Backgammon OpenAI Gym

A simple reinforcement learning simulation engine for OpenAI's gym.

Z. Sun, Q. Wang, J. Pan and Y. Xia, "Data-Driven MPC for Linear Systems using Reinforcement Learning," 2021 China Automation Congress (CAC), Beijing, China, 2021, pp. 394-399, doi: 10.1109/CAC53003.2021.9728233.

Implementation of Q-Learning using TD error to navigate a maze avoiding obstacles and a moving enemy

Implementation of Reinforcement Algorithms from scratch

train an RNN to estimate value in a POMDP using TD learning

Onitama Board Game Simulator with Reinforcement Learning opponents (CS 5033)

Implementation of reinforcement learning algorithms to solve pacman game. Part of CS188 AI course from UC Berkeley.

NYCU 強化學習專論 Selected Topics in Reinforcement Learning Fall 2023

👉 A biologically grounded RL agent that learns through dopamine signals, membrane dynamics, and sleep-driven synaptic pruning.

Code for the numerical experiments in Zhang, Sheng, Zhe Zhang, and Siva Theja Maguluri. "Finite Sample Analysis of Average-Reward TD Learning and Q-Learning."

AI of modified version of Othello/Reversi

multi-armed bandit, gambler problem, cliff problem and TD learning

🐀 TD learning model of a rat who learns how to navigate in a watermaze from the activation of its place cells

A neural network playing Backgammon.

TD-Gammon implementation

python implementation of SARSA learning algorithm to solve a maze

Educational RL repo: DP, MC, SARSA, Q-learning from scratch using NumPy and GridWorld.

Tic-Tac-Toe agent trained by Deep Reinforcement Learning

Master MVA - Reinforcement Learning Project