An RBF based Neuro-dynamic Approach for the Control of Stochastic Dynamic Systems
| Authors: | Sarimveis Haralambos, National Technical University of Athens, Greece
Patrinos Panagiotis K., National Technical University of Athens, Greece |
|---|
| Topic: | 3.2 Cognition and Control ( AI, Fuzzy, Neuro, Evolut.Comp.) |
|---|
| Session: | Neural Control |
|---|
| Keywords: | Markov decision processes, Radial base function networks, uncertain dynamic systems, optimal control |
|---|
Abstract
This paper presents a neuro-dynamic programming methodology for the control of markov decision processes. The proposed method can be considered as a variant of the optimistic policy iteration, where radial basis function (RBF) networks are employed as a compact representation of the cost-to-go function and the λ-LSPE is used for policy evaluation. We also emphasize the reformulation of the Bellman equation around the post-decision state in order to circumvent the calculation of the expectation. The proposed algorithm is applied to a retailer-inventory management problem.
