- 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.

.gitignore

@@ -20,6 +20,7 @@ env/
 
 # Logs / test / tooling
 *.log
+.cache/
 .pytest_cache/
 .mypy_cache/
 .ruff_cache/