Neuro-evolution behavior transfer for collective behavior tasks

Simple item page
dc.contributor.advisorNitschke, Geoff Stuarten_ZA
dc.contributor.authorDidi, Sabre Zen_ZA
dc.date.accessioned2018-05-03T12:36:15Z
dc.date.available2018-05-03T12:36:15Z
dc.date.issued2018en_ZA
dc.description.abstractThe design of effective, robust and autonomous controllers for multi-agent and multi-robot systems is a long-standing problem in the fields of computational intelligence and robotics. Whilst nature-inspired problem-solving techniques such as reinforcement learning (RL) and evolutionary algorithms (EA) are often used to adapt controllers for solving such tasks, the complexity of such tasks increases with the addition of more agents (or robots) in difficult environments. This is due to specific issues related to task complexity, such as the curse of dimensionality and bootstrapping problems. Despite an increasing attempt over the last decade to incorporate behavior (knowledge) transfer in machine learning so that relevant behavior acquired in previous learning experiences can be used to boost task performance in complex tasks, using evolutionary algorithms to facilitate behavior transfer (especially multi-agent behavior transfer) has received little attention. It remains unclear how behavior transfer addresses issues such as the bootstrapping problem in complex multi-agent tasks (for example, RoboCup soccer). This thesis seeks to investigate and establish the essential features constituting effective and efficient evolutionary search to augment behavior transfer for boosting the quality of evolved behaviors across increasingly complex tasks. Experimental results indicate a hybrid of objective-based search and behavioral diversity maintenance in evolutionary controller design coupled with behavior transfer yields evolved behaviors of significantly high quality across increasingly complex multi-agent tasks. The evolutionary controller design method thus addresses the bootstrapping task for the given range of multi-agent tasks, whilst comparative controller design methods yield scant performance results.en_ZA
dc.identifier.apacitationDidi, S. Z. (2018). <i>Neuro-evolution behavior transfer for collective behavior tasks</i>. (Thesis). University of Cape Town ,Faculty of Science ,Department of Computer Science. Retrieved from http://hdl.handle.net/11427/27910en_ZA
dc.identifier.chicagocitationDidi, Sabre Z. <i>"Neuro-evolution behavior transfer for collective behavior tasks."</i> Thesis., University of Cape Town ,Faculty of Science ,Department of Computer Science, 2018. http://hdl.handle.net/11427/27910en_ZA
dc.identifier.citationDidi, S. 2018. Neuro-evolution behavior transfer for collective behavior tasks. University of Cape Town.en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Didi, Sabre Z AB - The design of effective, robust and autonomous controllers for multi-agent and multi-robot systems is a long-standing problem in the fields of computational intelligence and robotics. Whilst nature-inspired problem-solving techniques such as reinforcement learning (RL) and evolutionary algorithms (EA) are often used to adapt controllers for solving such tasks, the complexity of such tasks increases with the addition of more agents (or robots) in difficult environments. This is due to specific issues related to task complexity, such as the curse of dimensionality and bootstrapping problems. Despite an increasing attempt over the last decade to incorporate behavior (knowledge) transfer in machine learning so that relevant behavior acquired in previous learning experiences can be used to boost task performance in complex tasks, using evolutionary algorithms to facilitate behavior transfer (especially multi-agent behavior transfer) has received little attention. It remains unclear how behavior transfer addresses issues such as the bootstrapping problem in complex multi-agent tasks (for example, RoboCup soccer). This thesis seeks to investigate and establish the essential features constituting effective and efficient evolutionary search to augment behavior transfer for boosting the quality of evolved behaviors across increasingly complex tasks. Experimental results indicate a hybrid of objective-based search and behavioral diversity maintenance in evolutionary controller design coupled with behavior transfer yields evolved behaviors of significantly high quality across increasingly complex multi-agent tasks. The evolutionary controller design method thus addresses the bootstrapping task for the given range of multi-agent tasks, whilst comparative controller design methods yield scant performance results. DA - 2018 DB - OpenUCT DP - University of Cape Town LK - https://open.uct.ac.za PB - University of Cape Town PY - 2018 T1 - Neuro-evolution behavior transfer for collective behavior tasks TI - Neuro-evolution behavior transfer for collective behavior tasks UR - http://hdl.handle.net/11427/27910 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/27910
dc.identifier.vancouvercitationDidi SZ. Neuro-evolution behavior transfer for collective behavior tasks. [Thesis]. University of Cape Town ,Faculty of Science ,Department of Computer Science, 2018 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/27910en_ZA
dc.language.isoengen_ZA
dc.publisher.departmentDepartment of Computer Scienceen_ZA
dc.publisher.facultyFaculty of Scienceen_ZA
dc.publisher.institutionUniversity of Cape Town
dc.subject.otherComputer Scienceen_ZA
dc.titleNeuro-evolution behavior transfer for collective behavior tasksen_ZA
dc.typeDoctoral Thesis
dc.type.qualificationlevelDoctoral
dc.type.qualificationnamePhDen_ZA
uct.type.filetypeText
uct.type.filetypeImage
uct.type.publicationResearchen_ZA
uct.type.resourceThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
thesis_sci_2018_didi_sabre_z.pdf
Size:
7.11 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
PhD / Doctoral