Solving zero-sum one-sided partially observable stochastic games

DOI10.1016/j.artint.2022.103838arXiv2010.11243OpenAlexW3093689670MaRDI QIDQ6098841

Branislav Bošanský, Karel Horák, Vojtěch Kovařík, Christopher Kiekintveld

Publication date: 19 June 2023

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2010.11243

zbMATH Keywords

value iterationheuristic search value iterationone-sided informationzero-sum partially observable stochastic games

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Zero-sum stochastic games with partial information
• On general minimax theorems
• The role of information in the cop-robber game
• Efficient computation of behavior strategies
• Efficient computation of equilibria for extensive two-person games
• On Stefan Banach and some of his results
• Optimal control of Markov processes with incomplete state information
• On a minimax theorem and its applications to functional analysis
• Optimally Solving Dec-POMDPs as Continuous-State MDPs
• An Exact Double-Oracle Algorithm for Zero-Sum Extensive-Form Games with Imperfect Information
• The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs
• DeepStack: Expert-level artificial intelligence in heads-up no-limit poker
• Superhuman AI for heads-up no-limit poker: Libratus beats top professionals
• Distributionally Robust Partially Observable Markov Decision Process with Moment-Based Ambiguity
• FSTTCS 2005: Foundations of Software Technology and Theoretical Computer Science
• Networks

This page was built for publication: Solving zero-sum one-sided partially observable stochastic games