Simultaneously Evolving Deep Reinforcement Learning Models using Multifactorial optimization

Simple item page
dc.contributor.authorMartinez, Aritz D.
dc.contributor.authorOsaba, Eneko
dc.contributor.authorSery, Javier Del
dc.contributor.authorHerrera, Francisco
dc.contributor.institutionIA
dc.contributor.institutionQuantum
dc.date.accessioned2024-07-24T11:55:13Z
dc.date.available2024-07-24T11:55:13Z
dc.date.issued2020-07
dc.descriptionPublisher Copyright: © 2020 IEEE.
dc.description.abstractIn recent years, Multifactorial optimization (MFO) has gained a notable momentum in the research community. MFO is known for its inherent capability to efficiently address multiple optimization tasks at the same time, while transferring information among such tasks to improve their convergence speed. On the other hand, the quantum leap made by Deep Q Learning (DQL) in the Machine Learning field has allowed facing Reinforcement Learning (RL) problems of unprecedented complexity. Unfortunately, complex DQL models usually find it difficult to converge to optimal policies due to the lack of exploration or sparse rewards. In order to overcome these drawbacks, pre-trained models are widely harnessed via Transfer Learning, extrapolating knowledge acquired in a source task to the target task. Besides, meta-heuristic optimization has been shown to reduce the lack of exploration of DQL models. This work proposes a MFO framework capable of simultaneously evolving several DQL models towards solving interrelated RL tasks. Specifically, our proposed framework blends together the benefits of meta-heuristic optimization, Transfer Learning and DQL to automate the process of knowledge transfer and policy learning of distributed RL agents. A thorough experimentation is presented and discussed so as to assess the performance of the framework, its comparison to the traditional methodology for Transfer Learning in terms of convergence, speed and policy quality, and the intertask relationships found and exploited over the search process.en
dc.description.sponsorshipAritz D. Martinez, Eneko Osaba and Javier Del Ser would like to thank the Basque Government for its funding support through the EMAITEK and ELKARTEK programs. Javier Del Ser receives funding support from the Consolidated Research Group MATHMODE (IT1294-19) granted by the Department of Education of the Basque Government.
dc.description.statusPeer reviewed
dc.identifier.citationMartinez , A D , Osaba , E , Sery , J D & Herrera , F 2020 , Simultaneously Evolving Deep Reinforcement Learning Models using Multifactorial optimization . in 2020 IEEE Congress on Evolutionary Computation, CEC 2020 - Conference Proceedings . , 9185667 , 2020 IEEE Congress on Evolutionary Computation, CEC 2020 - Conference Proceedings , Institute of Electrical and Electronics Engineers Inc. , 2020 IEEE Congress on Evolutionary Computation, CEC 2020 , Virtual, Glasgow , United Kingdom , 19/07/20 . https://doi.org/10.1109/CEC48606.2020.9185667
dc.identifier.citationconference
dc.identifier.doi10.1109/CEC48606.2020.9185667
dc.identifier.isbn9781728169293
dc.identifier.urihttps://hdl.handle.net/11556/2489
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85089741571&partnerID=8YFLogxK
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartof2020 IEEE Congress on Evolutionary Computation, CEC 2020 - Conference Proceedings
dc.relation.ispartofseries2020 IEEE Congress on Evolutionary Computation, CEC 2020 - Conference Proceedings
dc.relation.projectIDDepartment of Education of the Basque Government
dc.relation.projectIDEusko Jaurlaritza, IT1294-19
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subject.keywordsDeep Reinforcement Learning
dc.subject.keywordsEvolutionary Algorithm
dc.subject.keywordsMultifactorial optimization
dc.subject.keywordsTransfer Learning
dc.subject.keywordsControl and Optimization
dc.subject.keywordsDecision Sciences (miscellaneous)
dc.subject.keywordsArtificial Intelligence
dc.subject.keywordsComputer Vision and Pattern Recognition
dc.subject.keywordsHardware and Architecture
dc.titleSimultaneously Evolving Deep Reinforcement Learning Models using Multifactorial optimizationen
dc.typeconference output
Files