the open
    research
    Contribute
    Back to the reading lists

    Reinforcement learning· 2016

    Asynchronous Methods for Deep Reinforcement Learning

    Volodymyr Mnih (first author) · 2016

    Read the original

    arXiv 1602.01783OpenAlex W2260756217

    On the reading lists

    Why it matters

    Popularized parallel actor-critic training, stabilizing deep RL without experience replay.

    Condensed from the expert lists' notes.

    The record

    First released
    2016 (from arXiv 1602.01783)
    Citations
    10,427 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.617 · computed rank 132 · consensus 0.71, must-read 0.5, citations percentile 0.87 (2010s · reinforcement-learning), awards 0, existing lists 0.5. Method

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.