## ReinforcementLearningZoo v0.3.4

[Diff since v0.3.3](JuliaReinforcementLearning/ReinforcementLearningZoo.jl@v0.3.3...v0.3.4)



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

## ReinforcementLearningZoo v0.3.3

[Diff since v0.3.2](JuliaReinforcementLearning/ReinforcementLearningZoo.jl@v0.3.2...v0.3.3)



**Merged pull requests:**
- fix atari related experiments (JuliaReinforcementLearning#145) (@findmyway)

## ReinforcementLearningZoo v0.3.2

[Diff since v0.3.1](JuliaReinforcementLearning/ReinforcementLearningZoo.jl@v0.3.1...v0.3.2)


**Closed issues:**
- TD3 Implementation (JuliaReinforcementLearning#143)

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

## ReinforcementLearningZoo v0.3.1

[Diff since v0.3.0](JuliaReinforcementLearning/ReinforcementLearningZoo.jl@v0.3.0...v0.3.1)



**Merged pull requests:**
- Update dependency (JuliaReinforcementLearning#135) (@findmyway)
- Drop dependency of RLEnvs (JuliaReinforcementLearning#136) (@findmyway)
- Update format_pr.yml (JuliaReinforcementLearning#137) (@norci)
- added .JuliaFormatter.toml (JuliaReinforcementLearning#139) (@norci)
- Enable cfr tests (JuliaReinforcementLearning#141) (@findmyway)

## ReinforcementLearningZoo v0.3.0

[Diff since v0.2.2](JuliaReinforcementLearning/ReinforcementLearningZoo.jl@v0.2.2...v0.3.0)



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

## ReinforcementLearningZoo v0.2.2

[Diff since v0.2.1](JuliaReinforcementLearning/ReinforcementLearningZoo.jl@v0.2.1...v0.2.2)


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

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

## ReinforcementLearningZoo v0.2.1

[Diff since v0.2.0](JuliaReinforcementLearning/ReinforcementLearningZoo.jl@v0.2.0...v0.2.1)


**Closed issues:**
- How to run experiment (JuliaReinforcementLearning#104)

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

## ReinforcementLearningZoo v0.2.0

[Diff since v0.1.7](JuliaReinforcementLearning/ReinforcementLearningZoo.jl@v0.1.7...v0.2.0)


**Closed issues:**
- Add policy gradient (JuliaReinforcementLearning#80)
- Improve the PPOLearner to support continuous action space (JuliaReinforcementLearning#92)

**Merged pull requests:**
- Fix (JuliaReinforcementLearning#85) (@norci)
- PG policy (JuliaReinforcementLearning#87) (@norci)
- Twin Delayed DDPG (TD3) (JuliaReinforcementLearning#89) (@rbange)
- Add MCCFR (JuliaReinforcementLearning#90) (@findmyway)
- Rename PPOLearner to PPOPolicy and make it support continuous space (JuliaReinforcementLearning#93) (@findmyway)
- CompatHelper: add new compat entry for "StructArrays" at version "0.4" (JuliaReinforcementLearning#95) (@github-actions[bot])

## ReinforcementLearningZoo v0.1.7

[Diff since v0.1.6](JuliaReinforcementLearning/ReinforcementLearningZoo.jl@v0.1.6...v0.1.7)


**Closed issues:**
- Implement Soft Actor Critic (JuliaReinforcementLearning#45)
- Support legal_actions and legal_actions_mask (JuliaReinforcementLearning#60)

**Merged pull requests:**
- support legal_actions_mask (JuliaReinforcementLearning#69) (@findmyway)
- Soft Actor Critic (JuliaReinforcementLearning#71) (@rbange)
- CompatHelper: add new compat entry for "Distributions" at version "0.23" (JuliaReinforcementLearning#72) (@github-actions[bot])
- fix legal_actions_mask errors (JuliaReinforcementLearning#74) (@findmyway)
- add experiment of snake game (JuliaReinforcementLearning#77) (@findmyway)
- added more tensorboard logs in rl experiments ... (JuliaReinforcementLearning#81) (@norci)
- Multi agent related changes (JuliaReinforcementLearning#83) (@findmyway)

## ReinforcementLearningZoo v0.1.6

[Diff since v0.1.5](JuliaReinforcementLearning/ReinforcementLearningZoo.jl@v0.1.5...v0.1.6)



**Merged pull requests:**
- update dependency of RLCore (JuliaReinforcementLearning#67) (@findmyway)