In this work, we present an approximate value iteration algorithm for a production and storage model with multiple production stages and a single final product, subject to random demand. We use linear function approximation schemes in subsets of the state space and represent a few key states in a look-up table form. We obtain some promising results and perform sensitivity analysis with respect to the parameters of the algorithm for the benchmark problem studied. © 2005 IEEE. 665670Davis, M.H.A., (1993) Markov Models and Optimization, , London: Chapman and HallSethi, S.P., Yan, H., Zhang, H., Zhang, Q., Optimal and hierarchical controls in dynamic stochastic manufacturing sytems: A review (2002) Manuf. & Serv, Ops. Management, 4 (2), pp. 133-170Yin, K.K., Liu, H., Yin, G.G., Stochastic models and numerical solutions for production planning with applications to the paper industry (2003) Computers & Chemical Engineering, 27, pp. 1693-1706Si, J., Barto, A., Powell, W., Wunsch, D., (2004) Handbook of Learning and Approximate Dynamic Programming, , Piscataway-NJ: John Wiley & Sons-IEEE PressBertsekas, D.P., Tsitsiklis, J.N., (1996) Neuro-dynamic Programming, , Belmont: Athena ScientificSutton, R.S., Barto, A.G., (1998) Reinforcement Learning: An Introduction, , Cambridge: MIT PressArruda, E.F., Almudevar, A., Do Val, J.B.R., Stability and optimally of a discrete production and storage model with uncertain demand (2004) Proceedings of the 43th IEEE Conference on Decision and Control, pp. 3354-3360. , NassauGordon, G., Stable function approximation in dynamic programming (1995) Proceedings of IMCL'95B. III, L.C., Residual algorithms: Reinforcement learning with function approximation (1995) International Conference on Machine Learning, pp. 30-37. , [Online], Available: citeseer.csail.mit.edu/baird95residual.htmlReynolds, S.I., The stability of general discounted reinforcement learning with linear function approximation (2002) Proceedings of the UK Workshop on Computational Intelligence, pp. 139-146. , Birmingham-UKWeiring, M.A., Convergence and divergence in standard and averaging reinforcement learning (2004) Proc. 15th European Conf. on Machine Learning, pp. 477-488. , Pisa-ItalyGolub, G.H., Van Loan, C.F., (1996) Matrix Computations, 3rd Ed., , Baltimore: Johns Hopkins University Press