The University of Southampton
University of Southampton Institutional Repository

Filtered Fictitious Play for Perturbed Observation Potential Games and Decentralised POMDPs

Filtered Fictitious Play for Perturbed Observation Potential Games and Decentralised POMDPs
Filtered Fictitious Play for Perturbed Observation Potential Games and Decentralised POMDPs
Potential games and decentralised partially observable MDPs (Dec–POMDPs) are two commonly used models of multi–agent interaction, for static optimisation and sequential decision-making settings, respectively. In this paper we introduce filtered fictitious play for solving repeated potential games in which each player’s observations of others’ actions are perturbed by random noise, and use this algorithm to construct an online learning method for solving Dec–POMDPs. Specifically, we prove that noise in observations prevents standard fictitious play from converging to Nash equilibrium in potential games, which also makes fictitious play impractical for solving Dec–POMDPs. To combat this, we derive filtered fictitious play, and provide conditions under which it converges to a Nash equilibrium in potential games with noisy observations. We then use filtered fictitious play to construct a solver for Dec–POMDPs, and demonstrate our new algorithm’s performance in a box pushing problem. Our results show that we consistently outperform the state-of-the-art Dec-POMDP solver by an average of 100% across the range of noise in the observation function.
77-85
Chapman, Archie
2eac6920-2aff-49ab-8d8e-a0ea3e39ba60
Williamson, Simon
28eaa4d9-5fcb-410e-91b6-0b42d4513a75
Jennings, Nick
ab3d94cc-247c-4545-9d1e-65873d6cdb30
Chapman, Archie
2eac6920-2aff-49ab-8d8e-a0ea3e39ba60
Williamson, Simon
28eaa4d9-5fcb-410e-91b6-0b42d4513a75
Jennings, Nick
ab3d94cc-247c-4545-9d1e-65873d6cdb30

Chapman, Archie, Williamson, Simon and Jennings, Nick (2011) Filtered Fictitious Play for Perturbed Observation Potential Games and Decentralised POMDPs. 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011), Barcelona, Spain. 14 - 17 Jul 2011. pp. 77-85 .

Record type: Conference or Workshop Item (Paper)

Abstract

Potential games and decentralised partially observable MDPs (Dec–POMDPs) are two commonly used models of multi–agent interaction, for static optimisation and sequential decision-making settings, respectively. In this paper we introduce filtered fictitious play for solving repeated potential games in which each player’s observations of others’ actions are perturbed by random noise, and use this algorithm to construct an online learning method for solving Dec–POMDPs. Specifically, we prove that noise in observations prevents standard fictitious play from converging to Nash equilibrium in potential games, which also makes fictitious play impractical for solving Dec–POMDPs. To combat this, we derive filtered fictitious play, and provide conditions under which it converges to a Nash equilibrium in potential games with noisy observations. We then use filtered fictitious play to construct a solver for Dec–POMDPs, and demonstrate our new algorithm’s performance in a box pushing problem. Our results show that we consistently outperform the state-of-the-art Dec-POMDP solver by an average of 100% across the range of noise in the observation function.

Text
UAI_2011_cameraReady.pdf - Version of Record
Download (124kB)

More information

Published date: July 2011
Additional Information: Event Dates: July 14-17, 2011
Venue - Dates: 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011), Barcelona, Spain, 2011-07-14 - 2011-07-17
Organisations: Agents, Interactions & Complexity

Identifiers

Local EPrints ID: 272481
URI: http://eprints.soton.ac.uk/id/eprint/272481
PURE UUID: ff2bd87e-2ee1-424d-a1d0-3c20d82cd45c

Catalogue record

Date deposited: 16 Jun 2011 21:50
Last modified: 14 Mar 2024 10:02

Export record

Contributors

Author: Archie Chapman
Author: Simon Williamson
Author: Nick Jennings

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×