v0.0.5

CHANGELOG.md

@@ -1,3 +1,23 @@
+2024.04.12 (v0.0.5)
+- env: MemoryEnv (#197)
+- env: mountain_car (#181)
+- algo: Gumbel AlphaZero in ctree (#212)
+- feature: add ZeroPal and discord link (#209)
+- feature: add eval_offline option (#188)
+- feature: save the updated searched policy and value to the buffer during reanalyze (#190)
+- feature: add muzero visualization (#181)
+- feature: add efficientzero tictactoe configs (#204)
+- feature: add 2 mcts related iclr2024 papers
+- polish: add load pretrained model option in test_game_segment (#194)
+- polish: polish _forward_learn() and some data process operations (#191)
+- polish: add customization documentation section in readme
+- fix: fix sync_gradients and log in DDP settings (#200)
+- fix: fix channel_last bug
+- fix: fix total_episode_count bug in collector
+- fix: fix memory_lightzero_env return bug
+- fix: fix obs_max_scale bug in memory_env
+- style: add unittest for game_buffer_muzero (#186)
+
 2024.02.08 (v0.0.4)
 - polish: add agent configurations & polish replay video saving method (#184)
 - polish: polish comments in worker files

README.md

@@ -27,10 +27,10 @@
 [![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 2024.04.09 LightZero-v0.0.4
+Updated on 2024.04.12 LightZero-v0.0.5
 
 > 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).
-> For any questions about LightZero, you can consult the RAG-based Q&A assistant: [ZeroPal](https://huggingface.co/spaces/OpenDILabCommunity/ZeroPal) (Simplified Chinese).
+> For any questions about LightZero, you can consult the RAG-based Q&A assistant: [ZeroPal](https://huggingface.co/spaces/OpenDILabCommunity/ZeroPal)gst.
 
 English | [简体中文(Simplified Chinese)](https://github.com/opendilab/LightZero/blob/main/README.zh.md) | [Paper](https://arxiv.org/pdf/2310.08348.pdf)
 

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 2024.04.09 LightZero-v0.0.4
+最近更新于 2024.04.12 LightZero-v0.0.5
 
 > LightZero 是一个轻量、高效、易懂的 MCTS+RL 开源算法库。
 > 有关 LightZero 的任何疑问，您都可以咨询基于 RAG 技术的问答助手：[ZeroPal](https://huggingface.co/spaces/OpenDILabCommunity/ZeroPal)。