ROOG 2960ac1df5 - Implemented policy_utils.py with helper functions for action selection, including epsilon-greedy support. ...

- Updated `requirements.txt` to relax PyTorch version constraint for better GPU compatibility.
- Added detailed GPU setup instructions, new device fallback options, and command examples to `README.md`.
- Developed a new script `plot_model_max_x_trend.py` for visualizing training trends, generating HTML/Markdown reports.

2026-02-13 16:11:38 +08:00

..

__init__.py

feat: initial mario rl mvp

2026-02-12 18:54:06 +08:00

env.py

- Implemented policy_utils.py with helper functions for action selection, including epsilon-greedy support.

2026-02-13 16:11:38 +08:00

eval.py

- Implemented policy_utils.py with helper functions for action selection, including epsilon-greedy support.

2026-02-13 16:11:38 +08:00

plot_model_max_x_trend.py

- Implemented policy_utils.py with helper functions for action selection, including epsilon-greedy support.

2026-02-13 16:11:38 +08:00

policy_utils.py

- Implemented policy_utils.py with helper functions for action selection, including epsilon-greedy support.

2026-02-13 16:11:38 +08:00

record_video.py

- Implemented policy_utils.py with helper functions for action selection, including epsilon-greedy support.

2026-02-13 16:11:38 +08:00

runtime.py

- Implemented policy_utils.py with helper functions for action selection, including epsilon-greedy support.

2026-02-13 16:11:38 +08:00

train_ppo.py

- Implemented policy_utils.py with helper functions for action selection, including epsilon-greedy support.

2026-02-13 16:11:38 +08:00

utils.py

- Implemented policy_utils.py with helper functions for action selection, including epsilon-greedy support.

2026-02-13 16:11:38 +08:00