chore: codebase hygiene pass — untrack weights, migrate to logging, tidy comments

docs(round4): finalize R4 Double DQN results — 78% Holdout, Grid-SPL clarification

style(train): remove forward-reference quotes from type hints (Python 3.10+)

fix(train): use terminated-only mask for TD bootstrap (Gymnasium v0.26)

fix(train): guarantee BFS-connected start/goal, bounded retry with fallback

chore: initial project scaffold