docs: update README with troubleshooting and performance curves

Fix plot generation to parse TRL log_history and regenerate PNGs

Update trained LoRA adapter and reward curves

UI Overhaul, W&B Tracking, Automated Compliance Scripts, and Documentation Update for Hackathon Submission

Update training plots with successful learning curves

Update README with HF space and training plots, reduce colab model size

Initial commit for EcoGrid-OpenEnv hackathon