Educational project comparing synchronous vs asynchronous dynamic programming algorithms (Policy Iteration, Value Iteration, In-Place VI, Prioritized Sweeping) for MDP solving. Well-documented with clear algorithm explanations but minimal adoption (1 star, no external users).

Educational RL mini-project implementing MC, Q-learning, and SARSA(λ) on a tennis rally simulator with a 6-feature state space. Clean implementation but lacks tests, CI, type hints, and formal documentation beyond README. Early-stage (~10 commits in 10 days).

Educational reinforcement learning project implementing Easy21 blackjack variant with Monte Carlo and TD(λ) learning algorithms. Untyped Python code with no tests, CI, or license; minimal README.

Single Jupyter notebook implementing Sutton-Barto Chapter 2 exercise solutions with reinforcement learning code. Minimal documentation, no tests/CI, experimental scope.

Early-stage reinforcement learning grid world implementation with policy iteration algorithms. 7kb codebase across 5 files (2 substantive), 7 commits in 5 days. No tests, CI, license, or type hints.

Exercise solutions for "The Computer Always Wins" book. Five untyped Python algorithm implementations (maze solvers, N-Queens, word ladder) with flat structure, no tests/CI, minimal docs, and single-week development. Experimental learning project.

Personal educational RL project implementing policy iteration on a 1D gridworld environment. Single untyped Python file (hallway5RL.py) with no tests, CI, or documentation beyond inline comments.

Empty scaffold with no commits, files, or documentation. Created 2026-06-26 with zero recent activity, no README, tests, CI, or meaningful structure.