RL-course-huggin-face

This repository contains reinforcement learning agent I trained for the Deep Reinforcement Learning Course from Hugging Face this

1. Lunar lander

Agent trained using PPO implemented in Stable-Baselines3

replay.mp4

2. Taxi-v3

Agent trained using Q-learning implemented from scratch.

replay.mp4

3. CartPole-v1

Agent trained using custom PolicyGradient implemented in PyTorch

replay.mp4

4. PixelCopter

Agent trained the same ways as in CartPole. Diffrence beeing the input was an image of the game.

replay.mp4

5. PandaReachDense-v2

This agent was trained using Stable-Baselines3 implementation of A2C (Actor-Critic)

replay.1.mp4