Reinforcement learning with supervision by a stable controller

Reinforcement learning (RL) methods provide a means for solving optimal control problems when accurate models are unavailable. For many such problems, however, RL alone is impractical and the associated learning problem must be structured somehow to take advantage of prior knowledge. In this paper w...

Full description

Saved in:
Bibliographic Details
Main Authors: Rosenstein, M.T., Barto, A.G.
Format: Conference Proceeding
Language:English
Subjects:
Animals
Applied sciences
Artificial intelligence
Computer science
Computer science
control theory
systems
Control system synthesis
Control systems
Control theory. Systems
Exact sciences and technology
Learning systems
Manipulators
Mathematical model
Modelling and identification
Optimal control
Protection
Robotics
Robots
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Reinforcement learning (RL) methods provide a means for solving optimal control problems when accurate models are unavailable. For many such problems, however, RL alone is impractical and the associated learning problem must be structured somehow to take advantage of prior knowledge. In this paper we examine the use of such knowledge in the form of a stable controller that generates control inputs in parallel with an RL system. The controller acts as a supervisor that not only teaches the RL system about favorable control actions but also protects the learning system from risky behavior. We demonstrate the approach with a simulated robotic arm and a real seven-DOF manipulator.
ISSN:0743-1619
2378-5861
DOI:10.23919/ACC.2004.1384022