Solving Heads-Up Limit Texas Hold'em

By Oskari Tammelin, Neil Burch, Michael Bradley Johanson, Michael H. Bowling. 2015

182 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Game & Decision Theory

Citations in the corpus

OpenSpiel: A Framework for Reinforcement Learning in Games (2019, methodology): “In addition to basic CFR, OpenSpiel contains a few variants of Monte Carlo CFR [34] such as outcome sampling and external sampling, and CFR+ [69].”
Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms (2019, methodology): “.,2015), where a player is required to take an action at each information set.Bowling et al.(2015) has for the ﬁrst time reported solving HULHE to approximate Nash equilibrium via CFR+ (Tammelin,2014;Tammelin et al., 2015), a variant of counterfactual regret minimization (Zinkevich et al.,2008). Sub”
Deep Counterfactual Regret Minimization (2018, background): “However, most of these faster variants of CFR do not handle approximation error well (Tammelin et al., 2015; Burch, 2017; Brown & Sandholm, 2019; Schmid et al., 2019).”
Depth-Limited Solving for Imperfect-Information Games (2018, methodology): “This was done by running the CFR+ equilibrium-approximation algorithm [37] for 1,000 iterations, which resulted in less than 1 mbb/g of exploitability within the action abstraction.”
Safe and Nested Endgame Solving for Imperfect-Information Games (2017, methodology): “For equilibrium finding, we used a version of CFR called CFR+ (Tammelin et al. 2015) with the speed-improvement techniques introduced by Johanson et al.”
Libratus: The Superhuman AI for No-Limit Poker (2017, methodology): “2Heads-up limit Texas Hold’em, a significantly smaller game with 1013 decision points, was essentially solved in 2015 [Bowling et al., 2015; Tammelin et al., 2015].”
Actor-Critic Policy Optimization in Partially Observable Multiagent Environments (2018, methodology): “Near-optimal solutions for heads-up limit Texas Hold’em were found with tabular methods using state aggregation, powered by policy iteration algorithms based on regret minimization [102, 87, 12].”
Time and Space: Why Imperfect Information Games are Hard (2018, background): “These results were originally published at IJCAI [85].”
Dynamic Thresholding and Pruning for Regret Minimization (2017, methodology): “CFR+, a variant of CFR with RM, was recently used to essentially solve Limit Texas Hold’em, the largest imperfectinformation game ever to be essentially solved and the first that is played competitively by humans (Bowling et al. 2015; Tammelin et al. 2015).”