Home > Publications . Search All . Browse All . Country . Browse PSC Pubs . PSC Report Series

PSC In The News

RSS Feed icon

Frey says China is source country of most new U.S. immigrants

Rodriguez, Geronimus, Bound and Dorling find excess mortality among blacks influences key elections

DeWitt's map of 40-year shifts in Baltimore's racial composition helps explain April 2015 uprising


Cheng wins ASA Outstanding Graduate Student Paper Award

Hicken wins 2015 UROP Outstanding Research Mentor Award

U-M ranked #1 in Sociology of Population by USN&WR's "Best Graduate Schools"

PAA 2015 Annual Meeting: Preliminary program and list of UM participants

Next Brown Bag

Mon, May 18
Lois Verbrugge, Disability Experience & Measurement

Sampling strategies for batch mode reinforcement learning

Publication Abstract

Fonteneau, Raphael, Susan A. Murphy, L. Wehenkel, and D. Ernst. 2013. "Sampling strategies for batch mode reinforcement learning." Revue d'Intelligence Artificielle, 27(2): 171-194.

We propose two strategies for experiment selection in the context of batch mode reinforcement learning. The first strategy is based on the idea that the most interesting experiments to carry out at some stage are those that are the most liable to falsify the current hypothesis about the optimal control policy. We cast this idea in a context where a policy learning algorithm and a model identification method are given a priori. The second strategy exploits recently published methods for computing bounds on the return of control policies from a set of trajectories in order to sample the state-action space so as to be able to discriminate between optimal and non-optimal policies. Both strategies are experimentally validated, showing promising results. © 2013 Lavoisier.

DOI:10.3166/RIA.27.171-194 (Full Text)

Browse | Search : All Pubs | Next