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

PSC In The News

RSS Feed icon

Owen-Smith says universities must demonstrate value of higher education

Armstrong says USC's removal of questions from a required Title IX training module may reflect student-administration relations

Fomby finds living with step- or half-siblings linked to higher aggression among 5 year olds

Highlights

PRB training program in policy communication for pre-docs. Application deadline, 2.28.2016

Call for proposals: PSID small grants for research on life course impacts on later life wellbeing

PSC News, fall 2015 now available

Barbara Anderson appointed chair of Census Scientific Advisory Committee

Next Brown Bag

Monday, Feb 1 at noon, 6050 ISR-Thompson
Sarah Miller

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