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

PSC In The News

RSS Feed icon

Savolainen links antisocial behavior in childhood to disadvantage and poverty in adulthood

Norton et al. put dollar value on relief from chronic pain for Americans age 50+

Seefeldt says TANF restrictions may limit program's help for poor Americans

More News

Highlights

Paula Fomby to succeed Jennifer Barber as Associate Director of PSC

PSC community celebrates Violet Elder's retirement from PSC

Neal Krause wins GSA's Robert Kleemeier Award

U-M awarded $58 million to develop ideas for preventing and treating health problems

More Highlights

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