Clay: Integrating Motor Schemas and Reinforcement Learning
Author(s)
Balch, Tucker
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
Clay is an evolutionary architecture for autonomous robots that integrates
motor schema-based control and reinforcement learning. Robots utilizing
Clay benefit from the real-time performance of motor schemas in continuous
and dynamic environments while taking advantage of adaptive reinforcement
learning. Clay coordinates assemblages (groups of motor schemas) using
embedded reinforcement learning modules. The coordination modules activate
specific assemblages based on the presently perceived situation. Learning
occurs as the robot selects assemblages and samples a reinforcement signal
over time. Experiments in a robot soccer simulation illustrate the
performance and utility of the system.
Sponsor
Date
1997
Extent
384322 bytes
Resource Type
Text
Resource Subtype
Technical Report