Model-Free Monte Carlo-like Policy Evaluation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Documents Associated With Scientific Events Year :

Model-Free Monte Carlo-like Policy Evaluation

Abstract

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.
Fichier principal
Vignette du fichier
REN-Ernst.pdf (65.22 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00510325 , version 1 (18-08-2010)

Identifiers

  • HAL Id : inria-00510325 , version 1

Cite

Raphael Fonteneau, Susan Murphy, Louis Wehenkel, Damien Ernst. Model-Free Monte Carlo-like Policy Evaluation. Journées MAS et Journée en l'honneur de Jacques Neveu, Aug 2010, Talence, France. ⟨inria-00510325⟩

Collections

INSMI MAS2010
41 View
33 Download

Share

Gmail Facebook Twitter LinkedIn More