Work

Entropy-Regularized Partially Observed Markov Decision Processes

Year: 2023

Type: article

Abstract: We investigate partially observed Markov decision processes (POMDPs) with cost functions regularized by entropy terms describing state, observation, and control uncertainty. Standard POMDP techniques are shown to offer bounded-error solutions to these entropy-regularized POMDPs, with exact solutions possible when the regularization involves the joint entropy of the state, observation, and control trajectories. Our joint-entropy result is particularly surprising since it constitutes a novel, tractable formulation of active state estimation.

Source: IEEE Transactions on Automatic Control

DOI: 10.1109/tac.2023.3264177

Authors: Timothy L. Molloy, Girish N. Nair

Institutions: Australian National University, The University of Melbourne

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Australian Government, Multidisciplinary University Research Initiative, Office of Naval Research