CartPole-v1
A small control benchmark where an agent balances a pole by pushing its cart left or right.
Published by Farama Foundation
Setup and evaluation
Use CartPole to verify that a reinforcement learning training loop can handle observations, discrete actions, and episode boundaries. Compare average episode length across fixed evaluation seeds instead of reporting a single successful run.
Install with pip install gymnasium. Create the environment with gymnasium.make('CartPole-v1'). Rendering is optional and uses the classic-control extra.
- Framework
- Gymnasium
- Access
- Local Gymnasium environment. No account required.