Tartanian7: A Champion Two-Player No-Limit Texas Hold'em Poker-Playing Program

The leading approach for solving large imperfect-information games is automated abstraction followed by running an equilibrium-finding algorithm. We introduce a distributed version of the most commonly used equilibrium-finding algorithm, counterfactual regret minimization (CFR), which enR to scale to dramatically larger abstractions and numbers of cores. The new algorithm begets constraints on raction so as to make the pieces running on different computers disjoint. We introduce an algorithm for generating such abstractions while capitalizing on state-of-the-art abstraction ideas such as imperfect recall and the earth-mover’sdistance similarity metric. Our techniques enabled an equilibrium computation of unprecedented size on a supercomputer with a high inter-blade memory latency. Prior approaches run slowly on this architecture. Our approach also leads to a significant improvement over using the prior best approach on a large shared-memory server with low memory latency. Finally...

• Type: Journal
• Year: 2015
• Where: AAAI
• Authors: Noam Brown, Sam Ganzfried, Tuomas Sandholm
• Keywords: AAAI 2015, Intelligent Agents