This repository contains 3 different Deep Reinforcement Learning implementations for the CarRacing-v2 game from gymnasium:
- Deep Q-Learning (DQN)
- Dueling Deep Q-Learning (DDQN)
- Proximal Policy Optimization (PPO)
The Deep Learning Architecture is based on Convolutional Neural Networks (CNN).
The goal is for the agent to learn how to control the car and gain as many rewards as possible.
Here is an example: