|
1 | | -2023.9.21(v0.0.2) |
| 1 | +2023.12.07 (v0.0.3) |
| 2 | +- env: MiniGrid env (#110) |
| 3 | +- env: Bsuite env (#110) |
| 4 | +- env: GoBigger env (#39) |
| 5 | +- algo: RND+MuZero (#110) |
| 6 | +- algo: Sampled AlphaZero (#141) |
| 7 | +- algo: Multi-Agent MuZero/EfficientZero (#39) |
| 8 | +- feature: add ctree version of mcts in alphazero (#142) |
| 9 | +- feature: upgrade the dependency on gym with gymnasium (#150) |
| 10 | +- feature: add agent class to support LightZero's HuggingFace Model Zoo (#163) |
| 11 | +- feature: add recent MCTS-related papers in readme (#159) |
| 12 | +- feature: add muzero config for connect4 (#107) |
| 13 | +- feature: added CONTRIBUTING.md (#119) |
| 14 | +- feature: added .gitpod.yml and .gitpod.Dockerfile (#123) |
| 15 | +- feature: added contributors subsection in README (#132) |
| 16 | +- feature: added CODE_OF_CONDUCT.md (#127) |
| 17 | +- polish: refine comments and render_eval configs for various common envs (#154) (#161) |
| 18 | +- polish: polish action_type and env_type, fix test.yml, fix unittest (#160) |
| 19 | +- polish: update env and algo tutorial doc (#106) |
| 20 | +- polish: polish gomoku env (#141) |
| 21 | +- polish: add random_policy support for continuous env (#118) |
| 22 | +- polish: polish simulation method of ptree_az (#120) |
| 23 | +- polish: polish comments of game_segment_to_array |
| 24 | +- fix: fix render method for various common envs (#154) (#161) |
| 25 | +- fix: fix gumbel muzero collector bug, fix gumbel typo (#144) |
| 26 | +- fix: fix assert bug in game_segment.py (#138) |
| 27 | +- fix: fix visit_count_distributions name in muzero_evaluator |
| 28 | +- fix: fix mcts and alphabeta bot unittest (#120) |
| 29 | +- fix: fix typos in ptree_mz.py (#113) |
| 30 | +- fix: fix root_sampled_actions_tmp shape bug in sez ptree |
| 31 | +- fix: fix policy utils unittest |
| 32 | +- fix: fix typo in readme and add a 'back to top' button in readme (#104) (#109) (#111) |
| 33 | +- style: add nips2023 paper link |
| 34 | + |
| 35 | +2023.09.21 (v0.0.2) |
2 | 36 | - env: MuJoCo env (#50) |
3 | 37 | - env: 2048 env (#64) |
4 | 38 | - env: Connect4 env (#63) |
5 | 39 | - algo: Gumbel MuZero (#22) |
6 | 40 | - algo: Stochastic MuZero (#64) |
7 | | -- polish: polish mcts and ptree_az (#57) (#61) |
8 | | -- polish: polish readme (#36) (#47) (#51) (#77) (#95) (#96) |
9 | | -- polish: update paper notes (#89) (#91) |
10 | | -- polish: polish model and configs (#26) (#27) (#50) |
11 | 41 | - feature: add Dockerfile and its usage instructions (#95) |
12 | 42 | - feature: add doc about how to customize envs and algos (#78) |
13 | 43 | - feature: add pytorch ddp support (#68) |
14 | 44 | - feature: add eps greedy and random collect option in train_muzero_entry (#54) |
15 | 45 | - feature: add atari visualization option (#40) |
16 | 46 | - feature: add log_buffer_memory_usage utils (#30) |
| 47 | +- polish: polish mcts and ptree_az (#57) (#61) |
| 48 | +- polish: polish readme (#36) (#47) (#51) (#77) (#95) (#96) |
| 49 | +- polish: update paper notes (#89) (#91) |
| 50 | +- polish: polish model and configs (#26) (#27) (#50) |
17 | 51 | - fix: fix priority bug in muzero collector (#74) |
18 | 52 | - style: update github action (#71) (#72) (#73) (#81) (#83) (#84) (#90) |
19 | 53 |
|
20 | | -2023.4.14(v0.0.1) |
| 54 | +2023.04.14 (v0.0.1) |
0 commit comments