DeepStack: Expert-level artificial intelligence in heads-up no-limit poker
Matej Moravčík, Martin Schmid, NEIL R. BURCH et al. · Science · 2017
Artificial intelligence has seen several breakthroughs in recent years, with games often serving as milestones. A common feature of these games is that players have perfect information. Poker, the quintessential game of imperfect information, is a long-standing challenge problem in artificial intelligence. We introduce DeepStack, an algorithm for imperfect-information settings. It combines recursive reasoning to handle information asymmetry, decomposition to focus computation on the relevant decision, and a form of intuition that is automatically learned from self-play using deep learning. In a study involving 44,000 hands of poker, DeepStack defeated, with statistical significance, professional poker players in heads-up no-limit Texas hold'em. The approach is theoretically sound and is shown to produce strategies that are more difficult to exploit than prior approaches.
Cited by 786 works. doi:10.1126/science.aam6960 Open-access PDF
Authors
- Matej Moravčík
- Martin Schmid
- NEIL R. BURCH
- Viliam Lisý
- Dustin Morrill
- Nolan Bard
- Kevin Waugh
- Michael Johanson
- Michael Bowling
References
- ImageNet classification with deep convolutional neural networks
- Human-level control through deep reinforcement learning
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
- Equilibrium points in n -person games
- Robust Estimation of a Location Parameter
- Mastering the game of Go with deep neural networks and tree search
- Some Studies in Machine Learning Using the Game of Checkers
- Bandit Based Monte-Carlo Planning
- Temporal difference learning and TD-Gammon
- Temporal Difference Learning and TD-Gammon