A LEARNING ALGORITHM FOR DISCRETE-TIME STOCHASTIC CONTROL
- 1 January 2000
- journal article
- research article
- Published by Cambridge University Press (CUP) in Probability in the Engineering and Informational Sciences
- Vol. 14 (2) , 243-258
- https://doi.org/10.1017/s0269964800142081
Abstract
A simulation-based algorithm for learning good policies for a discrete-time stochastic control process with unknown transition law is analyzed when the state and action spaces are compact subsets of Euclidean spaces. This extends the Q-learning scheme of discrete state/action problems along the lines of Baker [4]. Almost sure convergence is proved under suitable conditions.Keywords
This publication has 0 references indexed in Scilit: