The optimal Reward Baseline for Gradient-Based Reinforcement Learning

L Weaver, Nigel Tao

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Original languageEnglish
    Title of host publicationUncertainty in Artificial Intelligence: Proceedings of the Seventeenth Conference (2001)
    EditorsJack Breese & Daphne Koller
    Place of PublicationSan Francisco
    PublisherMorgan Kauffman Publishers
    Pages538-545
    EditionPeer Reviewed
    ISBN (Print)1558608001
    Publication statusPublished - 2001
    EventConference on Uncertainty in Artificial Intelligence (UAI 2001) - Seattle USA
    Duration: 1 Jan 2001 → …

    Conference

    ConferenceConference on Uncertainty in Artificial Intelligence (UAI 2001)
    Period1/01/01 → …
    OtherAugust 2 2001

    Cite this