Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning. Some notable examples include training agents to play Atari games based on raw pixel data and to acquire advanced manipulation skills using raw sensory inputs. However, it has been difficult to quantify progress in the domain of continuous control due to the lack of a commonly adopted benchmark. In this work, we present a benchmark suite of continuous control tasks, including classic tasks like cart-pole swing-up, tasks with very high state and action dimensionality such as 3D humanoid locomotion, tasks with partial observations, and tasks with hierarchical structure. We report novel findings based on the systematic evaluation of a range of implemented reinforcement learning algorithms. Both the benchmark and reference implementations are released at this https URL in order to facilitate experimental reproducibility and to encourage adoption by other researchers.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Benchmarking deep reinforcement learning for continous control


    Beteiligte:
    Duan, Yan (Autor:in) / Chen, Xi (Autor:in) / Houthooft, Rein (Autor:in) / Schulman, John (Autor:in) / Abbeel, Pieter (Autor:in)

    Erscheinungsdatum :

    2016-01-01


    Anmerkungen:

    Proceedings of the 33rd International Conference on Machine Learning (ICML)


    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Enhancing continous miner flexibility

    Walker, S. | Tema Archiv | 1994


    Continous Oil Change System

    Power Plus,US | Kraftfahrwesen | 1979


    Continous Oil Change System

    Power Plus,City of Industry,US | Kraftfahrwesen | 1980


    Continous Flow Customized Production

    Sandras,W.A. / Hewlett-Packard,US | Kraftfahrwesen | 1985


    Continous improvement and simultaneous engineering

    Walklet,R.H. / General Motors,Cadillac Div.,US | Kraftfahrwesen | 1989