This repository aims to provide and cover different reinforcement learning algorithms and aproaches from scratch in Python. This is ongoing work which will cover the following topics:
- Gymnasium Environment
- Custom gymnasium environment (Done)
- Q Learning Algorithm
- Gymnasium Environment
- Custom Gymnasium Environment (Done)
- SARSA Algorithm
- Gymnasium Environment
- Custom Gymnasium Environment (Done)
- Deep Q-Learning Network (DQN)
- Double Deep Q-Learning Network (DDQN)
- Advantage Actor Critic (A2C)
- Asynchronous Advantage Actor Critic (A3C)
- Policy Gradient Algorithm