A Practical Use of Imperfect Recall

Perfect recall is the common and natural assumption that an agent never forgets. As a consequence, the agent can always condition its choice of action on any prior observations. In this paper, we explore relaxing this assumption. We observe the negative impact this relaxation has on algorithms: some algorithms are no longer well-defined, while others lose their theoretical guarantees on the quality of a solution. Despite these disadvantages, we show that removing this restriction can provide considerable empirical advantages when modeling extremely large extensive games. In particular, it allows fine granularity of the most relevant observations without requiring decisions to be contingent on all past observations. In the domain of poker, this improvement enables new types of ion to be used in the abstraction. By making use of imperfect recall and new types of information, our poker program was able to win the limit equilibrium event as well as the no-limit event at the 2008 AAAI Co...

• Type: Conference
• Year: 2009
• Where: SARA
• Authors: Kevin Waugh, Martin Zinkevich, Michael Johanson, Morgan Kan, David Schnizlein, Michael H. Bowling
• Keywords: Artificial Intelligence, Imperfect Recall, Perfect Recall, Perfect Recall Counterparts, SARA 2009