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. All code used in the experiments is available on the project's web site.
Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/6718 |
Date | 01 May 2003 |
Creators | Martin, Martin C. |
Source Sets | M.I.T. Theses and Dissertation |
Language | en_US |
Detected Language | English |
Format | 12 p., 1085830 bytes, 303781 bytes, application/postscript, application/pdf |
Relation | AIM-2003-014 |
Page generated in 0.0354 seconds