UCL Discovery Stage
UCL home » Library Services » Electronic resources » UCL Discovery Stage

From MDP to POMDP and Back: Safety and Compositionality

Bujorianu, Manuela L; Caulfield, Tristan; Pym, David; Wisniewski, Rafael; (2023) From MDP to POMDP and Back: Safety and Compositionality. In: 2023 European Control Conference (ECC). (pp. pp. 1-6). IEEE: Bucharest, Romania. Green open access

[thumbnail of Bujorianu_ECC23_final (1).pdf]
Preview
Text
Bujorianu_ECC23_final (1).pdf - Accepted Version

Download (248kB) | Preview

Abstract

We propose a compositional framework for the stochastic safety of distributed Markov Decision Processes (MDPs) and Partially Observable Markov Decision Processes (POMDPs). We use MDP and POMDPs and their distributed versions as an appropriate modelling paradigm for computational ecosystems, understood in the context of distributed systems. We extend our work on stochastic safety from MDPs to POMDPs, and then to networked MDP/POMDPs. We propose a unifying mathematical framework for stochastic safety for MDPs, their partially observable version and their composition.

Type: Proceedings paper
Title: From MDP to POMDP and Back: Safety and Compositionality
Event: 2023 European Control Conference (ECC)
Location: Bucharest, ROMANIA
Dates: 13 Jun 2023 - 16 Jun 2023
ISBN-13: 978-3-907144-08-4
Open access status: An open access version is available from UCL Discovery
DOI: 10.23919/ECC57647.2023.10178169
Publisher version: http://dx.doi.org/10.23919/ecc57647.2023.10178169
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
Keywords: Markov decision process, stochastic safety, evolution equation, probabilistic potential theory, distributed systems, parallel composition, modular safety
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery-pp.ucl.ac.uk/id/eprint/10188535
Downloads since deposit
738Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item