Feature reinforcement learning: State of the art

Mayank Daswani, Peter Sunehag, Marcus Hutter

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

    8 Citations (Scopus)

    Abstract

    Feature reinforcement learning was introduced five years ago as a principled and practical approach to history-based learning. This paper examines the progress since its inception. We now have both model-based and model-free cost functions, most recently extended to the function approximation setting. Our current work is geared towards playing ATARI games using imitation learning, where we use Feature RL as a feature selection method for high-dimensional domains.

    Original languageEnglish
    Title of host publicationSequential Decision-Making with Big Data - Papers Presented at the 28th AAAI Conference on Artificial Intelligence, Technical Report
    PublisherAI Access Foundation
    Pages2-5
    Number of pages4
    ISBN (Electronic)9781577356738
    Publication statusPublished - 2014
    Event28th AAAI Conference on Artificial Intelligence, AAAI 2014 - Quebec City, Canada
    Duration: 28 Jul 2014 → …

    Publication series

    NameAAAI Workshop - Technical Report
    VolumeWS-14-12

    Conference

    Conference28th AAAI Conference on Artificial Intelligence, AAAI 2014
    Country/TerritoryCanada
    CityQuebec City
    Period28/07/14 → …

    Fingerprint

    Dive into the research topics of 'Feature reinforcement learning: State of the art'. Together they form a unique fingerprint.

    Cite this