# Mastering the game of Stratego with model-free multiagent reinforcement learning

*Source* · `src-perolat-2022-deepnash` · status: **n/a**

| field | value |
|---|---|
| kind | Peer-reviewed paper |
| authors | Julien Perolat, et al. |
| venue | Science 378:990-996 |
| date | 2022-12-02 |
| doi | 10.1126/science.add4679 |
| arxiv | 2206.15378 |
| accessed | 2026-10-24 |
| notes | DeepNash: Regularised Nash Dynamics (R-NaD), model-free, no search; top-3 2022 and all-time ranking on the Gravon Stratego platform against human experts. |

## Backlinks (computed)

**cited by:** [Regret minimization and search for imperfect-information games](../technique/imperfect-information-solvers.md)

## Citation

Julien Perolat, et al. (2022-12-02). *Mastering the game of Stratego with model-free multiagent reinforcement learning*. Science 378:990-996 https://doi.org/10.1126/science.add4679

---
Provenance: created in run `2026-10-24-techniques-rl-design`.