Accession Number : ADA298004

Title :   Learning World Models in Environments with Manifest Causal Structure,

Corporate Author : MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s) : Bergman, Ruth

PDF Url : ADA298004

Report Date : MAY 1995

Pagination or Media Count : 143

Abstract : This thesis examines the problem of an autonomous agent learning a causal world model of its environment. Previous approaches to learning causal world models have concentrated on environments that are too "easy" (deterministic finite state machines) or too "hard" (containing much hidden state). We describe a new domain ?

Descriptors :   *ARTIFICIAL INTELLIGENCE, *LEARNING, ALGORITHMS, METHODOLOGY, GLOBAL, ENVIRONMENTS, MODELS, DISTRIBUTION, COMPUTERS, ROBOTS, RATES, THESES, ERRORS, SELF OPERATION, MACHINES, MAN MACHINE SYSTEMS, LOW RATE, DETERMINANTS(MATHEMATICS).

Subject Categories : Computer Systems
      Numerical Mathematics

Distribution Statement : APPROVED FOR PUBLIC RELEASE