Transfer learning exploiting demonstrations in a human-robot interactive game

Σταύρου, Νικόλαος; Stavrou, Nikolaos

dc.contributor.author	Σταύρου, Νικόλαος
dc.contributor.author	Stavrou, Nikolaos	en
dc.date.accessioned	2024-06-28T09:48:56Z
dc.date.available	2024-06-28T09:48:56Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/59767
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.27463
dc.rights	Default License
dc.subject	Human-Robot Collaboration	en
dc.subject	Machine Learning	en
dc.subject	Reinforcement learning	en
dc.subject	Transfer learning	en
dc.subject	Learning from demonstrations	en
dc.title	Transfer learning exploiting demonstrations in a human-robot interactive game	en
heal.type	bachelorThesis
heal.classification	Robotics	el
heal.language	el
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2024-03-28
heal.abstract	Enhancing Human-Robot Collaboration requires robots that are not only socially aware but also proficient in adapting and learning from interactions to perform interdependent tasks effectively. This thesis extends recent research by focusing on the dynamics of Human-Robot Collaboration where humans collaborate with a Deep Reinforcement Learning agent to achieve a common goal. The performance in such collaborations de pends on the Deep Reinforcement Learning agent’s ability to adapt and learn from its human partner and vice versa. Our study implements an alternative Transfer Learning (TL) approach, Learning from Demonstrations, specifically through Deep Q-Learning from Demonstrations (DQfD), aimed at encouraging more efficient human-robot teamwork. In contrast to the foundational work that utilized Probabilistic Policy Reuse, our approach, coupled with adjustments to the Soft Actor Critic algorithm’s settings, seeks to enhance adaptability and learning outcomes. We conducted experiments involving 24 participants to evaluate the impact of these changes. Our findings suggest that the direct transfer of expertise with Learning from Demonstrations, complemented by specific SAC algorithm settings can significantly influence the collaborative performance.	el
heal.advisorName	Τζαφέστας, Κωνσταντίνος	el
heal.committeeMemberName	Κορδώνης, Ιωάννης	el
heal.committeeMemberName	Ψυλλάκης, Χαράλαμπος	el
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών. Τομέας Σημάτων, Ελέγχου και Ρομποτικής	el
heal.academicPublisherID	ntua
heal.numberOfPages	122 σ.	el
heal.fullTextAvailability	false