Integration of genetic programming and reinforcement learning for real robots

Authors:
Shotaro Kamio;Hideyuki Mitsuhashi;Hitoshi Iba
Affiliations:
Graduate School of Frontier Science, The University of Tokyo, Bunkyo-ku, Tokyo, Japan;Graduate School of Frontier Science, The University of Tokyo, Bunkyo-ku, Tokyo, Japan;Graduate School of Frontier Science, The University of Tokyo, Bunkyo-ku, Tokyo, Japan
Venue:
GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartI
Year:
2003

Citing 7
Cited 2

Simulation-assisted learning by competition: effects of noise differences between training model and target environment

Proceedings of the seventh international conference (1990) on Machine learning
Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
Purposive behavior acquisition for a real robot by vision-based reinforcement learning

Machine Learning - Special issue on robot learning
Robot Shaping: An Experiment in Behavior Engineering

Robot Shaping: An Experiment in Behavior Engineering
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Multi-agent Robot Learning by Means of Genetic Programming: Solving an Escape Problem

ICES '01 Proceedings of the 4th International Conference on Evolvable Systems: From Biology to Hardware
Hierarchical reinforcement learning with the MAXQ value function decomposition

Journal of Artificial Intelligence Research

A genetic programming formulation to evade proportional navigation

Proceedings of the 43rd annual Southeast regional conference - Volume 2
Genetic programming incorporating biased mutation for evolution and adaptation of Snakebot

Genetic Programming and Evolvable Machines

Quantified Score

Hi-index	0.03

Visualization

Abstract

We propose an integrated technique of genetic programming (GP) and reinforcement learning (RL) that allows a real robot to execute real-time learning. Our technique does not need a precise simulator because learning is done with a real robot. Moreover, our technique makes it possible to learn optimal actions in real robots. We show the result of an experiment with a real robot AIBO and represents the result which proves proposed technique performs better than traditional Q-learning method.