Multi-agent intention progression with reward machines

Michael Dann, Yuan Yao, Natasha Alechina, Brian Logan, John Thangarajah

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

Abstract

Recent work in multi-agent intention scheduling has shown that enabling agents to predict the actions of other agents when choosing their own actions may be beneficial. However existing approaches to ‘intention-aware’ scheduling assume
that the programs of other agents are known, or are “similar” to that of the agent making the prediction. While this assumption is reasonable in some circumstances, it is less plausible when the agents are not co-designed. In this paper, we present a new approach to multi-agent intention scheduling in which
agents predict the actions of other agents based on a high-level specification of the tasks performed by an agent in the form of a reward machine (RM)
rather than on its (assumed) program. We show how a reward machine can be used to generate tree and rollout policies for an MCTS-based scheduler.
We evaluate our approach in a range of multi-agent environments, and show that RM-based scheduling out-performs previous intention-aware scheduling approaches in settings where agents are not co-designed.
Original languageEnglish
Title of host publicationProceedings of the Thirty-First International Joint Conference on Artificial Intelligence Main Track
Editors Luc De Raedt
PublisherInternational Joint Conferences on Artificial Intelligence
Pages215-222
ISBN (Electronic)9781956792003
DOIs
Publication statusPublished - Jul 2022
EventThe 31st International Joint Conference on Artificial Intelligence - Vienna, Austria
Duration: 23 Jul 202229 Jul 2022
Conference number: 31

Conference

ConferenceThe 31st International Joint Conference on Artificial Intelligence
Abbreviated titleIJCAI-ECAI 2022
Country/TerritoryAustria
CityVienna
Period23/07/2229/07/22

Keywords

  • Agent-based and Multi-agent Systems
  • Agent Theories and Models
  • Engineering Methods
  • Languages and Tools
  • Platforms

Fingerprint

Dive into the research topics of 'Multi-agent intention progression with reward machines'. Together they form a unique fingerprint.

Cite this