A web-based interactive reinforcement learning demonstration for games, created for my A-level Computer Science coursework.

It provides a sandbox for experimenting with different reinforcement learning techniques including Q-Learning and Policy Gradients using neural networks to learn to play common games such as Pong or find optimal strategies for tasks such as the mountain-car problem.

The website is available at: https://basimkhajwal.github.io/RL-Playground/