompatHelper: bump compat for FillArrays to 1 for package ReinforcementLearningCore, (keep existing compat) (#859) (@github-actions[bot])
• MultiAgent Proposal (#861) (@jeremiahpslewis)
• CompatHelper: add new compat entry for ReinforcementLearningCore at version 0.9 for package ReinforcementLearningEnvironments, (keep existing compat) (#865) (@github-actions[bot])
• Multiplayer Fixes (Clean up errors) (#867) (@jeremiahpslewis)
• Added a section to the home page about getting help for Reinforcement… (#868) (@LooseTerrifyingSpaceMonkey)
• Bump StatsBase compat (#873) (@jeremiahpslewis)
• ComposedHooks, MultiHook fixes (#874) (@jeremiahpslewis)
• Fix RLEnvs compat (#875) (@jeremiahpslewis)
• Add back ComposedStop (#876) (@jeremiahpslewis)
• Bump RLBase to v0.11.1 (#877) (@jeremiahpslewis)
• Further refinements (#879) (@jeremiahpslewis)
• Use multiple dispatch / methods plan! and act! (#880) (@jeremiahpslewis)
• RLCore.update! -> Base.push! API change (#884) (@jeremiahpslewis)
• Add compat for CommonRLInterface (#886) (@jeremiahpslewis)
• Fix hook issues (#887) (@jeremiahpslewis)
• CompatHelper: bump compat for ReinforcementLearningZoo to 0.6 for package ReinforcementLearningExperiments, (keep existing compat) (#888) (@github-actions[bot])
• Stacknamespace (#889) (@HenriDeh)
• allow more recent versions (#890) (@HenriDeh)
• Fix stack (#891) (@HenriDeh)
• CompatHelper: add new compat entry for DelimitedFiles at version 1 for package ReinforcementLearningEnvironments, (keep existing compat) (#894) (@github-actions[bot])
• Update implement new alg docs (#896) (@jeremiahpslewis)
• NFQ (#897) (@CasBex)
• fixed problem with sequential multi agent envs (#898) (@Mytolo)
• Sketch out optimise! refactor (#899) (@jeremiahpslewis)
• Bug fix optimise! (#902) (@jeremiahpslewis)
• Breaking changes to optimise! interface: Bump RLCore to v0.11 and RLZoo to v0.8 (#903) (@jeremiahpslewis)
• Swap out rng code (#905) (@jeremiahpslewis)
• CompatHelper: bump compat for NNlib to 0.9 for package ReinforcementLearningZoo, (keep existing compat) (#906) (@github-actions[bot])
• Fix dispatch and update documentation (#907) (@HenriDeh)
• QBasedPolicy optimise! forwards to learner. (#909) (@HenriDeh)
• Bump RLZoo version for NNlib (#911) (@jeremiahpslewis)
• Add performance testing run loop (#914) (@jeremiahpslewis)
• Fix Timer bug (#915) (@jeremiahpslewis)
• couple of improvements to MPO (#919) (@HenriDeh)
• Rework the run loop (#921) (@HenriDeh)
• adjusted pettingzoo to PettingZooEnv simultaneous environment more co… (#925) (@Mytolo)
• fixed devmode / project files (#932) (@Mytolo)
• fixed DQNLearner Gpu isse (#933) (@Mytolo)
• fixing prob. /w symbol/ string correspondence (#934) (@Mytolo)
• Bump flux compat (#935) (@jeremiahpslewis)
• Reduce find_all_max allocations and increase speed based on chatgpt s… (#938) (@jeremiahpslewis)
• Add Buildkite / GPU tests (#942) (@jeremiahpslewis)
• Add RLZoo and RLExperiments to Buildkite (#943) (@jeremiahpslewis)
• Drop deprecated @provide interface (#944) (@jeremiahpslewis)
• CI Improvements (#946) (@jeremiahpslewis)
• Github Actions Fixes (#947) (@jeremiahpslewis)
• gpu updates RLExperiments, RLZoo (#949) (@jeremiahpslewis)
• Bump RLCore version (#950) (@jeremiahpslewis)
• Refactor TRPO and VPG with EpisodesSampler (#952) (@HenriDeh)
• Fix TotalRewardPerEpisode bug (#953) (@jeremiahpslewis)
• update docs to loop refactor (#955) (@HenriDeh)
• CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningEnvironments, (keep existing compat) (#956) (@github-actions[bot])
• CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningZoo, (keep existing compat) (#957) (@github-actions[bot])
• CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningExperiments, (keep existing compat) (#958) (@github-actions[bot])
• CompatHelper: add new compat entry for cuDNN at version 1 for package ReinforcementLearningCore, (keep existing compat) (#962) (@github-actions[bot])
• CompatHelper: add new compat entry for cuDNN at version 1 for package ReinforcementLearningZoo, (keep existing compat) (#963) (@github-actions[bot])
• CompatHelper: add new compat entry for cuDNN at version 1 for package ReinforcementLearningExperiments, (keep existing compat) (#964) (@github-actions[bot])
• TargetNetwork (#966) (@HenriDeh)
• CompatHelper: bump compat for GPUArrays to 9 for package ReinforcementLearningCore, (keep existing compat) (#969) (@github-actions[bot])
• Prioritised DQN GPU (#974) (@CasBex)
• CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningZoo, (keep existing compat) (#975) (@github-actions[bot])
• CompatHelper: bump compat for ReinforcementLearningZoo to 0.8 for package ReinforcementLearningExperiments, (keep existing compat) (#976) (@github-actions[bot])
• CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningExperiments, (keep existing compat) (#977) (@github-actions[bot])
• Nfq refactor (#980) (@CasBex)
• Fix and refactor SAC (#985) (@HenriDeh)
• CompatHelper: bump compat for DomainSets to 0.7 for package ReinforcementLearningBase, (keep existing compat) (#986) (@github-actions[bot])
• remove rlenv dep for tests (#989) (@HenriDeh)
• CompatHelper: add new compat entry for CUDA at version 5 for package ReinforcementLearningExperiments, (keep existing compat) (#991) (@github-actions[bot])
• CompatHelper: add new compat entry for IntervalSets at version 0.7 for package ReinforcementLearningExperiments, (keep existing compat) (#994) (@github-actions[bot])
• Conservative Q-Learning (#995) (@HenriDeh)
• CompatHelper: add new compat entry for Parsers at version 2 for package ReinforcementLearningCore, (keep existing compat) (#997) (@github-actions[bot])
• CompatHelper: add new compat entry for MLUtils at version 0.4 for package ReinforcementLearningZoo, (keep existing compat) (#998) (@github-actions[bot])
• CompatHelper: add new compat entry for Statistics at version 1 for package ReinforcementLearningCore, (keep existing compat) (#999) (@github-actions[bot])
• Update CQL_SAC.jl (#1003) (@HenriDeh)
• Bump tj-actions/changed-files from 35 to 41 in /.github/workflows (#1006) (@dependabot[bot])
• Make it compatible with Adapt 4 and Metal 1 (#1008) (@joelreymont)
• Bump RLCore, RLEnv (#1012) (@jeremiahpslewis)
• Fix PPO per #1007 (#1013) (@jeremiahpslewis)
• Fix RLCore version (#1018) (@jeremiahpslewis)
• Add Devcontainer, handle DomainSets 0.7 (#1019) (@jeremiahpslewis)
• Initial GPUArray transition (#1020) (@jeremiahpslewis)
• Update TagBot.yml for subprojects (#1021) (@jeremiahpslewis)
• Fix offline agent test (#1025) (@joelreymont)
• Fix spell check CI errors (#1027) (@joelreymont)
• GPU Code Migration Part 2.1 (#1029) (@jeremiahpslewis)
• Bump RLZoo to v0.8 (#1031) (@jeremiahpslewis)
• Fix RLZoo version (#1032) (@jeremiahpslewis)

Closed issues:

• A3C (#133)
• Box2D environment (#2)
• Visualize episodes (#3)
• Implement TRPO/ACER (#134)
• ERROR: UndefVarError: AtariPreprocessor not defined (#6)
• bullet3 environment (#7)
• vizdoom environment (#8)
• Error tagging new release (#11)
• loadenvironment error (#19)
• Support alternative deep learning libraries (#20)
• Random Thoughts on v0.3.0 (#24)
• ViZDoom is broken (#130)
• Document basic environments (#129)
• bullet3 environment (#128)
• Box2D environment (#127)
• Prioritized DQN (#27)
• Improve interfaces for model exploration and hyperparameter optimization (#28)
• A2C (#32)
• Add built-in support for TensorBoard (#35)
• Add checkpoints (#36)
• Improve code coverage (#40)
• AbstractActionSelector not exported (#41)
• Params empty - no tracking (#43)
• Add reproducible examples for Atari environments (#44)
• Add procgen (#126)
• StopAfterEpisode with progress meter (#51)
• Add MAgent (#125)
• Regret Policy Gradients (#131)
• Support SEED RL (SCALABLE AND EFFICIENT DEEP-RL ) (#62)
• Support julia 1.4 (#63)
• How to define a new environment? (#64)
• Roadmap of v0.9 (#65)
• Add MCTS related algorithms (#132)
• Question about AbstractEnv API (#68)
• bsuite (#124)
• Classic environments in separate package? (#123)
• Implement Fully Parameterized Quantile Function for Distributional Reinforcement Learning. (#135)
• Failed to precompile ReinforcementLearning (#71)
• Experimental support of Torch.jl (#136)
• depends on HDF5? (#72)
• warning and error (#73)
• Compatibility issue in ReinforcementLearning & Flux (#74)
• ERROR: KeyError: key "ArnoldiMethod" not found (#79)
• Add dueling DQN (#137)
• In DDPG: Add support for vector actions (#138)
• Rename AbstractAgent to AbstractPolicy (#111)
• How should ReinforcementLearning.jl be cited ? (#80)
• Add a stop condition to terminate the experiment after reaching reward threashold (#112)
• Add Game 2048 (#122)
• add CUDA accelerated Env (#121)
• Unify common network architectures and patterns (#139)
• Alternative handling of max steps in environment (#140)
• I get NNlib error when trying to load a model (#82)
• "convert" warning (#83)
• Seg fault on macbook pro (#84)
• ACME RL lib by deepmind (#85)
• Add Highway env (#120)
• Definition of a policy (#86)
• Add remote trajectories (#87)
• Add experiments based on offline RL data (#141)
• Asynchronous Methods for Deep Reinforcement Learning (#142)
• Base.convert method for DiscreteSpace (#104)
• Action Space Meaning (#88)
• Base.in method for EmptySpace (#105)
• Renaming get_terminal to isterminated (#106)
• Requesting more informative field names for SharedTrajectory (#113)
• R2D2 (#143)
• Suggestion: More informative name for FullActionSet & MinimalActionSet (#107)
• Returning an AbstractSpace object using get_actions (#108)
• Recurrent Models (#144)
• Split experiments into separate files (#145)
• Add project.toml for tests (#146)
• Migrate to Pluto (#148)
• Update dependency to the latest version of ReinforcementLearning.jl (#149)
• Docs build error (#91)
• Split out Trajectory & CircularArrayBuffer as independent packages (#114)
• Requesting explanation for better performance at ... (#115)
• Add an extra mode when evaluating agent (#116)
• Why are wrapper environments a part of RLBase instead of RLCore (say)? (#109)
• Purpose and scope of sub-packages (#93)
• The names of keyword arguments in Trajectory is kind of misunderstanding (#117)
• Add experiments with GymEnv (#147)
• Cross language support (#103)
• Check compatibility between agent and environments (#118)
• Behaviour for hooks for RewardOverridenEnv (#119)
• StopAfterEpisode with custom DQNL errors beyond a particular Episode Count (#96)
• ERROR: UndefVarError: NNlib not defined while loading agent (#110)
• Support compression? (#102)
• State monitoring and fault tolerance (#101)
• Use JLSO for (de)serialization? (#97)
• Add an example running in K8S (#100)
• Setup github actions (#98)
• Fails to load trajectory (#150)
• Replace Travis with github actions (#151)
• Test error in ReinforcementLearningEnvironments.jl (#152)
• Move preallocations in MultiThreadEnv from global to local (#153)
• Flux as service (#154)
• remove @views (#155)
• error in save & load ElasticCompactSARTSATrajectory (#156)
• add early stopping in src\core\stop_conditions.jl (#157)
• add time stamp in load & save function, in file src\components\agents\agent.jl (#158)
• policies in GPU can not be saved || loaded (#159)
• AbstractStage docstring doesn't render correctly in docs. (#160)
• List of contributors (#161)
• code formatting (#165)
• Purpose of CommonRLInterface (#166)
• Moving example environments from RLBase to RLEnvs? (#167)
• Keeping prefix get_ in method names like get_reward (#168)
• Currently getting an ambiguous method error in ReinforcementLearningCore v0.5.1 (#171)
• Return experiment instead of hook only (#173)
• TD3 Implementation (#174)
• Train policy with GymEnv (#175)
• Travis CI Credits (#178)
• Training mode and testing mode (#179)
• Unrecognized symbols (#180)
• AbstractEnv (#181)
• SARTTrajectory for SAC (#182)
• define environment of FULL_ACTION_SET (#184)
• CircularArraySLARTTrajectory instance is not of type CircularArraySLARTTrajectory (#185)
• TagBot trigger issue (#186)
• Is hook the same thing as "callback"? (#190)
• Use @threads instead of @sync + @spawn in MultiThreadEnv? (#191)
• Blog custom env link typo (#192)
• Change clip_by_global_norm! into a Optimizer (#193)
• PPO related algorithms are broken (#194)
• Add card game environments (#196)
• Separate envs from algos in Zoo? (#197)
• Why "examples"? (#198)
• WandB integration? (#201)
• Add default implementations for AbstractEnvWrapper (#202)
• Add configuration in DQNLearner to enable double-dqn by default (#205)
• Derivative-Free Reinforcement Learning (#206)
• ERROR: type RandomPolicy has no field policy (#208)
• Why split repos? (#209)
• "Getting Started" too long imo (#210)
• PreActStage clarification (#212)
• What's a "trace"? (#213)
• Continuous time supported? (#215)
• Docs looks ugly in dark mode (#217)
• Julia 1.6.0 dependency problem with ReinforcementLearningBase/RLBase (#221)
• Add Discrete Batch-Constrained Deep Q-learning (#226)
• Docstring of DoEveryNStep (#225)
• Documentation of environment; actions seems not work. (#222)
• Documentation of "How to use Tensorboard?": with_logger not defined (#223)
• Getting figure object; How to get an animation using GR.plot in CartPolEnv (#246)
• Update dependency to [email protected] and resolve type piracy of findmax (#227)
• IQN is broken with [email protected] (#228)
• The components of Rainbow (#229)
• Source links in documentation directs to julia repo (#231)
• Support Tables.jl and PrettyTables.jl for Trajectories (#232)
• code in get_started seems to be broken (#233)
• PPO strange behaviour from having actions as one element arrays instead of scalar (#234)
• SAC and GaussianNetwork (#236)
• Precompilation prohibitively long (#237)
• Document how to save/load parameters (#238)
• Workflow of saving trajectory data (#239)
• An explanation of "how to train policy (agent)" such as Basic_DQN would be valuable (#240)
• How to guarantee the environment's reproducibility? (#241)
• [Call for Contributors] Summer 2021 of Open Source Promotion Plan (#242)
• Cannot use RLBase.action_space etc. when writing my own environment (#244)
• ReinforcementLearningZoo.jl experiments (#245)
• Next Release Plan (v0.9) (#247)
• How about making this package compatible with DifferentialEquations.jl? (#249)
• Reinforcement Learning and Combinatorial Optimization (#250)
• PPO and multi dimensional actions spaces (#251)
• Add ReinforcementLearningDatasets (#253)
• Incompatibility with CSVFiles.jl (#256)
• [RLEnvs] easy access of the length of an action vector (dimension of action space) (#257)
• Cannot add LinearAlgebra (#258)
• What's the checkpoints? (#261)
• Model based reinforcement learning (#262)
• Add a dedicated multi-dimensional space type (#268)
• PPO is broken when using CUDA (#280)
• Lack of reproducibility of QRDQN CartPole Experiment. (#281)
• Reinforcement Learning.jl in a RTS (#291)
• StopAfterNoImprovement hook test fails occasionally (#297)
• Get error when using ReinforcementLearning (#298)
• Problems with PGFPlotsX during the install (#301)
• Plotting CartPole environment in Jupyter (#306)
• Support CircularVectorSARTTrajectory RLZoo (#316)
• Local development environment setup tips causing error (#320)
• Rename some functions to help beginners navigate source code (#326)
• Question about PER (#328)
• Docs error in code output (#332)
• Setup a CI for typo (#336)
• double code & dysfunctional master branch when downloading package (#341)
• Support multiple discrete action space (#347)
• Precompilation error; using Plots makes a conflict (#349)
• Problem with running initial tutorial. Using TabularPolicy() generates an UndefinedKeyword error for n_action (#354)
• Question: Clarification on the RL plots generated by the run() function (#357)
• prob question for QBasedPolicy (#360)
• Can evaluate function be used as a component of RLcore? (#369)
• problem about precompiling the forked package (#377)
• Question: Can we use packages like DifferentialEquations.jl to evolve or model the environment in ReinforcementLearning.jl (#378)
• Combine transformers and RL (#392)
• MultiAgentManager does not select correct action space for RockPaperScissorsEnv (#393)
• Add ReinforcementLearningDatasets.jl (#397)
• error: dimension mismatch "cannot broadcast array to have fewer dimensions" (#400)
• SAC policy problems? (#410)
• Add pre-training hook (#411)
• Dead links in documentation (#418)
• Links of show nbview badges in RLExperiments are incorrect (#421)
• Problem accessing public google cloud storage bucket for RLDatasets.jl (#424)
• Function to access base env through multiple wrapper layers (#425)
• The problem of using GaussianNetwork in gpu (#455)
• Next Release Plan (v0.10) (#460)
• Error in experiment "JuliaRL_DDPG_Pendulum" (#471)
• In Windows, ReinforcementLearningDataset.jl encounter a bug (#485)
• Conditional Testing (#493)
• Inconsistency of the EpsilonGreedyExplorer selection function (#520)
• PyCall.getindex in module ReinforcementLearningEnvironments conflict warning (#527)
• device method definition overwritten (#530)
• How to display/render AtariEnv? (#546)
• StackFrames bug? (#551)
• Refactor of DQN Algorithms (#557)
• Small performance improvement (#558)
• Infinite-recursion bug in function is_discrete_space when an object of type ClosedInterval is passed (#566)
• JuliaRL_BasicDQN_CartPole example fails (#568)
• action_space not defined in tutorial (#569)
• CI fails with [email protected] (#572)
• Warning while precompiling RLCore due to kwargs (#575)
• Gain in VPGPolicy does not account for terminal states? (#578)
• Strange Bug with examples CartPoleEnv and RLBase.test_runnable!(RandomWalk1D) (#579)
• Missing docs for TDLearner (#580)
• Difficulty Creating a Custom Environment (#581)
• Missing docs for how to implement a new algorithm (#582)
• Donation (#595)
• MultiThreadEnv with custom (continuous) action spaces fails (#596)
• PPOCartPole fails, source of error included (#605)
• Question: Can ReinforcementLearning.jl handle Partially Observed Markov Processes (POMDPs)? (#608)
• Add an environment wrapper to IsaacGym (#619)
• Explain current implementation of PPO in detail (#620)
• How to run this source code in vscode? (#623)
• Bug: Issue with TD3 for multi-dimensional action spaces (#624)
• Make documentation on trace normalization (#633)
• ActionTransformedEnv doesn't transform legal_action_space_mask (#642)
• Bug: Previous example from RLZoo now has a bug (#643)
• TDLearner time step parameter (#648)
• Examples of multidimensional continous actions (#676)
• estimate v.s. basis in policies (#677)
• Base.copy not implemented for the TicTacToe environment (#678)
• Broken link to src (#693)
• Support Brax (#696)
• Q-learning update timing (#702)
• PPO on environments with multiple action dimensions? (#703)
• Can't checkout RLCore for development (#704)
• various eligibility trace-equipped TD methods (#709)
• Improve the logging mechanism during training (#725)
• questions while looking at implementation of VPG (#729)
• Setup sponsor related info (#730)
• new _run() (#731)
• SAC example experiment does not work (#736)
• Custom environment action and state space explanation (#738)
• PPOPolicy training: ERROR: DomainError with NaN: Normal: the condition σ >= zero(σ) is not satisfied. (#739)
• Code Readability (#740)
• MultiThreadEnv not available in ReinforcementLearningZoo (#741)
• ReinforcementLearningExperiment dependencies fail to precompile (#744)
• tanh normalization destabilizes learning with GaussianNetwork (#745)
• how to load a saved model and test it? (#755)
• Custom Environment Passes RLBase.test_runnable!(env) but infinite hangs and crashes when run. (#757)
• Bounds Error at UPDATE_FREQ Step (#758)
• StopAfterEpisode returns 1 more episode using StepsPerEpisode() hook (#759)
• Move basic definition of environment wrapper into RLBase (#760)
• Precompilation error - DomainSets not in dependencies (#761)
• How to set RLBase.state_space() if the number of state space is uncertain (#762)
• Collect both number of steps and rewards in a single hook (#763)
• how to use MultiAgentManager on different algorithms? (#764)
• Example run of Offline RL that totally depends on dataset without online environment (#765)
• Every single environment / experiment crashes with following error: (#766)
• Neural Network Approximator based policies not working (#770)
• Deep RL example for LSTM (#772)
• "params not defined," "JuliaRL_BasicDQN_CartPole" (#778)
• MonteCarloLearner incorrect PreActStage behavior (#779)
• Prioritised Experience Replay (#780)
• Outdated dependencies (#781)
• Running experiments throws a "UndefVarError: params not defined" message (#784)
• Failing MPOCovariance experiment (#791)
• Logo image was not found (#836)
• Reactivate docs on CI/CD (#838)
• update docs: Tips for developers (#844)
• Package dependencies not compatible (#860)
• need help from an expert (#862)
• Installing ReinforcementLearning.jl downgrades Flux.jl (#864)
• Fix Experiment type setup (#881)
• LoadError: UndefVarError: params not defined (#882)
• Rename update! to push! (#883)
• Contribute Neural Fitted Q-iteration algorithm (#895)
• PPo policy experiments failing (#910)
• Executing RLBase.plan! after end of experiment (#913)
• EpisodeSampler in Trajectories (#927)
• Hook RewardsPerEpisode broken (#945)
• Can implement this ARZ algorithm ? (#965)
• AssertionError: action in env.action_space (#967)
• Fixing SAC Policy (#970)
• Prioritized DQN experiment nonfunctional (#971)
• Prioritised DQN failing on GPU (#973)
• An error (#983)
• params() is no longer supported in Flux (#996)
• GPU Compile error on PPO with MaskedPPOTrajectory (#1007)
• RL Core tests fail sporadically (#1010)
• RL Env tests fail with latest OpenSpiel patches (#1011)
• Tutorial OpenSpiel KuhnOpenNSFP fails (#1024)
• CI: Should spell check be dropped or fixed? (#1026)