Skip to content

Commit

Permalink
fix(pu): update fourrooms benchamrk
Browse files Browse the repository at this point in the history
  • Loading branch information
puyuan1996 committed Oct 13, 2023
1 parent 20c7423 commit 005fd48
Show file tree
Hide file tree
Showing 4 changed files with 5 additions and 3 deletions.
3 changes: 2 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -206,9 +206,10 @@ python3 -u zoo/board_games/tictactoe/config/tictactoe_muzero_bot_mode_config.py
<details open><summary>Click to collapse</summary>
- Below are the benchmark results of [AlphaZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/alphazero.py) and [MuZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/muzero.py) on two board games: [TicTacToe](https://github.com/opendilab/LightZero/blob/main/zoo/board_games/tictactoe/envs/tictactoe_env.py), [Gomoku](https://github.com/opendilab/LightZero/blob/main/zoo/board_games/gomoku/envs/gomoku_env.py).
- Below are the benchmark results of [AlphaZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/alphazero.py) and [MuZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/muzero.py) on three board games: [TicTacToe](https://github.com/opendilab/LightZero/blob/main/zoo/board_games/tictactoe/envs/tictactoe_env.py), [Connect4](https://github.com/opendilab/LightZero/blob/main/zoo/board_games/connect4/envs/connect4_env.py), [Gomoku](https://github.com/opendilab/LightZero/blob/main/zoo/board_games/gomoku/envs/gomoku_env.py).
<p align="center">
<img src="assets/benchmark/main/tictactoe_bot-mode_main.png" alt="tictactoe_bot-mode_main" width="30%" height="auto" style="margin: 0 1%;">
<img src="assets/benchmark/main/gomoku_bot-mode_main.png" alt="connect4_bot-mode_main" width="30%" height="auto" style="margin: 0 1%;">
<img src="assets/benchmark/main/gomoku_bot-mode_main.png" alt="gomoku_bot-mode_main" width="30%" height="auto" style="margin: 0 1%;">
</p>
Expand Down
5 changes: 3 additions & 2 deletions README.zh.md
Original file line number Diff line number Diff line change
Expand Up @@ -193,13 +193,14 @@ python3 -u zoo/board_games/tictactoe/config/tictactoe_muzero_bot_mode_config.py

<details open><summary>点击折叠</summary>

- [AlphaZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/alphazero.py) 和 [MuZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/muzero.py) 在两个棋类游戏([TicTacToe (井字棋)](https://github.com/opendilab/LightZero/blob/main/zoo/board_games/tictactoe/envs/tictactoe_env.py) 和 [Gomoku (五子棋)](https://github.com/opendilab/LightZero/blob/main/zoo/board_games/gomoku/envs/gomoku_env.py))上的基线结果:
- [AlphaZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/alphazero.py) 和 [MuZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/muzero.py) 在3个棋类游戏([TicTacToe (井字棋)](https://github.com/opendilab/LightZero/blob/main/zoo/board_games/tictactoe/envs/tictactoe_env.py),[Connect4](https://github.com/opendilab/LightZero/blob/main/zoo/board_games/connect4/envs/connect4_env.py) 和 [Gomoku (五子棋)](https://github.com/opendilab/LightZero/blob/main/zoo/board_games/gomoku/envs/gomoku_env.py))上的基线结果:
<p align="center">
<img src="assets/benchmark/main/tictactoe_bot-mode_main.png" alt="tictactoe_bot-mode_main" width="30%" height="auto" style="margin: 0 1%;">
<img src="assets/benchmark/main/connect4_bot-mode_main.png" alt="connect4_bot-mode_main" width="30%" height="auto" style="margin: 0 1%;">
<img src="assets/benchmark/main/gomoku_bot-mode_main.png" alt="gomoku_bot-mode_main" width="30%" height="auto" style="margin: 0 1%;">
</p>

- [MuZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/muzero.py), [MuZero w/ SSL](https://github.com/opendilab/LightZero/blob/main/lzero/policy/muzero.py),[EfficientZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/efficientzero.py) 和 [Sampled EfficientZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/sampled_efficientzero.py) 在3个代表性的 [Atari](https://github.com/opendilab/LightZero/blob/main/zoo/atari/envs/atari_lightzero_env.py) 离散动作空间环境上的基线结果:
- [MuZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/muzero.py)[MuZero w/ SSL](https://github.com/opendilab/LightZero/blob/main/lzero/policy/muzero.py)[EfficientZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/efficientzero.py) 和 [Sampled EfficientZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/sampled_efficientzero.py) 在3个代表性的 [Atari](https://github.com/opendilab/LightZero/blob/main/zoo/atari/envs/atari_lightzero_env.py) 离散动作空间环境上的基线结果:
<p align="center">
<img src="assets/benchmark/main/pong_main.png" alt="pong_main" width="23%" height="auto" style="margin: 0 1%;">
<img src="assets/benchmark/main/qbert_main.png" alt="qbert_main" width="23%" height="auto" style="margin: 0 1%;">
Expand Down
Binary file modified assets/benchmark/main/2048/2048_stochasticmz_mz.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified assets/benchmark/main/minigrid/fourrooms_exploration.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit 005fd48

Please sign in to comment.