Passive sensory processing is often insufficient to guide biological organisms in complex environments. Rather, behaviourally relevant information can be accessed by performing so-called epistemic actions that explicitly aim at unveiling hidden information. However, it is still unclear how an autonomous agent can learn epistemic actions and how it can use them adaptively. In this work, we propose a definition of epistemic actions for POMDPs that derive from their characterizations in cognitive science and classical planning literature. We give theoretical insights about how partial observability and epistemic actions can affect the learning process and performance in the extreme conditions of model-free and memory-free reinforcement learning where hidden information cannot be represented. We finally investigate these concepts using an integrated eye-arm neural architecture for robot control, which can use its effectors to execute epistemic actions and can exploit the actively gathered information to efficiently accomplish a seek-and-reach task.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Learning Epistemic Actions in Model-Free Memory-Free Reinforcement Learning: experiments with a neuro-robotic model



    Erscheinungsdatum :

    2013-01-01



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    MODEL-FREE REINFORCEMENT LEARNING

    SAXENA DHRUV MAURIA / BAE SANGJAE / NAKHAEI SARVEDANI ALIREZA et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Model-free reinforcement learning

    SAXENA DHRUV MAURIA / BAE SANGJAE / NAKHAEI SARVEDANI ALIREZA et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Model-free Reinforcement Learning Technique for Nonlinear Systems

    Mohamadizaniani, Maryam | BASE

    Freier Zugriff

    Model-free Deep Reinforcement Learning for Urban Autonomous Driving

    Chen, Jianyu / Yuan, Bodi / Tomizuka, Masayoshi | IEEE | 2019


    Airport Runway Configuration Management with Offline Model-free Reinforcement Learning

    Milad Memarzadeh / Tejas Puranik / Krishna Kalyanam et al. | NTRS