Technical - Partner Event
AI Seminar – Dustin Morrill
When
July 30, 2021 - July 30, 2021
12:00 PM – 1:00 PM MST
Where
Online
Online
Title: Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games
Abstract: Hindsight rationality is an approach to playing general-sum games that prescribes no-regret learning dynamics for individual agents with respect to a set of deviations, and further describes jointly rational behavior among multiple agents with mediated equilibria. To develop hindsight rational learning in sequential decision-making settings, we formalize behavioral deviations as a general class of deviations that respect the structure of extensive-form games. Integrating the idea of time selection into counterfactual regret minimization (CFR), we introduce the extensive-form regret minimization (EFR) algorithm that achieves hindsight rationality for any given set of behavioral deviations with computation that scales closely with the complexity of the set. We identify behavioral deviation subsets, the partial sequence deviation types, that subsume previously studied types and lead to efficient EFR instances in games with moderate lengths. In addition, we present a thorough empirical analysis of EFR instantiated with different deviation types in benchmark games, where we find that stronger types typically induce better performance.
Short bio: Dustin Morrill is a Ph.D. candidate at the University of Alberta and Amii, co-supervised by Professor Michael Bowling and Professor Amy Greenwald of Brown University. He works on multi-agent learning and scaleable, dependable learning algorithms. Dustin is a co-author of DeepStack and created Cepheus’s public match interface.
Looking to build AI capacity? Need a speaker at your event?
