Learning the Arrow of Time for Problems in Reinforcement Learning

    Nasim Rahaman
    Nasim Rahaman
    Steffen Wolf
    Steffen Wolf
    Roman Remme
    Roman Remme
    Cited by: 0|Bibtex|29|

    international conference on learning representations, 2020.

    Keywords:
    Arrow of Time Reinforcement Learning AI-Safety

    Abstract:

    We humans have an innate understanding of the asymmetric progression of time, which we use to efficiently and safely perceive and manipulate our environment. Drawing inspiration from that, we approach the problem of learning an arrow of time in a Markov (Decision) Process. We illustrate how a learned arrow of time can capture salient info...More
    Your rating :
    0

     

    Tags
    Comments