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

PSC In The News

RSS Feed icon

Groves keynote speaker at MIDAS symposium, Nov 15-16: "Big Data: Advancing Science, Changing the World"

Shaefer says drop child tax credit in favor of universal, direct investment in American children

Buchmueller breaks down partisan views on Obamacare

More News


Gonzalez, Alter, and Dinov win NSF "Big Data Spokes" award for neuroscience network

Post-doc Melanie Wasserman wins dissertation award from Upjohn Institute

ISR kicks off DE&I initiative with lunchtime presentation: Oct 13, noon, 1430 ISR Thompson

U-M ranked #4 in USN&WR's top public universities

More Highlights

Next Brown Bag

Mon, Oct 24 at noon:
Academic innovation & the global public research university, James Hilton

Model-Free Monte Carlo-like Policy Evaluation

Publication Abstract

Fonteneau, R., Susan A. Murphy, L. Wehenkel, and D. Ernst. 2010. "Model-Free Monte Carlo-like Policy Evaluation." In Volume 9: AISTATS 2010 Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. San Francisco: Morgan Kaufmann Publishers.

We propose an algorithm for estimating the finite-horizon expected return of a closed loop control policy from an a priori given (off-policy) sample of one-step transitions. It averages cumulated rewards along a set of "broken trajectories" made of one-step transitions selected from the sample on the basis of the control policy. Under some Lipschitz continuity assumptions on the system dynamics, reward function and control policy, we provide bounds on the bias and variance of the estimator that depend only on the Lipschitz constants, on the number of broken trajectories used in the estimator, and on the sparsity of the sample of one-step transitions.

Browse | Search : All Pubs | Next