Solving for Best Responses and Equilibria in Extensive-Form Games with Reinforcement Learning Methods

DOI10.1007/978-3-319-47843-2_11zbMath1437.91066OpenAlexW2594844947MaRDI QIDQ3299845

Jiacui Li, Amy Greenwald, Eric Sodomka

Publication date: 27 July 2020

Published in: Outstanding Contributions to Logic (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-319-47843-2_11

zbMATH Keywords

reinforcement learningBayesian equillibriumpartially observable Markov games

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Games in extensive form (91A18) Rationality and learning in game theory (91A26)

Related Items (1)

Self-confirming price-prediction strategies for simultaneous one-shot auctions

Uses Software

• Gambit

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Planning and acting in partially observable stochastic domains
• Computing pure Bayesian-Nash equilibria in games with finite actions and continuous types
• Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model
• A two stage sequential auction with multi-unit demands
• Synergies and price trends in sequential auctions
• A sparse sampling algorithm for near-optimal planning in large Markov decision processes
• Near-optimal reinforcement learning in polynomial time
• Efficient computation of equilibria for extensive two-person games
• Non-cooperative games
• 10.1162/1532443041827880
• The Complexity of Computing a Nash Equilibrium

This page was built for publication: Solving for Best Responses and Equilibria in Extensive-Form Games with Reinforcement Learning Methods