Multi-Agent Reinforcement Learning and Adaptive Neural Networks.

Abstract

This project investigated learning systems consisting of multiple interacting controllers, or agents: each of which employed a modern reinforcement learning method. The objective was to study the utility of reinforcement learning as an approach to complex decentralized control problems. The major accomplishment was a detailed study of multi-agent reinforcement learning applied to a large-scale decentralized stochastic control problem. This study included a very successful demonstration that a multi-agent reinforcement learning system using neural networks could learn high-performance dispatching of multiple elevator cars in a simulated multi-story building. This problem is representative of very large-scale dynamic optimization problems of practical importance that are intractable for standard methods. The performance achieved by the distributed elevator controller surpassed that of the best of the elevator control algorithms accessible in the literature, showing that reinforcement learning can be a useful approach to difficult decentralized control problems. Additional empirical results demonstrated the performance of reinforcement learning-systems in the setting of nonzero-sum games, with mixed results. Some progress was also made in improving theoretical understanding of multi-agent reinforcement learning.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 08, 1996
Accession Number
ADA315266

Entities

People

  • Andrew G. Barto

Organizations

  • University of Massachusetts Amherst

Tags

Communities of Interest

  • Autonomy
  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Computer Programming
  • Computer Programs
  • Computer Science
  • Computers
  • Control Systems
  • Information Processing
  • Information Systems
  • Machine Learning
  • Neural Networks
  • Recurrent Neural Networks
  • Reinforcement Learning
  • Standards
  • Stochastic Control

Readers

  • Computational Modeling and Simulation
  • Structural Dynamics.
  • Systems Analysis and Design

Technology Areas

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