Abstract
This paper describes sufficient conditions for the existence of optimal policies for partially observable Markov decision processes (POMDPs) with Borel state, observation, and action sets, when the goal is to minimize the expected total costs over finite or infinite horizons. For infinite-horizon problems, one-step costs are either discounted or assumed to be nonnegative. Action sets may be noncompact and one-step cost functions may be unbounded. The introduced conditions are also sufficient for the validity of optimality equations, semicontinuity of value functions, and convergence of value iterations to optimal values. Since POMDPs can be reduced to completely observable Markov decision processes (COMDPs), whose states are posterior state distributions, this paper focuses on the validity of the above-mentioned optimality properties for COMDPs. The central question is whether the transition probabilities for the COMDP are weakly continuous. We introduce sufficient conditions for this and show that the transition probabilities for a COMDP are weakly continuous, if transition probabilities of the underlying Markov decision process are weakly continuous and observation probabilities for the POMDP are continuous in total variation. Moreover, the continuity in total variation of the observation probabilities cannot be weakened to setwise continuity. The results are illustrated with counterexamples and examples.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.