A reinforcement learning package for Julia
Merged pull requests:
explorers.jl
(#382) (@peterchen96)nfsp
implementation (#439) (@peterchen96)run
displays description of experiment (#477) (@ShuhuaGao)MADDPG
. (#481) (@peterchen96)QBasedPolicy.
(#488) (@peterchen96)act_limit
parameter in target_actor
(#588) (@NPLawrence)StackFrames
(#602) (@findmyway)TDLearner
(#649) (@baedan)JuliaRL_DQN_CartPole
(#650) (@findmyway)Closed issues:
AbstractAgent
to AbstractPolicy
(#111)AbstractSpace
object using get_actions
(#108)ERROR: UndefVarError: NNlib not defined
while loading agent (#110)get_
in method names like get_reward
(#168)ReinforcementLearningBase
/RLBase (#221)actions
seems not work. (#222)with_logger
not defined (#223)Basic_DQN
would be valuable (#240)LinearAlgebra
(#258)checkpoints
? (#261)using Plots
makes a conflict (#349)TabularPolicy()
generates an UndefinedKeyword
error for n_action
(#354)run()
function (#357)evaluate
function be used as a component of RLcore? (#369)DifferentialEquations.jl
to evolve or model the environment in ReinforcementLearning.jl
(#378)show nbview
badges in RLExperiments are incorrect (#421)device
method definition overwritten (#530)is_discrete_space
when an object of type ClosedInterval is passed (#566)TDLearner
(#580)MultiThreadEnv
with custom (continuous) action spaces fails (#596)ActionTransformedEnv
doesn't transform legal_action_space_mask
(#642)TDLearner
time step parameter (#648)StopAfterEpisode
returns 1 more episode using StepsPerEpisode()
hook (#759)params
not defined (#882)Diff since ReinforcementLearningEnvironments-v0.8.7
Merged pull requests:
Closed issues:
Diff since ReinforcementLearningCore-v0.13.1
Merged pull requests:
Closed issues:
Merged pull requests:
explorers.jl
(#382) (@peterchen96)nfsp
implementation (#439) (@peterchen96)run
displays description of experiment (#477) (@ShuhuaGao)MADDPG
. (#481) (@peterchen96)QBasedPolicy.
(#488) (@peterchen96)act_limit
parameter in target_actor
(#588) (@NPLawrence)StackFrames
(#602) (@findmyway)TDLearner
(#649) (@baedan)JuliaRL_DQN_CartPole
(#650) (@findmyway)Closed issues:
AbstractAgent
to AbstractPolicy
(#111)AbstractSpace
object using get_actions
(#108)ERROR: UndefVarError: NNlib not defined
while loading agent (#110)get_
in method names like get_reward
(#168)ReinforcementLearningBase
/RLBase (#221)actions
seems not work. (#222)with_logger
not defined (#223)Basic_DQN
would be valuable (#240)LinearAlgebra
(#258)checkpoints
? (#261)using Plots
makes a conflict (#349)TabularPolicy()
generates an UndefinedKeyword
error for n_action
(#354)run()
function (#357)evaluate
function be used as a component of RLcore? (#369)DifferentialEquations.jl
to evolve or model the environment in ReinforcementLearning.jl
(#378)show nbview
badges in RLExperiments are incorrect (#421)device
method definition overwritten (#530)is_discrete_space
when an object of type ClosedInterval is passed (#566)TDLearner
(#580)MultiThreadEnv
with custom (continuous) action spaces fails (#596)ActionTransformedEnv
doesn't transform legal_action_space_mask
(#642)TDLearner
time step parameter (#648)StopAfterEpisode
returns 1 more episode using StepsPerEpisode()
hook (#759)params
not defined (#882)Merged pull requests:
explorers.jl
(#382) (@peterchen96)nfsp
implementation (#439) (@peterchen96)run
displays description of experiment (#477) (@ShuhuaGao)MADDPG
. (#481) (@peterchen96)QBasedPolicy.
(#488) (@peterchen96)act_limit
parameter in target_actor
(#588) (@NPLawrence)StackFrames
(#602) (@findmyway)TDLearner
(#649) (@baedan)JuliaRL_DQN_CartPole
(#650) (@findmyway)Closed issues:
AbstractAgent
to AbstractPolicy
(#111)AbstractSpace
object using get_actions
(#108)ERROR: UndefVarError: NNlib not defined
while loading agent (#110)get_
in method names like get_reward
(#168)ReinforcementLearningBase
/RLBase (#221)actions
seems not work. (#222)with_logger
not defined (#223)Basic_DQN
would be valuable (#240)LinearAlgebra
(#258)checkpoints
? (#261)using Plots
makes a conflict (#349)TabularPolicy()
generates an UndefinedKeyword
error for n_action
(#354)run()
function (#357)evaluate
function be used as a component of RLcore? (#369)DifferentialEquations.jl
to evolve or model the environment in ReinforcementLearning.jl
(#378)show nbview
badges in RLExperiments are incorrect (#421)device
method definition overwritten (#530)is_discrete_space
when an object of type ClosedInterval is passed (#566)TDLearner
(#580)MultiThreadEnv
with custom (continuous) action spaces fails (#596)ActionTransformedEnv
doesn't transform legal_action_space_mask
(#642)TDLearner
time step parameter (#648)StopAfterEpisode
returns 1 more episode using StepsPerEpisode()
hook (#759)params
not defined (#882)Merged pull requests:
explorers.jl
(#382) (@peterchen96)nfsp
implementation (#439) (@peterchen96)run
displays description of experiment (#477) (@ShuhuaGao)MADDPG
. (#481) (@peterchen96)QBasedPolicy.
(#488) (@peterchen96)act_limit
parameter in target_actor
(#588) (@NPLawrence)StackFrames
(#602) (@findmyway)TDLearner
(#649) (@baedan)JuliaRL_DQN_CartPole
(#650) (@findmyway)Closed issues:
AbstractAgent
to AbstractPolicy
(#111)AbstractSpace
object using get_actions
(#108)ERROR: UndefVarError: NNlib not defined
while loading agent (#110)get_
in method names like get_reward
(#168)ReinforcementLearningBase
/RLBase (#221)actions
seems not work. (#222)with_logger
not defined (#223)Basic_DQN
would be valuable (#240)LinearAlgebra
(#258)checkpoints
? (#261)using Plots
makes a conflict (#349)TabularPolicy()
generates an UndefinedKeyword
error for n_action
(#354)run()
function (#357)evaluate
function be used as a component of RLcore? (#369)DifferentialEquations.jl
to evolve or model the environment in ReinforcementLearning.jl
(#378)show nbview
badges in RLExperiments are incorrect (#421)device
method definition overwritten (#530)is_discrete_space
when an object of type ClosedInterval is passed (#566)TDLearner
(#580)MultiThreadEnv
with custom (continuous) action spaces fails (#596)ActionTransformedEnv
doesn't transform legal_action_space_mask
(#642)TDLearner
time step parameter (#648)StopAfterEpisode
returns 1 more episode using StepsPerEpisode()
hook (#759)params
not defined (#882)Closed issues:
TDLearner
(#580)Merged pull requests:
TDLearner
(#649) (@baedan)JuliaRL_DQN_CartPole
(#650) (@findmyway)Closed issues:
device
method definition overwritten (#530)is_discrete_space
when an object of type ClosedInterval is passed (#566)MultiThreadEnv
with custom (continuous) action spaces fails (#596)ActionTransformedEnv
doesn't transform legal_action_space_mask
(#642)Merged pull requests:
act_limit
parameter in target_actor
(#588) (@NPLawrence)StackFrames
(#602) (@findmyway)Closed issues:
actions
seems not work. (#222)with_logger
not defined (#223)using Plots
makes a conflict (#349)TabularPolicy()
generates an UndefinedKeyword
error for n_action
(#354)run()
function (#357)evaluate
function be used as a component of RLcore? (#369)DifferentialEquations.jl
to evolve or model the environment in ReinforcementLearning.jl
(#378)show nbview
badges in RLExperiments are incorrect (#421)Merged pull requests:
explorers.jl
(#382) (@peterchen96)nfsp
implementation (#439) (@peterchen96)run
displays description of experiment (#477) (@ShuhuaGao)MADDPG
. (#481) (@peterchen96)QBasedPolicy.
(#488) (@peterchen96)