mlsanityData to 7 Oct 2026

Entropy-Regularized Partially Observed Markov Decision Processes

arXiv 2112.12255 ↗First posted 22 Dec 2021eess.SY cs.AI cs.ITcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 10 of its 35 references that are in the map. First posted on arXiv 22 Dec 2021.

Builds on

10 of 35 references.

References · 10

  1. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  2. 2018Entropy Maximization for Markov Decision Processes Under Temporal Logic Constraintscited by 11
  3. 2015Rationally inattentive control of Markov processescited by 6
  4. 2016Rate-cost tradeoffs in controlcited by 6
  5. 2013Active Classification for POMDPs: a Kalman-like State Estimatorcited by 4
  6. 2015LQG Control with Minimum Directed Information: Semidefinite Programming Approachcited by 4
  7. 2017Transfer-Entropy-Regularized Markov Decision Processescited by 4
  8. 2021Smoother Entropy for Active State Trajectory Estimation and Obfuscation in POMDPscited by 3
  9. 2013Directed Information on Abstract Spaces: Properties and Variational Equalitiescited by 2
  10. 2021Active Trajectory Estimation for Partially Observed Markov Decision Processes via Conditional Entropycited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Entropy-regularized Point-based Value Iterationcited by 1