On the relative value iteration with a risk-sensitive criterion

2019/12/18 by Ari Arapostathis, Arapostathis, Ari, Vivek S. Borkar +1
Mathematics · #49K40 (60J25 #60J60) #90C40 #93E20 #FOS: Mathematics #Optimization and Control (math.OC) #Probability (math.PR) #math.OC #math.PR #msc:49K40 #msc:90C40 #msc:93E20

paper · pdf · doi:10.48550/arxiv.1912.08758

14 pages

arxiv created 2019/12/18 · arxiv updated 2019/12/19

Abstract

A multiplicative relative value iteration algorithm for solving the dynamic programming equation for the risk-sensitive control problem is studied for discrete time controlled Markov chains with a compact Polish state space, and controlled diffusions in on the whole Euclidean space. The main result is a proof of convergence to the desired limit in each case.

Related

• Risk-sensitive control of continuous time Markov chains
• Discrete time risk sensitive control problem
• Average cost optimal control under weak ergodicity hypotheses: Relative\n value iterations
• A policy iteration algorithm for non-Markovian control problems
• Discrete-Time Approximation of Risk-Averse Control Problems for Diffusion Processes