Unsupervised State Representation Learning in AtariEI

    Ankesh Anand
    Ankesh Anand
    Evan Racah
    Evan Racah
    Marc-Alexandre Côté
    Marc-Alexandre Côté
    R. Devon Hjelm
    R. Devon Hjelm
    Click here to see all papers in nips2019
    Cited by: 4|Bibtex|67|

    NeurIPS, pp. 8766-8779, 2019.

    Keywords:
    mutual informationintelligent agents

    Abstract:

    State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks. Learning such representations without supervision from rewards is a challenging open problem. We introduce a method that learns state representations by ...More
    Your rating :
    0

     

    Tags
    Comments