Sökning: WFRF:(Baumann Dominik Ph.D. 1991 ) >
GOSAFEOPT :
GOSAFEOPT : Scalable safe exploration for global optimization of dynamical systems
-
- Sukhija, Bhavya (författare)
- Swiss Fed Inst Technol, Dept Comp Sci, Zurich, Switzerland.
-
- Turchetta, Matteo (författare)
- Swiss Fed Inst Technol, Dept Comp Sci, Zurich, Switzerland.
-
- Lindner, David (författare)
- Swiss Fed Inst Technol, Dept Comp Sci, Zurich, Switzerland.
-
visa fler...
-
- Krause, Andreas (författare)
- Swiss Fed Inst Technol, Dept Comp Sci, Zurich, Switzerland.
-
- Trimpe, Sebastian (författare)
- Rhein Westfal TH Aachen, Inst Data Sci Mech Engn, Aachen, Germany.
-
- Baumann, Dominik, Ph.D. 1991- (författare)
- Uppsala universitet,Avdelningen för systemteknik,Artificiell intelligens,Aalto Univ, Dept Elect Engn & Automat, Espoo, Finland.
-
visa färre...
-
Swiss Fed Inst Technol, Dept Comp Sci, Zurich, Switzerland Rhein Westfal TH Aachen, Inst Data Sci Mech Engn, Aachen, Germany. (creator_code:org_t)
- Elsevier BV, 2023
- 2023
- Engelska.
-
Ingår i: Artificial Intelligence. - : Elsevier BV. - 0004-3702 .- 1872-7921. ; 320
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://uu.diva-port... (primary) (Raw object)
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Learning optimal control policies directly on physical systems is challenging. Even a single failure can lead to costly hardware damage. Most existing model-free learning methods that guarantee safety, i.e., no failures, during exploration are limited to local optima. This work proposes GOSAFEOPT as the first provably safe and optimal algorithm that can safely discover globally optimal policies for systems with high-dimensional state space. We demonstrate the superiority of GOSAFEOPT over competing model-free safe learning methods in simulation and hardware experiments on a robot arm.(c) 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons .org /licenses /by /4 .0/).
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Model-free learning
- Bayesian optimization
- Safe learning
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas