Distributionally Robust Partially Observable Markov Decision Process with Moment-Based Ambiguity

Robust partially observable Markov decision process

We seek to find the robust policy that maximizes the expected cumulative reward for the worst case when a partially observable Markov decision process (POMDP) has uncertain parameters whose values are only known to be in a given region. We prove that the robust value function, which represents the expected cumulative reward that can be obtained with the robust policy, is convex with respect to ...

The Infinite Partially Observable Markov Decision Process

The Partially Observable Markov Decision Process (POMDP) framework has proven useful in planning domains where agents must balance actions that provide knowledge and actions that provide reward. Unfortunately, most POMDPs are complex structures with a large number of parameters. In many real-world problems, both the structure and the parameters are difficult to specify from domain knowledge alo...

Text Understanding With Partially Observable Markov Decision Process

The process of understanding the meaning of a written passage inherently involves dynamic manipulation and composition of ideas. Starting from this observation this thesis proposes an artificial system for text understanding in which the semantic space containing the possible meanings of the analyzed text is selectively explored by a partially observable Markov decision process trained to effec...

Dynamic Decision Model using Partially Observable Markov Decision Process

Distributionally Robust Markov Decision Processes

We consider Markov decision processes where the values of the parameters are uncertain. This uncertainty is described by a sequence of nested sets (that is, each set contains the previous one), each of which corresponds to a probabilistic guarantee for a different confidence level so that a set of admissible probability distributions of the unknown parameters is specified. This formulation mode...