# Pluribus: First AI to beat pros in 6-player poker

*Source* · `src-facebook-2019-pluribus-blog` · status: **n/a**

| field | value |
|---|---|
| kind | Technical report / blog |
| authors | Facebook AI, Carnegie Mellon University |
| venue | Facebook AI blog |
| date | 2019-07-11 |
| url | https://ai.facebook.com/blog/pluribus-first-ai-to-beat-pros-in-6-player-poker/ |
| accessed | 2026-10-24 |

## Notes

Blueprint by improved Monte Carlo CFR in 8 days on a 64-core server, under 512 GB RAM, no GPUs, under $150; play on two CPUs and under 128 GB; 1-33 s per decision (about 20 s per hand); about 5 bb/100 over 10,000 hands; leaf nodes choose among four continuation strategies.

## Backlinks (computed)

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

## Citation

Facebook AI, Carnegie Mellon University (2019-07-11). *Pluribus: First AI to beat pros in 6-player poker*. Facebook AI blog https://ai.facebook.com/blog/pluribus-first-ai-to-beat-pros-in-6-player-poker/

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