Commit Graph

  • f536f5f39c 为评估新增视频录制支持,包括单环境和矢量环境录像功能,并更新 README.md 添加使用示例和效果展示。 main ROOG 2026-02-14 13:19:59 +08:00
  • 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. ROOG 2026-02-13 16:11:38 +08:00
  • 71008dfb72 feat: improve device handling and add stochastic option Roog (顾新培) 2026-02-12 19:13:12 +08:00
  • d23de69b9a feat: initial mario rl mvp Roog (顾新培) 2026-02-12 18:54:06 +08:00