TU Darmstadt / ULB / TUbiblio

High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards

Ploeger, Kai ; Lutter, Michael ; Peters, Jan (2022)
High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards.
Conference on Robot Learning (CoRL) 2020. Cambridge MA, USA (16.-18.11.2020)
Konferenzveröffentlichung, Bibliographie

Dies ist die neueste Version dieses Eintrags.

Kurzbeschreibung (Abstract)

Robots that can learn in the physical world will be important to enable robots to escape their stiff and pre-programmed movements. For dynamic high-acceleration tasks, such as juggling, learning in the real-world is particularly challenging as one must push the limits of the robot and its actuation without harming the system, amplifying the necessity of sample efficiency and safety for robot learning algorithms. In contrast to prior work which mainly focuses on the learning algorithm, we propose a learning system, that directly incorporates these requirements in the design of the policy representation, initialization, and optimization. We demonstrate that this system enables the high-speed Barrett WAM manipulator to learn juggling two balls from 56 minutes of experience with a binary reward signal and finally juggles continuously for up to 33 minutes or about 4500 repeated catches. The videos documenting the learning process and the evaluation can be found at https://sites.google.com/view/jugglingbot

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2022
Autor(en): Ploeger, Kai ; Lutter, Michael ; Peters, Jan
Art des Eintrags: Bibliographie
Titel: High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards
Sprache: Englisch
Publikationsjahr: 2022
Ort: Darmstadt
Verlag: PMLR
Buchtitel: Proceedings of the 2020 Conference on Robot Learning
Reihe: Proceedings of Machine Learning Research
Band einer Reihe: 155
Kollation: 12 Seiten
Veranstaltungstitel: Conference on Robot Learning (CoRL) 2020
Veranstaltungsort: Cambridge MA, USA
Veranstaltungsdatum: 16.-18.11.2020
Zugehörige Links:
Kurzbeschreibung (Abstract):

Robots that can learn in the physical world will be important to enable robots to escape their stiff and pre-programmed movements. For dynamic high-acceleration tasks, such as juggling, learning in the real-world is particularly challenging as one must push the limits of the robot and its actuation without harming the system, amplifying the necessity of sample efficiency and safety for robot learning algorithms. In contrast to prior work which mainly focuses on the learning algorithm, we propose a learning system, that directly incorporates these requirements in the design of the policy representation, initialization, and optimization. We demonstrate that this system enables the high-speed Barrett WAM manipulator to learn juggling two balls from 56 minutes of experience with a binary reward signal and finally juggles continuously for up to 33 minutes or about 4500 repeated catches. The videos documenting the learning process and the evaluation can be found at https://sites.google.com/view/jugglingbot

Freie Schlagworte: Reinforcement Learning, Dynamic Manipulation, Juggling
Sachgruppe der Dewey Dezimalklassifikatin (DDC): 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Intelligente Autonome Systeme
TU-Projekte: EC/H2020|640554|SKILLS4ROBOTS
Hinterlegungsdatum: 02 Aug 2024 12:45
Letzte Änderung: 02 Aug 2024 12:45
PPN:
Export:
Suche nach Titel in: TUfind oder in Google

Verfügbare Versionen dieses Eintrags

Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen