From Animals to Animats 3

by Cliff, Dave; Husbands, Philip; Meyer, Jean-Arcady; Wilson, Stewart

• ISBN13: 9780262531221
• ISBN10: 0262531224
• Format: Paperback
• Copyright: 1994-07-27
• Publisher: Bradford Books

Summary

August 8-12, 1994, Brighton, England From Animals to Animats 3brings together research intended to advance the frontier of an exciting new approach to understanding intelligence. The contributors represent a broad range of interests from artificial intelligence and robotics to ethology and the neurosciences. Unifying these approaches is the notion of "animat" - an artificial animal, either simulated by a computer or embodied in a robot, which must survive and adapt in progressively more challenging environments. The 58 contributions focus particularly on well-defined models, computer simulations, and built robots in order to help characterize and compare various principles and architectures capable of inducing adaptive behavior in real or artificial animals. Topics include: - Individual and collective behavior. - Neural correlates of behavior. - Perception and motor control. - Motivation and emotion. - Action selection and behavioral sequences. - Ontogeny, learning, and evolution. - Internal world models and cognitive processes. - Applied adaptive behavior. - Autonomous robots. - Heirarchical and parallel organizations. - Emergent structures and behaviors. - Problem solving and planning. - Goal-directed behavior. - Neural networks and evolutionary computation. - Characterization of environments. A Bradford Book

Table of Contents

From SAB90 to SAB94: Four Years of Animal Research	p. 2
Mechanism and Process in Animal Behavior: Models of Animals, Animals as Models	p. 12
Coherent Behavior from Many Adaptive Processes	p. 22
Stability in Adaptation and Learning	p. 30
Modeling the Role of Cerebellum in Prism Adaptation	p. 36
Robotic Experiments in Cricket Phonotaxis	p. 45
How to Watch Your Step: Biological Evidence and an Initial Model	p. 55
On Why Better Robots Make It Harder	p. 64
Insect Vision and Olfaction: Different Neural Architectures for Different Kinds of Sensory Signal?	p. 73
The Interval Reduction Strategy for Monitoring Cupcake Problems	p. 82
Visual Control of Altitude and Speed in a Flying Agent	p. 91
What Is Cognitive and What Is Not Cognitive?	p. 102
Action-Selection in Hamsterdam: Lessons from Ethology	p. 108
Behavioral Dynamics of Escape and Avoidance: A Neural Network Approach	p. 118
Organizing an Animal's Behavioural Repertoires Using Kohonen Feature Maps	p. 128
Action Selection for Robots in Dynamic Environments through Inter-Behaviour Bidding	p. 138
An Hierarchical Classifier System Implementing a Motivationally Autonomous Animat	p. 144
Using Second Order Neural Connections for Motivation of Behavioral Choices	p. 154
Spatial Learning and Representation in Animats	p. 164
Location Recognition in Rats and Robots	p. 174
Emergent Functionality in Human Infants	p. 179
Connectionist Environment Modelling in a Real Robot	p. 189
A Hybrid Architecture for Learning Continuous Environmental Models in Maze Problems	p. 198
A Place Navigation Algorithm Based on Elementary Computing Procedures and Associative Memories	p. 206
Self-Organizing Topographic Maps and Motor Planning	p. 214
The Effect of Memory Length on the Foraging Behavior of a Lizard	p. 221
The Blind Breeding the Blind: Adaptive Behavior without Looking	p. 228
Memoryless Policies: Theoretical Limitations and Practical Results	p. 238
A Comparison of Q-Learning and Classifier Systems	p. 248
Paying Attention to What's Important: Using Focus of Attention to Improve Unsupervised Learning	p. 256
Learning Efficient Reactive Behavioral Sequences from Basic Reflexes in a Goal-Directed Autonomous Robot	p. 266
The Importance of Leaky Levels for Behavior-Based AI	p. 275
A Topological Neural Map for On-Line Learning: Emergence of Obstacle Avoidance in a Mobile Robot	p. 282
Reinforcement Tuning of Action Synthesis and Selection in a 'Virtual Frog'	p. 291
Achieving Rapid Adaptations in Robots by Means of External Tuition	p. 301
Two-Link-Robot Brachiation with Connectionist Q-Learning	p. 309
An Architecture for Learning to Behave	p. 315
Reinforcement Learning for Homeostatic Endogenous Variables	p. 325
An Architecture for Representing and Learning Behaviors by Trial and Error	p. 334
A Distributed Adaptive Control System for a Quadruped Mobile Robot	p. 344
Reinforcement Learning with Dynamic Covering of State-Action Space: Partitioning Q-Learning	p. 354
The Five Neuron Trick: Using Classical Conditioning to Learn How to Seek Light	p. 364
Adaptation in Dynamic Environments through a Minimal Probability of Exploration	p. 371
Integrating Reactive, Sequential, and Learning Behavior Using Dynamical Neural Networks	p. 382
Seeing the Light: Artificial Evolution, Real Vision	p. 392
Evolution of Corridor Following Behavior in a Noisy World	p. 402
Protean Behavior in Dynamic Games: Arguments for the Co-Evolution of Pursuit-Evasion Tactics	p. 411
Automatic Creation of an Autonomous Agent: Genetic Evolution of a Neural-Network Driven Robot	p. 421
The Effect of Parasitism on the Evolution of a Communication Protocol in an Artificial Life Simulation	p. 431
Towards Robot Cooperation	p. 440
A Case Study in the Behavior-Oriented Design of Autonomous Agents	p. 445
Learning to Behave Socially	p. 453
Signalling and Territorial Aggression: An Investigation by Means of Synthetic Behavioral Ecology	p. 463
Integration of Reactive and Telerobotic Control in Multi-Agent Robotic Systems	p. 473
MINIMEME: Of Life and Death in the Noosphere	p. 479
Learning Coordinated Motions in a Competition for Food between Ant Colonies	p. 487
Emergent Colonization and Graph Partitioning	p. 494
Diversity and Adaptation in Populations of Clustering Ants	p. 501
Author Index	p. 509
Table of Contents provided by Blackwell. All Rights Reserved.