Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/156966
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLeung, Jonathanen_US
dc.contributor.authorShen, Zhiqien_US
dc.contributor.authorZeng, Zhiweien_US
dc.contributor.authorMiao, Chunyanen_US
dc.date.accessioned2022-05-12T00:48:28Z-
dc.date.available2022-05-12T00:48:28Z-
dc.date.issued2021-
dc.identifier.citationLeung, J., Shen, Z., Zeng, Z. & Miao, C. (2021). Goal modelling for deep reinforcement learning agents. Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2021), 12975, 271-286. https://dx.doi.org/10.1007/978-3-030-86486-6_17en_US
dc.identifier.isbn9783030864859-
dc.identifier.issn0302-9743-
dc.identifier.urihttps://hdl.handle.net/10356/156966-
dc.description.abstractGoals provide a high-level abstraction of an agent’s objectives and guide its behavior in complex environments. As agents become more intelligent, it is necessary to ensure that the agent’s goals are aligned with the goals of the agent designers to avoid unexpected or unwanted agent behavior. In this work, we propose using Goal Net, a goal-oriented agent modelling methodology, as a way for agent designers to incorporate their prior knowledge regarding the subgoals an agent needs to achieve in order to accomplish an overall goal. This knowledge is used to guide the agent’s learning process to train it to achieve goals in dynamic environments where its goal may change between episodes. We propose a model that integrates a Goal Net model and hierarchical reinforcement learning. A high-level goal selection policy selects goals according to a given Goal Net model and a low-level action selection policy selects actions based on the selected goal, both of which use deep neural networks to enable learning in complex, high-dimensional environments. The experiments demonstrate that our method is more sample efficient and can obtain higher average rewards than other related methods that incorporate prior human knowledge in similar ways.en_US
dc.description.sponsorshipNational Research Foundation (NRF)en_US
dc.language.isoenen_US
dc.relationNRF-NRFI05-2019-0002en_US
dc.rights© 2021 Springer Nature Switzerland AG. All rights reserved. This paper was published in Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2021) and is made available with permission of Springer Nature Switzerland AG.en_US
dc.subjectEngineering::Computer science and engineeringen_US
dc.titleGoal modelling for deep reinforcement learning agentsen_US
dc.typeConference Paperen
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.contributor.conferenceJoint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2021)en_US
dc.identifier.doi10.1007/978-3-030-86486-6_17-
dc.description.versionSubmitted/Accepted versionen_US
dc.identifier.scopus2-s2.0-85115448159-
dc.identifier.volume12975en_US
dc.identifier.spage271en_US
dc.identifier.epage286en_US
dc.subject.keywordsDeep Reinforcement Learningen_US
dc.subject.keywordsHierarchical Reinforcement Learningen_US
dc.citation.conferencelocationBilbao, Spainen_US
dc.description.acknowledgementThis research is supported, in part, by the National Research Foundation, Prime Minister’s Office, Singapore under its NRF Investigatorship Programme (NRF Award No. NRF-NRFI05-2019-0002).en_US
item.grantfulltextembargo_20220917-
item.fulltextWith Fulltext-
Appears in Collections:SCSE Conference Papers
Files in This Item:
File Description SizeFormat 
Goal Modelling for Deep Reinforcement Learning Agents.pdf
  Until 2022-09-17
2.15 MBAdobe PDFUnder embargo until Sep 17, 2022

Page view(s)

31
Updated on Jul 2, 2022

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.