Superhuman AI for heads-up no-limit poker: Libratus beats top professionals
From MaRDI portal
Publication:4967518
DOI10.1126/science.aao1733zbMath1415.68163OpenAlexW2773381986WikidataQ46195803 ScholiaQ46195803MaRDI QIDQ4967518
Tuomas W. Sandholm, Noam Brown
Publication date: 3 July 2019
Published in: Science (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1126/science.aao1733
Noncooperative games (91A10) General topics in artificial intelligence (68T01) Probabilistic games; gambling (91A60) Software, source code, etc. for problems pertaining to game theory, economics, and finance (91-04)
Related Items (14)
Align, then memorise: the dynamics of learning with feedback alignment* ⋮ Solving zero-sum one-sided partially observable stochastic games ⋮ Provably efficient reinforcement learning in decentralized general-sum Markov games ⋮ Fast convergence of optimistic gradient ascent in network zero-sum extensive form games ⋮ Committing to correlated strategies with multiple leaders ⋮ Evaluating Strategic Structures in Multi-Agent Inverse Reinforcement Learning ⋮ A distributed algorithm to obtain repeated games equilibria with discounting ⋮ The Hanabi challenge: a new frontier for AI research ⋮ Analysis of Hannan consistent selection for Monte Carlo tree search in simultaneous move games ⋮ Libratus ⋮ Multi-agent reinforcement learning: a selective overview of theories and algorithms ⋮ World-class interpretable poker ⋮ Asymmetric Action Abstractions for Planning in Real-Time Strategy Games ⋮ Computing Large Market Equilibria Using Abstractions
This page was built for publication: Superhuman AI for heads-up no-limit poker: Libratus beats top professionals
