temporal-differencing-learning

This directory, contains the source code of the Adaptive PacMan i designed for my Master's degree dissertation. [Videoclip Inside]

Benchmarking tabular RL (Q-Learning, Double-Q, SARSA, Expected SARSA) on Gymnasium Taxi — with action masking, ablations, statistical analysis, and demos.

Reinforcement Learning Projects on Dynamic Programming, Monte Carlo and Deep Q-Networks (October, 2020).

Visualization of some reinforcement learning algorithms (sarsa, qlearning, monte carlo)

A Python script that executes a RL algorithm (Temporal Difference/Q-Learning) that trains an agent inside a labyrinth to find the exit with the least number of steps possible

Implementation of some Reinforcement Learning methods for grid world in Python

An AI plays Fib2584, a variation of the well-known game 2048, with temporal difference learning.

Experiments with n-step Temporal Difference learning (Q-learning, SARSA, Expected SARSA) in a Cliff Walking environment, inspired by Sutton & Barto’s Reinforcement Learning.

Assignments for CS747 - Foundations of Intelligent and Learning Agents

Play Tic-Tac-Toe against a reinforcement learning agent that just learned to play through temporal difference learning

Train a Tic-Tac-Toe and a Connect-4 player using the TD-lambda algorithm

Gino, The Temporal Difference Q Learning Gin Agent!

Teaching an agent to navigate "Rectangular Course" (4 turns) using Temporal Difference (TD) learning

Trained an artificial intelligence agent using reinforcement learning to play a simple version of the game "Snake". Implemented a Temporal Difference version of the Q-learning Algorithm. Completed for school.

RL Assignments , IIT KGP Autumn 2024

Reinforcement Learning agent for 2048 game

Implemented an Agent using Temporal Difference Learning to play TicTacToe

Learn Tabular Q-Learning, $\varepsilon$-greedy exploration, and Bellman Dynamic Programming in the browser with interactive Tic-Tac-Toe. Zero dependencies.