Adaptation technique for integrating genetic programming and reinforcement learning for real robots

Authors:
S. Kamio;H. Iba
Affiliations:
Graduate Sch. of Frontier Sci., Univ. of Tokyo, Chiba, Japan;-
Venue:
IEEE Transactions on Evolutionary Computation
Year:
2005

Citing 0
Cited 6

A Graph-Based Evolutionary Algorithm: Genetic Network Programming (GNP) and Its Extension Using Reinforcement Learning

Evolutionary Computation
Fitness functions in evolutionary robotics: A survey and analysis

Robotics and Autonomous Systems
Evolving controllers for high-level applications on a service robot: a case study with exhibition visitor flow control

Genetic Programming and Evolvable Machines
Adaptability analysis of genetic network programming with reinforcement learning in dynamically changing environments

Expert Systems with Applications: An International Journal
Backward Q-learning: The combination of Sarsa algorithm and Q-learning

Engineering Applications of Artificial Intelligence
A variable size mechanism of distributed graph programs and its performance evaluation in agent control problems

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose an integrated technique of genetic programming (GP) and reinforcement learning (RL) to enable a real robot to adapt its actions to a real environment. Our technique does not require a precise simulator because learning is achieved through the real robot. In addition, our technique makes it possible for real robots to learn effective actions. Based on this proposed technique, we acquire common programs, using GP, which are applicable to various types of robots. Through this acquired program, we execute RL in a real robot. With our method, the robot can adapt to its own operational characteristics and learn effective actions. In this paper, we show experimental results from two different robots: a four-legged robot "AIBO" and a humanoid robot "HOAP-1." We present results showing that both effectively solved the box-moving task; the end result demonstrates that our proposed technique performs better than the traditional Q-learning method.