Physical Sciences and Mathematics Commons^™

Solving Uncertain Mdps With Objectives That Are Separable Over Instantiations Of Model Uncertainty, Yossiri Adulyasak, Pradeep Varakantham, Asrar Ahmed, Patrick Jaillet

Research Collection School Of Computing and Information Systems

Markov Decision Problems, MDPs offer an effective mechanism for planning under uncertainty. However, due to unavoidable uncertainty over models, it is difficult to obtain an exact specification of an MDP. We are interested in solving MDPs, where transition and reward functions are not exactly specified. Existing research has primarily focussed on computing infinite horizon stationary policies when optimizing robustness, regret and percentile based objectives. We focus specifically on finite horizon problems with a special emphasis on objectives that are separable over individual instantiations of model uncertainty (i.e., objectives that can be expressed as a sum over instantiations of model uncertainty): …