Skip to Main content Skip to Navigation
Journal articles

Policy Gradient in Continuous Time

Rémi Munos 1, 2
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : Policy search is a method for approximately solving an optimal control problem by performing a parametric optimization search in a given class of parameterized policies. In order to process a local optimization technique, such as a gradient method, we wish to evaluate the sensitivity of the performance measure with respect to the policy parameters, the so-called policy gradient. This paper is concerned with the estimation of the policy gradient for continuous-time, deterministic state dynamics, in a reinforcement learning framework, that is, when the decision maker does not have a model of the state dynamics. We show that usual likelihood ratio methods used in discrete-time, fail to proceed the gradient because they are subject to variance explosion when the discretization time-step decreases to 0. We describe an alternative approach based on the approximation of the pathwise derivative, which leads to a policy gradient estimate that converges almost surely to the true gradient when the time-step tends to 0. The underlying idea starts with the derivation of an explicit representation of the policy gradient using pathwise derivation. This derivation makes use of the knowledge of the state dynamics. Then, in order to estimate the gradient from the observable data only, we use a stochastic policy to discretize the continuous deterministic system into a stochastic discrete process, which enables to replace the unknown coefficients by quantities that solely depend on known data. We prove the almost sure convergence of this estimate to the true policy gradient when the discretization time-step goes to zero. The method is illustrated on two target problems, in discrete and continuous control spaces.
Document type :
Journal articles
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download
Contributor : Rémi Munos Connect in order to contact the contributor
Submitted on : Thursday, November 30, 2006 - 11:33:46 AM
Last modification on : Thursday, January 20, 2022 - 4:17:05 PM
Long-term archiving on: : Tuesday, April 6, 2010 - 11:41:10 PM


Publisher files allowed on an open archive


  • HAL Id : inria-00117152, version 1



Rémi Munos. Policy Gradient in Continuous Time. Journal of Machine Learning Research, Microtome Publishing, 2006, 7, pp.771-791. ⟨inria-00117152⟩



Record views


Files downloads