Accession Number : ADA259893


Title :   A Comparative Analysis of Reinforcement Learning Methods


Descriptive Note : Memorandum rept.


Corporate Author : MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB


Personal Author(s) : Mataric, Maja J


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a259893.pdf


Report Date : Oct 1991


Pagination or Media Count : 13


Abstract : This paper analyzes the suitability of reinforcement learning for both programming and adapting situated agents. In the first part of the paper we discuss two specific reinforcement learning algorithms: Q-learning and the Bucket Brigade. We introduce a special case of the Bucket Brigade, and analyze and compare its performance to Q-learning in a number of experiments. The second part of the paper discusses the key problems of reinforcement learning: time and space complexity, input generalization, sensitivity to parameter values, and selection of the reinforcement function. We address the tradeoff between the amount of built in and learned knowledge in the context of the number of training examples required by a learning algorithm. Finally, we suggest directions for future research.


Descriptors :   *COMPUTER PROGRAMMING , *ARTIFICIAL INTELLIGENCE , ALGORITHMS , LEARNING , PARAMETERS


Subject Categories : Computer Programming and Software
      Cybernetics


Distribution Statement : APPROVED FOR PUBLIC RELEASE