TU Darmstadt / ULB / TUbiblio

Robust Reinforcement Learning: A Review of Foundations and Recent Advances

Moos, Janosch ; Hansel, Kay ; Abdulsamad, Hany ; Stark, Svenja ; Clever, Debora ; Peters, Jan (2022)
Robust Reinforcement Learning: A Review of Foundations and Recent Advances.
In: Machine Learning and Knowledge Extraction, 4 (1)
doi: 10.3390/make4010013
Artikel, Bibliographie

Dies ist die neueste Version dieses Eintrags.

Kurzbeschreibung (Abstract)

Reinforcement learning (RL) has become a highly successful framework for learning in Markov decision processes (MDP). Due to the adoption of RL in realistic and complex environments, solution robustness becomes an increasingly important aspect of RL deployment. Nevertheless, current RL algorithms struggle with robustness to uncertainty, disturbances, or structural changes in the environment. We survey the literature on robust approaches to reinforcement learning and categorize these methods in four different ways: (i) Transition robust designs account for uncertainties in the system dynamics by manipulating the transition probabilities between states; (ii) Disturbance robust designs leverage external forces to model uncertainty in the system behavior; (iii) Action robust designs redirect transitions of the system by corrupting an agent’s output; (iv) Observation robust designs exploit or distort the perceived system state of the policy. Each of these robust designs alters a different aspect of the MDP. Additionally, we address the connection of robustness to the risk-based and entropy-regularized RL formulations. The resulting survey covers all fundamental concepts underlying the approaches to robust reinforcement learning and their recent advances.

Typ des Eintrags: Artikel
Erschienen: 2022
Autor(en): Moos, Janosch ; Hansel, Kay ; Abdulsamad, Hany ; Stark, Svenja ; Clever, Debora ; Peters, Jan
Art des Eintrags: Bibliographie
Titel: Robust Reinforcement Learning: A Review of Foundations and Recent Advances
Sprache: Englisch
Publikationsjahr: 2022
Verlag: MDPI
Titel der Zeitschrift, Zeitung oder Schriftenreihe: Machine Learning and Knowledge Extraction
Jahrgang/Volume einer Zeitschrift: 4
(Heft-)Nummer: 1
DOI: 10.3390/make4010013
Zugehörige Links:
Kurzbeschreibung (Abstract):

Reinforcement learning (RL) has become a highly successful framework for learning in Markov decision processes (MDP). Due to the adoption of RL in realistic and complex environments, solution robustness becomes an increasingly important aspect of RL deployment. Nevertheless, current RL algorithms struggle with robustness to uncertainty, disturbances, or structural changes in the environment. We survey the literature on robust approaches to reinforcement learning and categorize these methods in four different ways: (i) Transition robust designs account for uncertainties in the system dynamics by manipulating the transition probabilities between states; (ii) Disturbance robust designs leverage external forces to model uncertainty in the system behavior; (iii) Action robust designs redirect transitions of the system by corrupting an agent’s output; (iv) Observation robust designs exploit or distort the perceived system state of the policy. Each of these robust designs alters a different aspect of the MDP. Additionally, we address the connection of robustness to the risk-based and entropy-regularized RL formulations. The resulting survey covers all fundamental concepts underlying the approaches to robust reinforcement learning and their recent advances.

Freie Schlagworte: reinforcement learning, robustness, min-max optimization
Sachgruppe der Dewey Dezimalklassifikatin (DDC): 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik
600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften und Maschinenbau
Fachbereich(e)/-gebiet(e): 16 Fachbereich Maschinenbau
16 Fachbereich Maschinenbau > Institut für Mechatronische Systeme im Maschinenbau (IMS)
20 Fachbereich Informatik
20 Fachbereich Informatik > Intelligente Autonome Systeme
Hinterlegungsdatum: 02 Aug 2024 12:39
Letzte Änderung: 02 Aug 2024 12:39
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