# Combining Deep Reinforcement Learning and Search for Imperfect-Information Games

*Source* · `src-brown-2020-rebel` · status: **n/a**

| field | value |
|---|---|
| kind | Preprint |
| authors | Noam Brown, Anton Bakhtin, Adam Lerer, Qucheng Gong |
| venue | arXiv |
| date | 2020-07-27 |
| arxiv | 2007.13544 |
| accessed | 2026-10-24 |

## Notes

ReBeL: self-play RL plus search that provably converges to a Nash equilibrium in two-player zero-sum games; reduces to an AlphaZero-like algorithm in perfect-information games; superhuman heads-up no-limit hold'em.

## Backlinks (computed)

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

## Citation

Noam Brown, Anton Bakhtin, Adam Lerer, Qucheng Gong (2020-07-27). *Combining Deep Reinforcement Learning and Search for Imperfect-Information Games*. arXiv https://arxiv.org/abs/2007.13544

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