Šošić, A. ; Rueckert, E. ; Peters, J. ; Zoubir, A. M. ; Koeppl, H. (2018)
Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling.
In: Journal of Machine Learning Research, 19 (69)
Artikel, Bibliographie
Dies ist die neueste Version dieses Eintrags.
Kurzbeschreibung (Abstract)
Advances in the field of inverse reinforcement learning (IRL) have led to sophisticated inference frameworks that relax the original modeling assumption of observing an agent behavior that reflects only a single intention. Instead of learning a global behavioral model, recent IRL methods divide the demonstration data into parts, to account for the fact that different trajectories may correspond to different intentions, e.g., because they were generated by different domain experts. In this work, we go one step further: using the intuitive concept of subgoals, we build upon the premise that even a single trajectory can be explained more efficiently locally within a certain context than globally, enabling a more compact representation of the observed behavior. Based on this assumption, we build an implicit intentional model of the agent's goals to forecast its behavior in unobserved situations. The result is an integrated Bayesian prediction framework that significantly outperforms existing IRL solutions and provides smooth policy estimates consistent with the expert's plan. Most notably, our framework naturally handles situations where the intentions of the agent change over time and classical IRL algorithms fail. In addition, due to its probabilistic nature, the model can be straightforwardly applied in active learning scenarios to guide the demonstration process of the expert.
Typ des Eintrags: | Artikel |
---|---|
Erschienen: | 2018 |
Autor(en): | Šošić, A. ; Rueckert, E. ; Peters, J. ; Zoubir, A. M. ; Koeppl, H. |
Art des Eintrags: | Bibliographie |
Titel: | Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling |
Sprache: | Englisch |
Publikationsjahr: | 2018 |
Verlag: | Microtome Publishing |
Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Journal of Machine Learning Research |
Jahrgang/Volume einer Zeitschrift: | 19 |
(Heft-)Nummer: | 69 |
URL / URN: | http://jmlr.org/papers/v19/18-113.html |
Zugehörige Links: | |
Kurzbeschreibung (Abstract): | Advances in the field of inverse reinforcement learning (IRL) have led to sophisticated inference frameworks that relax the original modeling assumption of observing an agent behavior that reflects only a single intention. Instead of learning a global behavioral model, recent IRL methods divide the demonstration data into parts, to account for the fact that different trajectories may correspond to different intentions, e.g., because they were generated by different domain experts. In this work, we go one step further: using the intuitive concept of subgoals, we build upon the premise that even a single trajectory can be explained more efficiently locally within a certain context than globally, enabling a more compact representation of the observed behavior. Based on this assumption, we build an implicit intentional model of the agent's goals to forecast its behavior in unobserved situations. The result is an integrated Bayesian prediction framework that significantly outperforms existing IRL solutions and provides smooth policy estimates consistent with the expert's plan. Most notably, our framework naturally handles situations where the intentions of the agent change over time and classical IRL algorithms fail. In addition, due to its probabilistic nature, the model can be straightforwardly applied in active learning scenarios to guide the demonstration process of the expert. |
Fachbereich(e)/-gebiet(e): | 18 Fachbereich Elektrotechnik und Informationstechnik 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Nachrichtentechnik > Bioinspirierte Kommunikationssysteme 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Nachrichtentechnik 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Nachrichtentechnik > Signalverarbeitung Zentrale Einrichtungen Zentrale Einrichtungen > Centre for Cognitive Science (CCS) |
Hinterlegungsdatum: | 28 Feb 2018 12:31 |
Letzte Änderung: | 13 Mai 2024 09:49 |
PPN: | |
Export: | |
Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
-
Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling. (deposited 30 Apr 2024 09:17)
- Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling. (deposited 28 Feb 2018 12:31) [Gegenwärtig angezeigt]
Frage zum Eintrag |
Optionen (nur für Redakteure)
Redaktionelle Details anzeigen |