Name | Modified | Size | Downloads / Week |
---|---|---|---|
Parent folder | |||
README.md | 2024-02-21 | 872 Bytes | |
v0.0.4 source code.tar.gz | 2024-02-21 | 27.4 MB | |
v0.0.4 source code.zip | 2024-02-21 | 27.7 MB | |
Totals: 3 Items | 55.1 MB | 0 |
Enhancement
- add agent configurations & polish replay video saving method (#184)
- polish comments in worker files
- polish comments in tree search files (#185)
- rename mcts_mode to battle_mode_in_simulation_env, add sampled alphazero config for tictactoe (#179)
- polish redundant data squeeze operations (#177)
- polish the continuous action process in sez model
- polish bipedalwalker env
Fix
- fix completed value inf bug when zero exists in action_mask in gumbel muzero (#178)
- fix render settings when using gymnasium (#173)
- fix lstm_hidden_size in sampled_efficientzero_model.py
- fix action_mask in bipedalwalker_cont_disc_env, fix device bug in sampled efficientzero (#168)
Full Changelog: https://github.com/opendilab/LightZero/compare/v0.0.3...v0.0.4
Contributors: @karroyan @HarryXuancy @puyuan1996 @zjowowen