Automatic Symbolic Modelling of Co-evolutionarily Learned Robot Skills

Authors:
Agapito Ledezma;Antonio Berlanga;Ricardo Aler
Affiliations:
-;-;-
Venue:
IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Connectionist Models of Neurons, Learning Processes and Artificial Intelligence-Part I
Year:
2001

Citing 11
Cited 2

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Instance-Based Learning Algorithms

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
C4.5: programs for machine learning

C4.5: programs for machine learning
The automatic generation of plans for a mobile robot via genetic programming with automatically defined functions

Advances in genetic programming
Challenges in coevolutionary learning: arms-race dynamics, open-endedness, and medicocre stable states

ALIFE Proceedings of the sixth international conference on Artificial life
Co-Evolution in the Successful Learning of Backgammon Strategy

Machine Learning
RTCS: a Reactive with Tags Classifier System

Journal of Intelligent and Robotic Systems
Induction of Decision Trees

Machine Learning
Statistical Reasoning Strategies in the Pursuit and Evasion Domain

ECAL '99 Proceedings of the 5th European Conference on Advances in Artificial Life
Generating Accurate Rule Sets Without Global Optimization

ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning

OMBO: An opponent modeling approach

AI Communications
Predicting opponent actions by observation

RoboCup 2004

Quantified Score

Hi-index	0.00

Visualization

Abstract

Evolutionary based learning systems have proven to be very powerful techniques for solving a wide range of tasks, from prediction to optimization. However, in some cases the learned concepts are unreadable for humans. This prevents a deep sematic analysis of what has been really learned by those systems. We present in this paper an alternative to obtain symbolic models from subsymbolic learning. In the first stage, a subsymbolic learning system is applied to a given task. Then, a symbolic classifier us used for automatically generating the symbolic counterpart of the subsymbolic model.We have tested this approach to obtain a symbolic model of a neural network. The neural network defines a simple controller of an autonomous robot. A competitive coevolutive method has been applied in order to learn the right weights of the neural network. The results show that the obtained symbolic model is very accurate in the task of modelling the subsymbolic system, adding to this its readability characteristic.