Dynamical perceptual-motor primitives for better deep reinforcement learning agents

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

Abstract

Recent innovations in Deep Reinforcement Learning (DRL) and Artificial Intelligence (AI) techniques have allowed for the development of artificial agents that can outperform human counterparts. But when it comes to multiagent task contexts, the behavioral patterning of AI agents is just as important as their performance. Indeed, successful multi-agent interaction requires that co-actors behave reciprocally, anticipate each other’s behaviors, and readily perceive each other’s behavioral intentions. Thus, developing AI agents that can produce behaviors compatible with human co-actors is of vital importance. Of particular relevance here, research exploring the dynamics of human behavior has demonstrated that many human behaviors and actions can be modeled using a small set of dynamical perceptual-motor primitives (DPMPs) and, moreover, that these primitives can also capture the complex behavior of humans in multiagent scenarios. Motived by this understanding, the current paper proposes methodologies which use DPMPs to augment the training and action dynamics of DRL agents to ensure that the agents inherit the essential pattering of human behavior while still allowing for optimal exploration of the task solution space during training. The feasibility of these methodologies is demonstrated by creating hybrid DPMP-DRL agents for a multiagent herding task. Overall, this approach leads to faster training of DRL agents while also exhibiting behavior characteristics of expert human actors.
Original languageEnglish
Title of host publicationAdvances in practical applications of agents, multi-agent systems, and social good
Subtitle of host publicationthe PAAMS collection : 19th international conference, PAAMS 2021, Salamanca, Spain, October 6-8, 2021 : proceedings
EditorsFrank Dignum, Juan Manuel Corchado, Fernando De La Prieta
Place of PublicationCham, Switzerland
PublisherSpringer, Springer Nature
Pages176–187
Number of pages12
ISBN (Electronic)9783030857394
ISBN (Print)9783030857387
DOIs
Publication statusPublished - 2021
EventInternational Conference, Practical Applications of Agents, Multi-Agent Systems (19th : 2021) - Salamanca, Spain
Duration: 6 Oct 20218 Oct 2021
https://www.paams.net/

Publication series

NameLecture notes in artificial intelligence
Number12946
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceInternational Conference, Practical Applications of Agents, Multi-Agent Systems (19th : 2021)
Abbreviated titlePAAMS 2021
CountrySpain
CitySalamanca
Period6/10/218/10/21
Internet address

Bibliographical note

Advances in Practical Applications of Agents, Multi-Agent Systems, and Social Good, The PAAMS Collection

Keywords

  • Deep Reinforcement Learning (DRL)
  • Dynamical Motor Primitives (DMPs)
  • multiagent coordination

Fingerprint

Dive into the research topics of 'Dynamical perceptual-motor primitives for better deep reinforcement learning agents'. Together they form a unique fingerprint.

Cite this