F. Kabanza

  1. Decision-Theoretic Planning with non-Markovian Rewards.

    Authors: C. Gretton, F. Kabanza, D. Price, J. Slaney, S. Thiebaux
    Subjects: Artificial Intelligence
    Abstract

    A decision process in which rewards depend on history rather than merely on
    the current state is called a decision process with non-Markovian rewards
    (NMRDP). In decision-theoretic planning, where many desirable behaviours are
    more naturally expressed as properties of execution sequences rather than as
    properties of states, NMRDPs form a more natural model than the commonly
    adopted fully Markovian decision process (MDP) model.

Syndicate content