Mushroom Rl Versions Save

Python library for Reinforcement Learning.

1.5.4

3 years ago
  • Fixes in tiles;
  • Maxmin DQN and Maxmin Q-Learning added;
  • Minor fixes in SAC;
  • Added optimizer to policy gradient algorithms;
  • Code quality improvements;
  • Minor bug fixes.

1.5.3

3 years ago
  • Added QLambda algorithm (thanks to @nikosNalmpantis);
  • Improved regressor support for Torch tensors;
  • Added frames module;
  • Fixed observation shape in Atari environment.

1.5.2

3 years ago
  • Added missing resources to setup
  • Moved humanoid meshes into meshes folder (was Geometry)
  • Improved makefile in order to ensure proper build before uploading

1.5.1

3 years ago

Fixed source distribution by adding a missing .pyx file.

1.5.0

3 years ago
  • Implemented PEP 517-518;
  • Improved saving system:
    • Added Serializable interface that can be used by any Mushroom class;
    • Approximator is now serializable;
    • Fixed issue with save/load attributes;
    • Everything is saved in a zip file with .msh extension.
  • Implemented cmac regressor;
  • Step callback added in core;
  • callbacks_episode renamed in callbacks_fit;
  • Distributions are now serializable;
  • Added computation of entropy for distributions;
  • Policies are now serializable;
  • Added BoltzmannTorchPolicy;
  • Added LQR solver;
  • Added PyBullet environment;
  • Fixed issue in Gym environment when PyBullet import was missing;
  • LQR bug fixed and generate function improved;
  • Improved Mujoco environment;
  • Cythonization and cleanup of HumanoidGait environment;
  • TRPO bug fixed;
  • Added RandomFourierBasis;
  • Fixed pendulum_trust_region example.

1.4.0

4 years ago
  • Save and load of the agent;
  • Online data and performance visualization using pyqtgraph;
  • Normalization function added as preprocessors;
  • Step callback added;
  • Humanoid gait environment.

1.3.0

4 years ago

MushroomRL is the new name of the library. Code, doc, and config files have been updated accordingly. The package is now available on PyPI and can be installed using pip.

1.2.0

4 years ago
  • Improved test suit;
  • Implemented Deep RL algorithms;
  • Improved visualization;
  • Improved code quality;
  • Several bug fixes;
  • Refactoring of Torch approximator.

1.1

4 years ago
  • bug fixes;
  • torch support;
  • dm_control and pybullet interface;
  • doc improved.

1.0

6 years ago

First version of Mushroom