DRLPython — deep RL coursework

Course material for a deep reinforcement learning module, kept with the work I did on top of the provided harness.

• drl_sample_project_python/drl_lib/to_do/ — the graded part: dynamic programming, Monte-Carlo methods and temporal-difference learning over grid-world and line-world MDPs, driven from main.py.
• drl_sample_project_python/drl_lib/do_not_touch/ — the instructor-provided environment wrappers and result structures.
• drl_contracts/ — the Rust trait definitions describing the environment API the harness expects.
• drl_sample_project/ — the reference Rust sample project shipped with the course.

The short version: implement the three methods under to_do/, then run python drl_sample_project_python/main.py to see each demo print its learning curves.