the open
    research
    Contribute
    Back to the reading lists

    Reinforcement learning· 2015

    Trust Region Policy Optimization

    John Schulman (first author) · 2015

    Read the original

    arXiv 1502.05477OpenAlex W1771410628

    On the reading lists

    Why it matters

    Established stable policy improvement through trust-region constraints, directly inspiring PPO.

    Condensed from the expert lists' notes.

    The record

    First released
    2015 (from arXiv 1502.05477)
    Citations
    8,424 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Awards
    ICML Test of Time
    Named by
    both expert lists
    Score
    0.758 · computed rank 22 · consensus 0.78, must-read 0.5, citations percentile 0.783 (2010s · reinforcement-learning), awards 1, 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.