Value functions for depth-limited solving in zero-sum imperfect-information games

DOI10.1016/j.artint.2022.103805OpenAlexW2949285373MaRDI QIDQ2680767

Dominik Seitz, Vojtěch Kovařík, Viliam Lisý, Karel Ha, Shuo Sun, Jan Rudolf

Publication date: 4 January 2023

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

Full work available at URL: https://arxiv.org/abs/1906.06412

zbMATH Keywords

value functioncounterfactual regret minimizationextensive form gamepartially observable stochastic gameimperfect information gamemultiagent reinforcement learningdepth limited gamedepth limited solving

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Uses Software

• Adam
• DeepStack

Cites Work

• Unnamed Item
• Reexamination of the perfectness concept for equilibrium points in extensive games
• Generalised weakened fictitious play
• Rethinking formal models of partially observable multiagent decision making
• Optimally Solving Dec-POMDPs as Continuous-State MDPs
• Timeability of Extensive-Form Games
• Multiagent Systems
• DeepStack: Expert-level artificial intelligence in heads-up no-limit poker
• The Nonstochastic Multiarmed Bandit Problem
• 10.1162/1532443041827880
• Superhuman AI for multiplayer poker
• Dynamic games with hidden actions and hidden states

This page was built for publication: Value functions for depth-limited solving in zero-sum imperfect-information games