Poker-AI.org Poker AI and Botting Discussion Forum 2013-05-17T20:46:27+00:00 http://poker-ai.org/phpbb/feed.php?f=25&t=2433 2013-05-17T20:46:27+00:00 2013-05-17T20:46:27+00:00 http://poker-ai.org/phpbb/viewtopic.php?t=2433&p=4196#p4196 <![CDATA[Re: CFR-D: Solving Imperfect Information Games Using Decompo]]> Is it possible for this algorithm to consider our hole cards and only roll out hole cards for the opponent because of both players playing a best response?

Statistics: Posted by LOLWorld — Fri May 17, 2013 8:46 pm


]]>
2013-04-01T15:44:48+00:00 2013-04-01T15:44:48+00:00 http://poker-ai.org/phpbb/viewtopic.php?t=2433&p=3604#p3604 <![CDATA[Re: CFR-D: Solving Imperfect Information Games Using Decompo]]>

Think they're planning on solving a large, unabstracted trunk, up to maybe the turn (?), then just solving the remaining subtrees online during play at the ACPC?

Statistics: Posted by cantina — Mon Apr 01, 2013 3:44 pm


]]>
2013-03-31T14:57:57+00:00 2013-03-31T14:57:57+00:00 http://poker-ai.org/phpbb/viewtopic.php?t=2433&p=3601#p3601 <![CDATA[CFR-D: Solving Imperfect Information Games Using Decompositi]]> CFR-D: Solving Imperfect Information Games Using Decomposition
by: Neil Burch, Michael Bowling

Abstract
One of the significant advantages in problems with perfect information, like search or games like checkers, is that they can be decomposed into independent pieces. In contrast, problems with imperfect information, like market modeling or games like poker, are treated as a single decomposable whole. Handling the game as a single unit places a much stricter limit on the size of solvable imperfect information games. This paper has two main contributions. First, we introduce CFR-D, a new variant of the counterfactual regret minimising family of algorithms. For any problem which can be decomposed into a trunk and subproblems, CFR-D can handle the trunk and each subproblem independently. Decomposition lets CFR-D have memory requirements which are sub-linear in the number of decision points, a desirable property more commonly associated with perfect information algorithms. Second, we present an algorithm for recovering an equilibrium strategy in a subproblem given the trunk strategy and some summary information about the subproblem.

http://arxiv.org/pdf/1303.4441v1.pdf

Statistics: Posted by pumpkinpuree — Sun Mar 31, 2013 2:57 pm


]]>