loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Joshua Riley 1 ; Radu Calinescu 1 ; Colin Paterson 1 ; Daniel Kudenko 2 and Alec Banks 3

Affiliations: 1 Department of Computer Science, University of York, York, U.K. ; 2 L3S Research Centre, Leibniz University, Hanover, Germany ; 3 Defence Science and Technology Laboratory, U.K.

Keyword(s): Reinforcement Learning, Multi-Agent System, Quantitative Verification, Assurance, Multi-Agent Reinforcement Learning.

Abstract: In multi-agent reinforcement learning, several agents converge together towards optimal policies that solve complex decision-making problems. This convergence process is inherently stochastic, meaning that its use in safety-critical domains can be problematic. To address this issue, we introduce a new approach that combines multi-agent reinforcement learning with a formal verification technique termed quantitative verification. Our assured multi-agent reinforcement learning approach constrains agent behaviours in ways that ensure the satisfaction of requirements associated with the safety, reliability, and other non-functional aspects of the decision-making problem being solved. The approach comprises three stages. First, it models the problem as an abstract Markov decision process, allowing quantitative verification to be applied. Next, this abstract model is used to synthesise a policy which satisfies safety, reliability, and performance constraints. Finally, the synthesised policy is used to constrain agent behaviour within the low-level problem with a greatly lowered risk of constraint violations. We demonstrate our approach using a safety-critical multi-agent patrolling problem. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 44.199.225.221

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Riley, J.; Calinescu, R.; Paterson, C.; Kudenko, D. and Banks, A. (2021). Reinforcement Learning with Quantitative Verification for Assured Multi-Agent Policies. In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-484-8; ISSN 2184-433X, SciTePress, pages 237-245. DOI: 10.5220/0010258102370245

@conference{icaart21,
author={Joshua Riley. and Radu Calinescu. and Colin Paterson. and Daniel Kudenko. and Alec Banks.},
title={Reinforcement Learning with Quantitative Verification for Assured Multi-Agent Policies},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2021},
pages={237-245},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010258102370245},
isbn={978-989-758-484-8},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Reinforcement Learning with Quantitative Verification for Assured Multi-Agent Policies
SN - 978-989-758-484-8
IS - 2184-433X
AU - Riley, J.
AU - Calinescu, R.
AU - Paterson, C.
AU - Kudenko, D.
AU - Banks, A.
PY - 2021
SP - 237
EP - 245
DO - 10.5220/0010258102370245
PB - SciTePress