Search

MiS Preprint Repository

Delve into the future of research at MiS with our preprint repository. Our scientists are making groundbreaking discoveries and sharing their latest findings before they are published. Explore repository to stay up-to-date on the newest developments and breakthroughs.

MiS Preprint
9/2021

Task-agnostic constraining in average reward POMDPs

Guido Montúfar, Johannes Rauh and Nihat Ay

Abstract

We study the shape of the average reward as a function over the memoryless stochastic policies in infinite-horizon partially observed Markov decision processes. We show that for any given instantaneous reward function on state-action pairs, there is an optimal policy that satisfies a series of constraints expressed solely in terms of the observation model. Our analysis extends and improves previous descriptions for discounted rewards or which covered only special cases.

Received:
Mar 9, 2021
Published:
Mar 9, 2021
Keywords:
partial observability, Markov decision process, stochastic policy, memoryless policy, optimal planning

Related publications

inBook
2019 Repository Open Access
Guido Montúfar, Johannes Rauh and Nihat Ay

Task-agnostic constraining in average reward POMDPs

In: Task-agnostic reinforcement learning : workshop at ICLR, 06 May 2019, New Orleans
[S. L.] : ICLR, 2019.