MIT DeepTraffic top 2% solution (75.01 mph) 🚗.

DQN on Flappy Bird

A reinforcement learning pong game

MazeRunner project is an interactive, browser-based visualization of a Deep Q-Network (DQN) agent learning to solve a 10x10 maze. The entire reinforcement learning process, from model creation to training and inference, runs directly in your browser using TensorFlow.js.

Training a DQN agent to drive a car in a racing game

🐍 Train a neural network to play Snake, showcasing AI's potential in game strategy and decision-making. Run it easily with provided setup instructions.

This is a snake game on web. Can be injected DQN nn model.