# Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning

*Source* · `src-matthews-2024-craftax` · status: **n/a**

| field | value |
|---|---|
| kind | Peer-reviewed paper |
| authors | Michael Matthews, Michael Beukman, Benjamin Ellis, Mikayel Samvelyan, Matthew Jackson, Samuel Coward, Jakob Foerster |
| venue | ICML 2024 |
| date | 2024-02-26 |
| url | https://arxiv.org/abs/2402.16801 |
| arxiv | 2402.16801 |
| accessed | 2026-10-24 |
| notes | JAX rewrite of the Crafter survival-crafting game; up to 250x faster than the Python original; PPO for 1 billion interactions in under an hour on one GPU. |

## Backlinks (computed)

**cited by:** [Massively parallel GPU simulation](../technique/massively-parallel-simulation.md)

## Citation

Michael Matthews, Michael Beukman, Benjamin Ellis, Mikayel Samvelyan, Matthew Jackson, Samuel Coward, Jakob Foerster (2024-02-26). *Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning*. ICML 2024 https://arxiv.org/abs/2402.16801

---
Provenance: created in run `2026-10-24-techniques-sim-math`.