This repository houses implementations of various reinforcement learning algorithms, including Deep Q-Networks, REINFORCE, Actor-Critic, and Proximal Policy Optimization. The implementations are developed both from scratch and utilizing open-source frameworks. This work is adapted from the Hugging Face course on Deep Reinforcement Learning.
| Demo Description | Demo Link | Video Link | Image Link |
|---|---|---|---|
| SpaceInvaders using Deep Q-Networks | Demo Link | - |  |
| Robotic Arm with A2C Model | Demo Link | Video Link |  |
| LunarLanding with PPO (Stablebaselines) | Demo Link | Video Link |  |
| Lunar Landing with PPO (from scratch implementation) | Demo Link | Video Link | |
| VizDoom using PPO (Sample Factory) | Demo Link | Video Link |  |