Accession Number : ADA311507

Title :   Variable Resolution Reinforcement Learning.

Descriptive Note : Technical rept.,

Corporate Author : CARNEGIE-MELLON UNIV PITTSBURGH PA ROBOTICS INST

Personal Author(s) : Moore, Andrew W.

PDF Url : ADA311507

Report Date : APR 1995

Pagination or Media Count : 23

Abstract : Can reinforcement learning ever become a practical method for real control problems? This paper begins by reviewing three reinforcement learning algorithms to study their shortcomings and to motivate subsequent improvements. By assuming that paths must be continuous, we can substantially reduce the proportion of state space which the learning algorithms need explore. Next, we introduce the partigame algorithm for variable resolution reinforcement learning. In addition to exploring state space, and developing a control policy to achieve a task, partigame also learns a kd-tree partitioning of state space. Some experiments are described which show partigame in operation on a non-linear dynamics problems and a path learning planning task in a 9-dimensional configuration space.

Descriptors :   *ROBOTS, *LEARNING MACHINES, ALGORITHMS, OPTIMIZATION, QUEUEING THEORY, RESOLUTION, NONLINEAR SYSTEMS, CONVERGENCE, SYSTEMS ANALYSIS, CONTROL THEORY, DYNAMIC PROGRAMMING, GAME THEORY, CONDITIONING(LEARNING), AUTOMATIC PROGRAMMING.

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE