v0.3.7

ReinforcementLearningZoo v0.3.7

Diff since v0.3.6

Merged pull requests:

• Fix #251, ppo multidim action eval (#177) (@albheim)

v0.3.6

ReinforcementLearningZoo v0.3.6

Diff since v0.3.5

Closed issues:

• JuliaRL_PPO_Pendulum action_space not defined error (#164)
• JuliaRL_A2C_CartPole experiment hook TotalRewardPerEpisode not work (#168)

Merged pull requests:

• Add REM-DQN(Random Ensemble Mixture) method (#160) (@pilgrimygy)
• Fix ppo pendulum example (#165) (@albheim)
• Fix bug in multi action ppo (#169) (@albheim)
• Fix SAC Pendulum example (#170) (@albheim)
• Add dueling network (#171) (@pilgrimygy)
• Fix GaussianNetwork stddev and replace SACPolicyNetwork (#172) (@albheim)
• SAC multidimensional actions (#173) (@albheim)
• Fix a bug (#174) (@pilgrimygy)
• QRDQN implementation (#176) (@Mobius1D)

v0.3.5

ReinforcementLearningZoo v0.3.5

Diff since v0.3.4

Closed issues:

• A possible error (#154)

Merged pull requests:

• add some explanations (#155) (@pilgrimygy)
• Implemented double DQN (#156) (@Mobius1D)
• Typo fix. (#157) (@Mobius1D)
• DQN: take into account the update_horizon to know if we can update (#162) (@ilancoulon)
• fix test error with iqn (#163) (@findmyway)

v0.3.4

ReinforcementLearningZoo v0.3.4

Diff since v0.3.3

Merged pull requests:

• Add behavior cloning (#146) (@findmyway)
• CompatHelper: bump compat for "BSON" to "0.3" (#149) (@github-actions[bot])
• Update StructArrays dependency (#150) (@metab0t)
• Allow multidimensional actions in ppo (#151) (@albheim)
• add GridWorlds environments (#152) (@Sid-Bhatia-0)

v0.3.3

ReinforcementLearningZoo v0.3.3

Diff since v0.3.2

Merged pull requests:

• fix atari related experiments (#145) (@findmyway)

v0.3.2

ReinforcementLearningZoo v0.3.2

Diff since v0.3.1

Closed issues:

• TD3 Implementation (#143)

Merged pull requests:

• CompatHelper: bump compat for "Zygote" to "0.6" (#138) (@github-actions[bot])
• Support rlintro (#144) (@findmyway)

v0.3.1

ReinforcementLearningZoo v0.3.1

Diff since v0.3.0

Merged pull requests:

• Update dependency (#135) (@findmyway)
• Drop dependency of RLEnvs (#136) (@findmyway)
• Update format_pr.yml (#137) (@norci)
• added .JuliaFormatter.toml (#139) (@norci)
• Enable cfr tests (#141) (@findmyway)

v0.3.0

ReinforcementLearningZoo v0.3.0

Diff since v0.2.2

Merged pull requests:

• updated patch.jl, for ignore function. (#127) (@norci)
• Prepare for the next release of RLCore (#129) (@findmyway)
• Removed repetitive imports from algorithms. (#130) (@rishabhvarshney14)
• CompatHelper: add new compat entry for "CircularArrayBuffers" at version "0.1" (#132) (@github-actions[bot])

v0.2.2

ReinforcementLearningZoo v0.2.2

Diff since v0.2.1

Closed issues:

• Mean Actor-Critic (#11)
• Use StableRNG in tests (#100)
• Need RLCore's @E_cmd to run experiment as given in README (#112)
• Optimizer setting in PPO experiments (#118)

Merged pull requests:

• Revert auto format related changes (#107) (@findmyway)
• Adding Mean Actor Critic (#108) (@RajGhugare19)
• CompatHelper: bump compat for "CUDA" to "2.1" (#110) (@github-actions[bot])
• Update README.md (#114) (@findmyway)
• Changes related to distributed reinforcement learning (#117) (@findmyway)
• Fix #118 (#119) (@findmyway)
• Export PPOActionMaskTrajectory (#123) (@findmyway)
• MassInstallAction: Install the CompatHelper workflow on this repository (#125) (@findmyway)

v0.2.1

ReinforcementLearningZoo v0.2.1

Diff since v0.2.0

Closed issues:

• How to run experiment (#104)

Merged pull requests:

• Improve CFR (#99) (@findmyway)
• CompatHelper: bump compat for "Distributions" to "0.24" (#101) (@github-actions[bot])
• Update README.md (#105) (@findmyway)