Weg's Tutorials

Reinforcement Learning:

Foundations

Topic Implemented Tutorial
Q Tabular Learning soon
Actor Critic here
Deep Q Learning here
Experience Replay here
Life After Experience Replay 🎓 here

Upgrades

Topic Implemented Tutorial
Cleanup, Epsilon-Greedy, and Numpy Memory 🚿 here
Double DQL here
Dueling DQL
Dueling Double DQL
Continuous Action Spaces

Pathways

Topic Implemented Tutorial
Prioritized Experience Replay soon
Distributed Learning: A2C/A3C
Batch PPO hard
Curiosity: ICM hard
It Was Me: ICM2 harder
Multi Agent
Go-Explore hard