Show simple item record

dc.contributor.author
Lee, Joonho
dc.contributor.author
Schroth, Lukas
dc.contributor.author
Klemm, Victor
dc.contributor.author
Bjelonic, Marko
dc.contributor.author
Reske, Alexander
dc.contributor.author
Hutter, Marco
dc.date.accessioned
2025-01-06T10:13:33Z
dc.date.available
2024-11-06T07:12:06Z
dc.date.available
2024-11-06T09:15:55Z
dc.date.available
2025-01-06T10:13:33Z
dc.date.issued
2024
dc.identifier.isbn
979-8-3503-7770-5
en_US
dc.identifier.isbn
979-8-3503-7771-2
en_US
dc.identifier.other
10.1109/IROS58592.2024.10801341
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/703818
dc.identifier.doi
10.3929/ethz-b-000703818
dc.description.abstract
Shifting from traditional control strategies to Deep Reinforcement Learning (RL) for legged robots poses inherent challenges, especially when addressing real-world physical con straints during training. While high-fidelity simulations provide significant benefits, they often bypass these essential physical limitations. In this paper, we experiment with the Constrained Markov Decision Process (CMDP) framework instead of the conventional unconstrained RL for robotic applications. We evaluated five constrained policy optimization algorithms for quadrupedal locomotion using three different robot models. Our aim is to evaluate their applicability in real-world sce narios. Our robot experiments demonstrate the critical role of incorporating physical constraints, yielding successful sim-to-real transfers, and reducing operational errors on physical systems. The CMDP formulation streamlines the training process by separately handling constraints from rewards. Our findings underscore the potential of constrained RL for the effective development and deployment of learned controllers in robotics.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.title
Exploring Constrained Reinforcement Learning Algorithms for Quadrupedal Locomotion
en_US
dc.type
Conference Paper
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2024-12-25
ethz.book.title
2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
en_US
ethz.pages.start
11132
en_US
ethz.pages.end
11138
en_US
ethz.version.deposit
acceptedVersion
en_US
ethz.event
37th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)
en_US
ethz.event.location
Abu Dhabi, United Arab Emirates
en_US
ethz.event.date
October 14-18, 2024
en_US
ethz.grant
Learning Mobility for Real Legged Robots
en_US
ethz.publication.place
Piscataway, NJ
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02130 - Dep. Maschinenbau und Verfahrenstechnik / Dep. of Mechanical and Process Eng.::02620 - Inst. f. Robotik u. Intelligente Systeme / Inst. Robotics and Intelligent Systems::09570 - Hutter, Marco / Hutter, Marco
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02130 - Dep. Maschinenbau und Verfahrenstechnik / Dep. of Mechanical and Process Eng.::02620 - Inst. f. Robotik u. Intelligente Systeme / Inst. Robotics and Intelligent Systems::09570 - Hutter, Marco / Hutter, Marco
en_US
ethz.grant.agreementno
852044
ethz.grant.agreementno
852044
ethz.grant.fundername
EC
ethz.grant.fundername
EC
ethz.grant.funderDoi
10.13039/501100000780
ethz.grant.funderDoi
10.13039/501100000780
ethz.grant.program
H2020
ethz.grant.program
H2020
ethz.date.deposited
2024-11-06T07:12:06Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2025-01-06T10:13:34Z
ethz.rosetta.lastUpdated
2025-02-14T16:33:45Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Exploring%20Constrained%20Reinforcement%20Learning%20Algorithms%20for%20Quadrupedal%20Locomotion&rft.date=2024&rft.spage=11132&rft.epage=11138&rft.au=Lee,%20Joonho&Schroth,%20Lukas&Klemm,%20Victor&Bjelonic,%20Marko&Reske,%20Alexander&rft.isbn=979-8-3503-7770-5&979-8-3503-7771-2&rft.genre=proceeding&rft_id=info:doi/10.1109/IROS58592.2024.10801341&rft.btitle=2024%20IEEE/RSJ%20International%20Conference%20on%20Intelligent%20Robots%20and%20Systems%20(IROS)
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record