Hybrid Computational Models for Skill Acquisition

Abstract

The goal of this research was to develop a hybrid real time problem solving architecture that couples symbolic planning methods with connectionist reinforcement learning methods. The advantage of this hybrid architecture is that it can immediately achieve reasonable performance, because the symbolic planning system can quickly develop an acceptable control policy, but it can also gradually achieve optimal real time performance, because the reinforcement learning system will eventually converge on a near optimal policy. Many DoD problems would benefit from the ability to perform near optimal real time control of complex systems.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 27, 1998
Accession Number
ADA353324

Entities

People

  • Prasad Tadepalli
  • Thomas G. Dietterich

Organizations

  • Oregon State University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Algorithms
  • Applied Computer Science
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Classification
  • Complex Systems
  • Computational Science
  • Computer Programming
  • Computer Science
  • Computers
  • Data Science
  • Electronic Mail
  • Information Processing
  • Job Shop Scheduling
  • Learning
  • Machine Learning
  • Reinforcement Learning

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Artificial Intelligence
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms