English

Entropy-Regularized Partially Observed Markov Decision Processes

Systems and Control 2023-05-10 v2 Artificial Intelligence Information Theory Systems and Control math.IT

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.

Keywords

Cite

@article{arxiv.2112.12255,
  title  = {Entropy-Regularized Partially Observed Markov Decision Processes},
  author = {Timothy L. Molloy and Girish N. Nair},
  journal= {arXiv preprint arXiv:2112.12255},
  year   = {2023}
}

Comments

20 pages, 2 figures, submitted

R2 v1 2026-06-24T08:28:49.151Z