Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives

    Shagun Sodhani
    Shagun Sodhani
    Jonathan Binas
    Jonathan Binas
    Xue Bin Peng
    Xue Bin Peng
    Cited by: 0|Bibtex|35|

    international conference on learning representations, 2020.

    Abstract:

    Reinforcement learning agents that operate in diverse and complex environments can benefit from the structured decomposition of their behavior. Often, this is addressed in the context of hierarchical reinforcement learning, where the aim is to decompose a policy into lower-level primitives or options, and a higher-level meta-policy that t...More
    Your rating :
    0

     

    Tags
    Comments