Reinforcement Learning for Continuous Stochastic Control Problems
Conference Paper, Proceedings of (NeurIPS) Neural Information Processing Systems, pp. 1029 - 1035, December, 1997
Abstract
This paper is concerned with the problem of Reinforcement Learning (RL) for continuous state space and time stochastic control problems. We state the Hamilton-Jacobi-Bellman equation satisfied by the value function and use a Finite-Difference method for designing a convergent approximation scheme. Then we propose a RL algorithm based on this scheme and prove its convergence to the optimal solution.
BibTeX
@conference{Munos-1997-16479,author = {Remi Munos and Paul Bourgine},
title = {Reinforcement Learning for Continuous Stochastic Control Problems},
booktitle = {Proceedings of (NeurIPS) Neural Information Processing Systems},
year = {1997},
month = {December},
pages = {1029 - 1035},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.