v0.0.4

CHANGELOG.md

@@ -1,3 +1,16 @@
+2024.02.08 (v0.0.4)
+- polish: add agent configurations & polish replay video saving method (#184)
+- polish: polish comments in worker files
+- polish: polish comments in tree search files (#185)
+- polish: rename mcts_mode to battle_mode_in_simulation_env, add sampled alphazero config for tictactoe (#179)
+- polish: polish redundant data squeeze operations (#177)
+- polish: polish the continuous action process in sez model
+- polish: polish bipedalwalker env
+- fix: fix completed value inf bug when zero exists in action_mask in gumbel muzero (#178)
+- fix: fix render settings when using gymnasium (#173)
+- fix: fix lstm_hidden_size in sampled_efficientzero_model.py
+- fix: fix action_mask in bipedalwalker_cont_disc_env, fix device bug in sampled efficientzero (#168)
+
 2023.12.07 (v0.0.3)
 - env: MiniGrid env (#110)
 - env: Bsuite env (#110)

README.md

@@ -27,7 +27,7 @@
 [![Contributors](https://img.shields.io/github/contributors/opendilab/LightZero)](https://github.com/opendilab/LightZero/graphs/contributors)
 [![GitHub license](https://img.shields.io/github/license/opendilab/LightZero)](https://github.com/opendilab/LightZero/blob/master/LICENSE)
 
-Updated on 2023.12.07 LightZero-v0.0.3
+Updated on 2024.02.08 LightZero-v0.0.4
 
 > LightZero is a lightweight, efficient, and easy-to-understand open-source algorithm toolkit that combines Monte Carlo Tree Search (MCTS) and Deep Reinforcement Learning (RL). 
 

README.zh.md

@@ -27,7 +27,7 @@
 [![Contributors](https://img.shields.io/github/contributors/opendilab/LightZero)](https://github.com/opendilab/LightZero/graphs/contributors)
 [![GitHub license](https://img.shields.io/github/license/opendilab/LightZero)](https://github.com/opendilab/LightZero/blob/master/LICENSE)
 
-最近更新于 2023.12.07 LightZero-v0.0.3
+最近更新于 2024.02.08 LightZero-v0.0.4
 
 > LightZero 是一个轻量、高效、易懂的 MCTS+RL 开源算法库。
 

setup.py

@@ -71,7 +71,7 @@ def find_cython_extensions(path=None):
 
 setup(
     name='LightZero',
-    version='0.0.3',
+    version='0.0.4',
     description='A lightweight and efficient MCTS/AlphaZero/MuZero algorithm toolkits.',
     long_description_content_type='text/markdown',
     author='opendilab',