Reinforcement learning teaching

Each environment is a standalone .py file using PyTorch and the standard library. No Gymnasium: students can read and change the physics, observations, actions and rewards in one place.

Bandits

Inspect estimates and true rewards.

Compare the estimates with each arm’s true reward. (larger view)

Cat, dog and humanoid

Cat / Dog / Humanoid

A learned cat gait over mixed terrain. (larger view)

Multi-agent racing

Cooperative / competitive

The team finishes when every racer completes the circuit. (larger view)