Technical - Partner Event
AI Seminar – Chenjun Xiao
When
Nov. 12, 2021 - Nov. 12, 2021
12:00 PM – 1:00 PM MST
Where
Online
Online
Presenter: Chenjun Xiao
Title: On the Optimality of Batch Policy Optimization Algorithms
Abstract: Batch policy optimization considers leveraging existing data for policy construction before interacting with an environment. Although interest in this problem has grown significantly in recent years, its theoretical foundations remain under-developed. To advance the understanding of this problem, we provide three results that characterize the limits and possibilities of batch policy optimization in the finite-armed stochastic bandit setting. First, we introduce a class of confidence-adjusted index algorithms that unifies optimistic and pessimistic principles in a common framework, which enables a general analysis. For this family, we show that any confidence-adjusted index algorithm is minimax optimal, whether it be optimistic, pessimistic or neutral. Our analysis reveals that instance-dependent optimality, commonly used to establish optimality of on-line stochastic bandit algorithms, cannot be achieved by any algorithm in the batch setting. In particular, for any algorithm that performs optimally in some environment, there exists another environment where the same algorithm suffers arbitrarily larger regret. Therefore, to establish a framework for distinguishing algorithms, we introduce a new weighted-minimax criterion that considers the inherent difficulty of optimal value prediction. We demonstrate how this criterion can be used to justify commonly used pessimistic principles for batch policy optimization.
Bio: Chenjun Xiao is a PhD student advised by Martin Mueller and Dale Schuurmans at University of Alberta. His main research interests are reinforcement learning, including developing sample efficient planning algorithms, and understanding the theoretical foundations of batch reinforcement learning. He also spent time as a research intern at Borealis AI and Huawei. He is now a student researcher at Google brain.
The University of Alberta Artificial Intelligence (AI) Seminar is a weekly meeting where researchers (including students, developers, and professors) interested in AI can share their current research. Presenters include local speakers from the University of Alberta and industry as well as other institutions. The seminars discuss a wide range of topics related in any way to Artificial Intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems are of interest. Learn more at the AI Seminar website and by subscribing to the mailing list!
Looking to build AI capacity? Need a speaker at your event?
