Learning for stochastic dynamic programming

Abstract. We present experimental results about learning function values (i.e. Bellman values) in stochastic dynamic programming (SDP). All results come from openDP (opendp.sourceforge.net), a freely available source code, and therefore can be reproduced. The goal is an independent comparison of learning methods in the framework of SDP. 1 What is stochastic dynamic programming (SDP) ? We here very roughly introduce stochastic dynamic programming. The interested reader is referred to [1] for more details. Consider a dynamical system that stochastically evolves in time depending upon your decisions. Assume that time is discrete and has finitely many time steps. Assume that the total cost of your decisions is the sum of instantaneous costs. Precisely: cost = c1 + c2 +

• Type: Conference
• Year: 2006
• Where: ESANN
• Authors: Sylvain Gelly, Jérémie Mary, Olivier Teytaud
• Keywords: Bellman's Optimality Principle, ESANN 2006, ESANN 2007, Stochastic Dynamic Programming, Time Steps