Accession Number:

ADA434755

Title:

The Essential Dynamics Algorithm: Essential Results

Descriptive Note:

Corporate Author:

MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s):

Report Date:

2003-05-01

Pagination or Media Count:

12.0

Abstract:

This paper presents a novel algorithm for learning in a class of stochastic Markov decision processes MDPs with continuous state and action spaces that trades speed for accuracy. A transform of the stochastic MDP into a deterministic one is presented which captures the essence of the original dynamics, in a sense made precise. In this transformed MDP, the calculation of values is greatly simplified. the online algorithm estimates the model of the transformed MDP and simultaneously does policy search against it. Bounds on the error of this approximation are proven, and experimental results in a bicycle riding domain are presented. The algorithm learns near optimal policies in orders of magnitude fewer interactions with the stochastic MDP, using less domain knowledge.

Subject Categories:

  • Numerical Mathematics
  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE