This repository has all the codes and sources of various RL algorithms that I have implemented.

A collection of deep and tabular reinforcement learning algorithms, including implementations of DQN, Dueling DQN, Q-learning, SARSA, n-step Tree Backup, and Monte Carlo.

Q-Learning Agent that Learns and Plays Alan Parr’s Traffic Lights Game

Matchbox-RL: A tangible reinforcement learning library for Python. Based on Donald Michie's 1961 MENACE algorithm using matchboxes and colored beads. Perfect for education and visualizing RL.

RL was cheaper. The heuristic was safer. Neither was correct. POLARIS stress-tests operational policies under chaos, demand spikes, and black swan events asking one question: which policy survives when everything goes wrong? Built with constrained RL, Bayesian modeling, CVaR risk metrics, and a human-in-the-loop governor.

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Q-Learning agent that learns to navigate a 4×12 cliff-edge grid using ε-greedy exploration and Bellman updates — trained from scratch with NumPy + Gymnasium in 63 lines of Python.

Benchmarking 11 tabular RL methods on a 6×6 FrozenLake grid under deterministic and slippery dynamics.

Implementation of Q-Learning, SARSA, and Dyna Q to allow an agent to navigate the FrozenLake-v0 environment from OpenAI.

强化学习中文学习笔记与可复现实验仓库，涵盖 Q-Learning、SARSA、Monte Carlo Control 及 FrozenLake、CliffWalking、Blackjack 示例。