You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A coding project for Math 480 Combinatorial Game Theory (Spring 2024) exploring the relationship between AI and combinatorial game theory. Specifically, I will study the game Toads and Frogs by implementing a DQN reinforcement learning algorithm from scratch.
This project provides a comprehensive understanding of reinforcement learning, focusing on Deep Q-Learning (DQN). It involves exploring the OpenAI Gym library, implementing DQN from DeepMind's seminal paper, and enhancing the DQN algorithm for improved performance and stability.
Deep Q-Learning consists of combining Q-Learning with Artificial Neural Networks. Inputs are encoded vectors, each one defining a state of the environment. These inputs go to an Artificial Neural Network, where the output is the action to play
Implementation of the Double Deep Q-Learning algorithm with a prioritized experience replay memory to train an agent to play the minichess variante Gardner Chess
This repo implements Deep Q-Network (DQN) for solving the Frozenlake-v1 environment of the Gymnasium library using Python 3.8 and PyTorch 2.0.1 in both 4x4 and 8x8 map sizes.
This repo implements Deep Q-Network (DQN) for solving the Cliff Walking v0 environment of the Gymnasium library using Python 3.8 and PyTorch 2.0.1 with the finest tuning.