Accession Number : ADA261434


Title :   Reinforcement Learning for Robots Using Neural Networks


Descriptive Note : Doctoral thesis


Corporate Author : CARNEGIE-MELLON UNIV PITTSBURGH PA SCHOOL OF COMPUTER SCIENCE


Personal Author(s) : Lin, Long-Ji


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a261434.pdf


Report Date : 06 Jan 1993


Pagination or Media Count : 168


Abstract : Reinforcement learning agents are adaptive, reactive, and self-supervised. The aim of this dissertation is to extend the state of the art of reinforcement learning and enable its applications to complex robot-learning problems. In particular, it focuses on two issues. First, learning from sparse and delayed reinforcement signals is hard and in general a slow process. Techniques for reducing learning time must be devised. Second, most existing reinforcement learning methods assume that the world is a Markov decision process. This assumption is too strong for many robot tasks of interest, This dissertation demonstrates how one can possibly overcome the slow learning problem and tackle non-Markovian environments, making reinforcement learning more practical for realistic robot tasks.


Descriptors :   *NEURAL NETS , *ROBOTS , *LEARNING MACHINES , *ARTIFICIAL INTELLIGENCE , *PROBLEM SOLVING , COMPUTERIZED SIMULATION , TIME , MARKOV PROCESSES , SELF OPERATION , THESES , DECISION MAKING , STATE OF THE ART , MEMORY(PSYCHOLOGY)


Subject Categories : Cybernetics


Distribution Statement : APPROVED FOR PUBLIC RELEASE