Open-Source Notebooks Implement RL Algorithms From Scratch, From Q-learning to PPO

ZabihullahAtal · x · 2026-09-05

The GitHub repo reinforcement-learning-algorithms by ChristianOrr offers from-scratch implementations of RL algorithms ranging from tabular methods to deep RL, intentionally stripped down to the essentials.

Included notebooks cover Q-learning, Double Q-learning, SARSA (with function approximation and Acme variants), REINFORCE (with baseline), Actor-Critic, discrete A2C, GAE/Monte-Carlo variants, plus videos and environment utilities.

Related event: RL Open-Source Resources: From-Scratch Algorithms and Classic Awesome List(2 posts)→

Original post →

More from Research

Research channel →