Libratus: The Superhuman AI for No-Limit Poker

By Noam Brown, Tuomas Sandholm. 2017

108 citations recorded by the source corpus.

No-limit Texas Hold'em is the most popular variant of poker in the world. Heads-up no-limit Texas Hold'em is the main benchmark challenge for AI in imperfect-information games. We present Libratus, the first--and so far only--AI to defeat top human professionals in that game. Libratus's architecture features three main modules, each of which has new algorithms: pre-computing a solution to an abstraction of the game which provides a high-level blueprint for the strategy of the AI, a new nested subgame-solving algorithm which repeatedly calculates a more detailed strategy as play progresses, and a self-improving module which augments the pre-computed blueprint over time.

Subfields: Artificial Intelligence, Clinical Psychology, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sergey Levine
2. Mohammad Norouzi
3. Dale Schuurmans
4. Zhuoran Yang
5. Rishabh Agarwal
6. Kaiqing Zhang
7. Tamer Basar
8. Lasse Becker-Czarnetzki

In Clinical Psychology

1. Zhuoran Yang
2. Kaiqing Zhang
3. Lasse Becker-Czarnetzki
4. Tamer Basar

In Sociology and Political Science

1. Mohammad Norouzi
2. Zhuoran Yang
3. Dale Schuurmans
4. Kaiqing Zhang
5. Lasse Becker-Czarnetzki
6. Tamer Basar

Citations in the corpus

• Striving for Simplicity in Off-policy Deep Reinforcement Learning (2019, background): “Recent progress in mastering the games of Go [50] and Poker [43, 10] and advances in robotic control [36, 44, 30] present additional supporting evidence for the enormous potential of deep RL.”
• An Introduction to Deep Reinforcement Learning (2018, unknown): “In recent years, several notable works have stood out in using deep RL for mastering Go (Silver et al., 2016a) or Poker (Brown and Sandholm, 2017; Moravčik et al., 2017).”
• Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms (2019, background): “(2019) propose to estimate the counterfactual value functions via regression; Brown and Sandholm (2015); Brown et al.”
• Report on DeepStack Expert-Level Artificial Intelligence in Heads-Up No-Limit Poker (2019, methodology): “To give a wider view on different attempts to solve the problem of HUNL Poker i want to call out some differences between Libratus and DeepStack.”