Show simple item record

dc.contributor.authorMannion, Patrick
dc.contributor.authorDevlin, Sam
dc.contributor.authorDuggan, Jim
dc.contributor.authorHowley, Enda
dc.date.accessioned2018-09-20T16:15:54Z
dc.date.available2018-09-20T16:15:54Z
dc.date.issued2017-01-01
dc.identifier.citationMannion, Patrick; Devlin, Sam; Duggan, Jim; Howley, Enda (2017). Multi-agent credit assignment in stochastic resource management games. The Knowledge Engineering Review 32 ,
dc.identifier.issn0269-8889,1469-8005
dc.identifier.urihttp://hdl.handle.net/10379/12633
dc.description.abstractMulti-agent systems (MASs) are a form of distributed intelligence, where multiple autonomous agents act in a common environment. Numerous complex, real world systems have been successfully optimized using multi-agent reinforcement learning (MARL) in conjunction with the MAS framework. In MARL agents learn by maximizing a scalar reward signal from the environment, and thus the design of the reward function directly affects the policies learned. In this work, we address the issue of appropriate multi-agent credit assignment in stochastic resource management games. We propose two new stochastic games to serve as testbeds for MARL research into resource management problems: the tragic commons domain and the shepherd problem domain. Our empirical work evaluates the performance of two commonly used reward shaping techniques: potential-based reward shaping and difference rewards. Experimental results demonstrate that systems using appropriate reward shaping techniques for multi-agent credit assignment can achieve near-optimal performance in stochastic resource management games, outperforming systems learning using unshaped local or global evaluations. We also present the first empirical investigations into the effect of expressing the same heuristic knowledge in state- or action-based formats, therefore developing insights into the design of multi-agent potential functions that will inform future work.
dc.publisherCambridge University Press (CUP)
dc.relation.ispartofThe Knowledge Engineering Review
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Ireland
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/3.0/ie/
dc.subjectcollective intelligence
dc.subjectsystems
dc.titleMulti-agent credit assignment in stochastic resource management games
dc.typeArticle
dc.identifier.doi10.1017/s026988891700011x
dc.local.publishedsourcehttps://www.cambridge.org/core/services/aop-cambridge-core/content/view/CC977EDFE4D719868BC5E830A317EA8F/S026988891700011Xa.pdf/div-class-title-multi-agent-credit-assignment-in-stochastic-resource-management-games-div.pdf
nui.item.downloads0


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivs 3.0 Ireland
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivs 3.0 Ireland