@inproceedings{eprints1035,
          author = {Panagiotis Patrinos and Haralambos Sarimveis},
       booktitle = {16th IFAC World Congress},
           title = {An RBF based neuro-dynamic approach for the control of stochastic dynamic systems},
            year = {2005},
             url = {http://eprints.imtlucca.it/1035/},
        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 ?-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.}
}