Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Learning Transferable Cooperative Behavior in Multi-Agent Team

Agarwal, Akshat and Kumar, Sumit and Sycara, Katia and Lewis, Michael (2020) Learning Transferable Cooperative Behavior in Multi-Agent Team. In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS'2020), May 9-13, Aukland, NZ.

[img]
Preview
PDF
Download (956kB) | Preview

Abstract

While multi-agent interactions can be naturally modeled as a graph, the environment has traditionally been considered as a black box. To better utilize the inherent structure of our environment, we propose to create a shared agent-entity graph, where agents and environmental entities form vertices, and edges exist between the vertices which can communicate with each other, allowing agents to selectively attend to different parts of the environment, while also introducing invariance to the number of agents or entities present in the system as well as permutation invariance. We present stateof- the-art results on coverage, formation and line control tasks for multi-agent teams in a fully decentralized execution framework.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: Conference or Workshop Item (Paper)
Status: Published
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Agarwal, Akshat
Kumar, Sumit
Sycara, Katiakatia@cs.cmu.edu
Lewis, Michaelcmlewis@pitt.educmlewis0000-0002-1013-9482
Date: 2020
Date Type: Publication
Journal or Publication Title: International Conference on Autonomous Agents and Multiagent Systems (AAMAS'2020)
Publisher: IFMAS
Place of Publication: Aukland, NZ
Event Title: International Conference on Autonomous Agents and Multiagent Systems (AAMAS'2020)
Event Dates: May 9-13
Event Type: Conference
Schools and Programs: School of Computing and Information > Information Science
Refereed: Yes
Date Deposited: 15 Jun 2020 14:18
Last Modified: 15 Jun 2020 14:18
URI: http://d-scholarship.pitt.edu/id/eprint/39099

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item