TU Darmstadt / ULB / TUbiblio

Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling

Šošić, A. ; Rueckert, E. ; Peters, J. ; Zoubir, A. M. ; Koeppl, H. :
Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling.
[Online-Edition: http://www.jmlr.org/papers/volume19/18-113/18-113.pdf]
In: Journal of Machine Learning Research, 19 (69) S. 1-45.
[Artikel] , (2018)

Offizielle URL: http://www.jmlr.org/papers/volume19/18-113/18-113.pdf

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.
Titel: Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling
Sprache: Englisch
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.

Titel der Zeitschrift, Zeitung oder Schriftenreihe: Journal of Machine Learning Research
Band: 19
(Heft-)Nummer: 69
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
Hinterlegungsdatum: 28 Feb 2018 12:31
Offizielle URL: http://www.jmlr.org/papers/volume19/18-113/18-113.pdf
Export:

Optionen (nur für Redakteure)

Eintrag anzeigen Eintrag anzeigen