Abstract
The paper deals with instance-based reinforcement learning control of autonomous robots. A classifier system, defined in the continuous state and action spaces, is outlined. Based on the sensory state space analysis, we define a learning strategy and fix structure of the action rules. The classifier system features a nonconservative bucket brigade algorithm and a fast reproduction mechanism. The system developed is then applied to learning cooperative behavior by two robots coupled via a common object, with each robot controlled by its own classifier. Feasibility of this scheme is tested under experiment with two Lynxmotion robots, and a motion pattern of cooperative behavior (lifting up an object) is evolved using the two interacting classifier systems.
Original language | English |
---|---|
Pages (from-to) | 416-422 |
Number of pages | 7 |
Journal | IEEE International Conference on Intelligent Robots and Systems |
Volume | 1 |
DOIs | |
Publication status | Published - Jan 1 2000 |
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Software
- Computer Vision and Pattern Recognition
- Computer Science Applications