Hindsight-Combined and Hindsight-Prioritized Experience Replay

Renzo Roel P Tan, Kazushi Ikeda, John Paul Vergara

    Research output: Contribution to journalArticlepeer-review

    Original languageAmerican English
    JournalMathematics Faculty Publications
    StatePublished - Nov 1 2020

    Keywords

    • Experience replay
    • Deep Q-Network
    • reinforcement learning
    • sample efficiency
    • hybrid algorithm

    Disciplines

    • Logic and Foundations
    • Mathematics

    Cite this