The framework of mixed observable Markov decision processes (MOMDP) models many robotic domains in which some state variables are fully observable while others are not. In this work, we identify a significant subclass of MOMDPs defined by how actions influence the fully observable components of the state and how those, in turn, influence the partially observable components and the rewards. This unique property allows for a two-level hierarchical approach we call HIerarchical Reinforcement Learning under Mixed Observability (HILMO), which restricts partial observability to the top level while the bottom level remains fully observable, enabling higher learning efficiency. The top level produces desired goals to be reached by the bottom level until the task is solved. We further develop theoretical guarantees to show that our approach can achieve optimal and quasi-optimal behavior under mild assumptions. Empirical results on long-horizon continuous control tasks demonstrate the efficacy and efficiency of our approach in terms of improved success rate, sample efficiency, and wall-clock training time. We also deploy policies learned in simulation on a real robot.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Hierarchical Reinforcement Learning Under Mixed Observability


    Weitere Titelangaben:

    Springer Proceedings in Advanced Robotics


    Beteiligte:
    LaValle, Steven M. (Herausgeber:in) / O’Kane, Jason M. (Herausgeber:in) / Otte, Michael (Herausgeber:in) / Sadigh, Dorsa (Herausgeber:in) / Tokekar, Pratap (Herausgeber:in) / Nguyen, Hai (Autor:in) / Yang, Zhihan (Autor:in) / Baisero, Andrea (Autor:in) / Ma, Xiao (Autor:in) / Platt, Robert (Autor:in)

    Kongress:

    International Workshop on the Algorithmic Foundations of Robotics ; 2022 ; , MD, USA June 22, 2022 - June 24, 2022



    Erscheinungsdatum :

    2022-12-15


    Format / Umfang :

    17 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Hierarchical Reinforcement Learning Under Mixed Observability

    Nguyen, Hai / Yang, Zhihan / Baisero, Andrea et al. | TIBKAT | 2023




    AUTONOMOUS BEHAVIOR GENERATION WITH HIERARCHICAL REINFORCEMENT LEARNING

    SOLEYMAN SEAN / KHOSLA DEEPAK | Europäisches Patentamt | 2021

    Freier Zugriff

    Hıerarchıcal reınforcement learnıng on non-statıonary envıronments

    Yücesoy, Yiğit Efe | BASE | 2015

    Freier Zugriff