Adaptive Behavior, 3 (1)

Review of The Adapted Mind: Evolutionary Psychology and the Generation of Culture, edited by Jerome H. Barkow, Leda Cosmides & John Tooby. New York: Oxford University Press, 1992.

Recent Books of Interest

Pages 1-3

Editorial

By Lashon B. Booker

Pages 5-28

Learning and Evolution in Neural Networks

By Stefano Nolfi, Jeffrey L. Elman, Domenico Parisi

Abstract

This article describes simulations on populations of neural networks that both evolve at the population level and learn at the individual level. Unlike other simulations, the evolutionary task (finding food in the environment) and the learning task (predicting the next position of food on the basis of present position and planned network's movement) are different tasks. In these conditions, learning influences evolution (without Lamarckian inheritance of learned weight changes) and evolution influences learning. Average but not peak fitness has a better evolutionary growth with learning than without learning. After the initial generations, individuals that learn to predict during life also improve their food-finding ability during life. Furthermore, individuals that inherit an innate capacity to find food also inherit an innate predisposition to learn to predict the sensory consequences of their movements. They do not predict better at birth, but they do learn to predict better than individuals of the initial generation given the same learning experience. The results are interpreted in terms of a notion of dynamic correlation between the fitness surface and the learning surface. Evolution succeeds in finding both individuals that have high fitness and individuals that, although they do not have high fitness at birth, end up with high fitness because they learn to predict.

Key Words

learning; evolution; neural networks; artificial life

Pages 29-49

Learning to Control Dynamic Systems with Automatic Quantization

By Charles X. Ling and Ralph Buchal

Abstract

Learning to control dynamic systems with unknown models is a challenging research problem. However, most previous work that learns qualitative control rules does not construct qualitative states; a proper partition of continuous-state variables has to be designed by human users and given to the learning programs. We design a new learning method that learns appropriate qualitative state representation and the control rules simultaneously. Our method can aggressively partition the continuous-state variables into finer, discrete ranges until control rules based on these ranges are learned. As a case study, we apply our method to the benchmark control problem of cart-pole balancing (also known as the inverted pendulum). Experimental results show that our method not only derives different partitions for the cart-pole systems with different parameters but also learns to control the systems for an extended period of time from random initial positions.

Key Words

adaptive control; reinforcement learning; automatic quantization

Pages 51-79

An Ethological Model for Implementation in Mobile Robots

By Bridget E. Hallam, Janet R. P. Halperin, John C. T. Hallam

Abstract

This article describes a neuroethological model of learning and motivation that accounts for many of the behavioral phenomena observed in animals. Unusual predictions from the model have been tested and shown to be demonstrable in laboratory Siamese fighting fish. In addition, the model is sufficiently mathematically well defined to be implementable in a robot or in computer simulation. A trial implementation in a mobile robot was carried out as part of this work. This article describes a simplified version of the model that was programmed into the robot, a thought experiment designed to show the main features of the model, and the preliminary robot experiments that were carried out. Using robots for ethological models of animal behavior is interesting for both robotics and ethological research: The study of robot autonomy can be enhanced through an understanding of complex and realistic models of animal autonomy, and ethological research should benefit from a supply of guaranteed "naive" agents on which rigorous testing of such models is tractable.

Key Words

learning; mobile robot; behavioral model

Page 81

Introduction to New Section: Reviews and announcements of books of interest

By Peter M. Todd

Pages 83-95

A Bottom-up Approach with a Clear View of the Top: How Human Evolutionary Psychology Can Inform Adaptive Behavior Research

By Geoffrey F. Miller and Peter M. Todd

Review of The Adapted Mind: Evolutionary Psychology and the Generation of Culture, edited by Jerome H. Barkow, Leda Cosmides & John Tooby. New York: Oxford University Press, 1992.

Pages 97-100

Recent Books of Interest

back to TOC, back to top

Adaptive Behavior, 3 (1)

Adaptive Behavior

Volume 3, Number 1

Summer 1994

Table of Contents

Lashon B. Booker

Editorial

Stefano Nolfi, Jeffrey L. Elman, and Domenico Parisi

Learning and Evolution in Neural Networks