On the Convergence of Modified Policy Iteration in Risk Sensitive Exponential Cost Markov Decision Processes

arXiv:2302.03811v2 Announce Type: replace
Abstract: Modified policy iteration (MPI) is a dynamic programming algorithm that combines elements of policy iteration and value iteration. The convergence of MPI has been well studied in the context of discounted and average-cost MDPs. In this work, we consider the exponential cost risk-sensitive MDP formulation, which is known to provide some robustness to model parameters. Although policy iteration and value iteration have been well studied in the context of risk sensitive MDPs, MPI is unexplored. …

abstract algorithm arxiv context convergence cost cs.ai cs.lg cs.sy decision dynamic eess.sy iteration markov mpi policy processes programming risk type value work