# DeepStack: Expert-level artificial intelligence in heads-up no-limit poker

*Source* · `src-moravcik-2017-deepstack` · status: **n/a**

| field | value |
|---|---|
| kind | Peer-reviewed paper |
| authors | Matej Moravčík, Martin Schmid, Neil Burch, Viliam Lisý, Dustin Morrill, Nolan Bard, Trevor Davis, Kevin Waugh, Michael Johanson, Michael Bowling |
| venue | Science |
| date | 2017 |
| doi | 10.1126/science.aam6960 |
| arxiv | 1701.01724 |
| accessed | 2026-10-24 |

## Notes

Recursive reasoning with decomposition and a learned value function; beat professionals with statistical significance over 44,000 hands of heads-up no-limit hold'em.

## Backlinks (computed)

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

## Citation

Matej Moravčík, Martin Schmid, Neil Burch, Viliam Lisý, Dustin Morrill, Nolan Bard, Trevor Davis, Kevin Waugh, Michael Johanson, Michael Bowling (2017). *DeepStack: Expert-level artificial intelligence in heads-up no-limit poker*. Science https://doi.org/10.1126/science.aam6960

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