Superhuman AI for multiplayer poker

DOI10.1126/SCIENCE.AAY2400MaRDI QIDQ5218598zbMATH OpenOpenAlexWikidataFDO

Authors Noam Brown, Tuomas Sandholm

Publication date 4 March 2020

Published in Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1126/science.aay2400

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) (n)-person games, (n>2) (91A06) General topics in artificial intelligence (68T01)

Recommendations

• DeepStack: expert-level artificial intelligence in heads-up no-limit poker
• World-class interpretable poker

Cited in

(25)

• Limited lookahead in imperfect-information games
• scientific article; zbMATH DE number 1784984 (Why is no real title available?)
• Align, then memorise: the dynamics of learning with feedback alignment
• Exploring the constraints on artificial general intelligence: a game-theoretic model of human vs machine interaction
• Entropy regularized actor-critic based multi-agent deep reinforcement learning for stochastic games
• Direct shape optimization through deep reinforcement learning
• Construction of symmetric orthogonal designs with deep Q-network and orthogonal complementary design
• Committing to correlated strategies with multiple leaders
• Almost optimal algorithms for two-player zero-sum linear mixture Markov games
• A review on deep reinforcement learning for fluid mechanics
• Algorithm for computing approximate Nash equilibrium in continuous games with application to continuous blotto
• DeepStack: expert-level artificial intelligence in heads-up no-limit poker
• Superhuman AI for heads-up no-limit poker: Libratus beats top professionals
• Robust reinforcement learning with dynamic distortion risk measures
• Partially observable RL: benign structures and simple generic algorithms
• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
• The challenge of poker
• Value functions for depth-limited solving in zero-sum imperfect-information games
• Rethinking formal models of partially observable multiagent decision making
• Optimistic MLE: a generic model-based algorithm for partially observable sequential decision making
• Multi-agent reinforcement learning: a selective overview of theories and algorithms
• On the complexity of computing sparse equilibria and lower bounds for no-regret learning in games
• Super-Nash performance
• Defense and security planning under resource uncertainty and multi‐period commitments
• What may lie ahead in reinforcement learning

Describes a project that uses

Uses Software

• ACPC
• Pluribus
• Libratus
• DeepStack
• Torch

This page was built for publication: Superhuman AI for multiplayer poker

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5218598)