Show simple item record

dc.contributor.authorGupta, Gaurav
dc.date.accessioned2020-05-14 15:38:46 (GMT)
dc.date.available2020-05-14 15:38:46 (GMT)
dc.date.issued2020-05-14
dc.date.submitted2020-05-05
dc.identifier.urihttp://hdl.handle.net/10012/15853
dc.description.abstractWe propose a mechanism for achieving cooperation and communication in Multi-Agent Reinforcement Learning (MARL) settings by intrinsically rewarding agents for obeying the commands of other agents. At every timestep, agents exchange commands through a cheap-talk channel. During the following timestep, agents are rewarded both for taking actions that conform to commands received as well as for giving successful commands. We refer to this approach as obedience-based learning. We demonstrate the potential for obedience-based approaches to enhance coordination and communication in challenging sequential social dilemmas, where traditional MARL approaches often collapse without centralized training or specialized architectures. We also demonstrate the flexibility of this approach with regards to population heterogeneity and vocabulary size. Obedience-based learning stands out as an intuitive form of cooperation with minimal complexity and overhead that can be applied to heterogeneous populations. In contrast, previous works with sequential social dilemmas are often restricted to homogeneous populations and require complete knowledge of every player's reward structure. Obedience-based learning is a promising direction for exploration in the field of cooperative MARL.en
dc.language.isoenen
dc.publisherUniversity of Waterlooen
dc.relation.urihttps://github.com/gauravg11/sequential_social_dilemma_gamesen
dc.subjectReinforcement Learningen
dc.subjectCooperationen
dc.subjectMulti-Agent Reinforcement Learningen
dc.subjectIntrinsic Rewarden
dc.subjectCheap-Talk Communicationen
dc.titleObedience-based Multi-Agent Cooperation for Sequential Social Dilemmasen
dc.typeMaster Thesisen
dc.pendingfalse
uws-etd.degree.departmentDavid R. Cheriton School of Computer Scienceen
uws-etd.degree.disciplineComputer Scienceen
uws-etd.degree.grantorUniversity of Waterlooen
uws-etd.degreeMaster of Mathematicsen
uws.contributor.advisorHoey, Jesse
uws.contributor.affiliation1Faculty of Mathematicsen
uws.published.cityWaterlooen
uws.published.countryCanadaen
uws.published.provinceOntarioen
uws.typeOfResourceTexten
uws.peerReviewStatusUnrevieweden
uws.scholarLevelGraduateen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record


UWSpace

University of Waterloo Library
200 University Avenue West
Waterloo, Ontario, Canada N2L 3G1
519 888 4883

All items in UWSpace are protected by copyright, with all rights reserved.

DSpace software

Service outages