December
1997
Reinforcement Learning for Continuous Stochastic Control Problems
Authors:
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.
copied = false, 2000);
">
@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},
}
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},
}