In this paper we propose a method to augment a Reinforcement Learning agent with legibility. This method is inspired by the literature in Explainable Planning and allows to regularize the agent’s policy after training, and without requiring to modify its learning algorithm. This is achieved by evaluating how the agent’s optimal policy may produce observations that would make an observer model to infer a wrong policy. In our formulation, the decision boundary introduced by legibility impacts the states in which the agent’s policy returns an action that is non-legible because having high likelihood also in other policies. In these cases, a trade-off between such action, and legible/sub-optimal action is made. We tested our method in a grid-world environment highlighting how legibility impacts the agent’s optimal policy, and gathered both quantitative and qualitative results. In addition, we discuss how the proposed regularization generalizes over methods functioning with goal-driven policies, because applicable to general policies of which goal-driven policies are a special case. ; Originally included in thesis in manuscript form.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Policy regularization for legible behavior


    Beteiligte:

    Erscheinungsdatum :

    2023-01-01


    Anmerkungen:

    Scopus 2-s2.0-85140636891



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    006 / 629



    Familiar Acoustic Cues for Legible Service Robots

    Angelopoulos G. / Vigni F. / Rossi A. et al. | BASE | 2022

    Freier Zugriff

    Legible Action Selection in Human-Robot Collaboration

    Zhu, Huaijiang / Gabler, Volker / Wollherr, Dirk | BASE | 2017

    Freier Zugriff


    A Highly Legible 6″ Multicolor Information LCD for Diagnostics and Navigation Uses

    Araki, Hiroshi / Tsubota, Hiroyoshi / Aoyama, Masao et al. | SAE Technical Papers | 1989


    A highly legible 6 inch multicolor information lcd for diagnostics and navigation uses

    Araki,H. / Muto,R. / Uchida,Y. et al. | Kraftfahrwesen | 1989