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

PSC In The News

RSS Feed icon

Lam looks at population and development in next 15 years in UN commission keynote address

Mitchell et al. find harsh family environments may magnify disadvantage via impact on 'genetic architecture'

Frey says Arizona's political paradoxes explained in part by demography

Highlights

4/17/14: NIH announces new policy for resubmissions

2014 PAA Annual Meeting, May 1-3, Boston

PSC newsletter spring 2014 issue now available

Raghunathan appointed director of Survey Research Center

Next Brown Bag


PSC Brown Bags will return in the fall

Batch mode reinforcement learning based on the synthesis of artificial trajectories

Publication Abstract

Fonteneau, R., Susan A. Murphy, L. Wehenkel, and D. Ernst. 2013. "Batch mode reinforcement learning based on the synthesis of artificial trajectories." Annals of Operations Research, 208(1): 383-416.

In this paper, we consider the batch mode reinforcement learning setting, where the central problem is to learn from a sample of trajectories a policy that satisfies or optimizes a performance criterion. We focus on the continuous state space case for which usual resolution schemes rely on function approximators either to represent the underlying control problem or to represent its value function. As an alternative to the use of function approximators, we rely on the synthesis of "artificial trajectories" from the given sample of trajectories, and show that this idea opens new avenues for designing and analyzing algorithms for batch mode reinforcement learning.

DOI:10.1007/s10479-012-1248-5 (Full Text)

PMCID: PMC3773886. (Pub Med Central)

Browse | Search : All Pubs | Next