Show simple item record

dc.contributor.authorMannion, Patrick
dc.contributor.authorRockefeller, Golden
dc.contributor.authorTurner, Kagan
dc.description.abstractIn this paper,we leverage curriculum learning(CL) to improve the performance of multiagent systems(MAS) that are trained with the cooperative coevolution of artificial neural networks. We design curricula to progressively change two dimensions:scale(i.e.domain size) and coupling (i.e.the number of agents required to complete a subtask).We demonstrate that CL can successfully mitigate the challenge of learning on a sparse reward signal resulting from a high degree of coupling in complex MAS. We also show that, in most cases, the combination of difference reward shaping with CL can improve performance by up to 56%. We evaluate our CL methods on the tightly coupled multi-rover domain.CL increased converged system performance on all tasks presented.Furthermore, agents were only able to learn when trained with CL for most tasksen_US
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Ireland*
dc.subjectMultiagent Coordinationen_US
dc.subjectCurriculum Learningen_US
dc.subjectDifference Rewardsen_US
dc.titleCurriculum Learning for Tightly Coupled Multiagent Systemsen_US
dc.subject.departmentDepartment of Computer Science & Applied Physicsen_US

Files in this item


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