Measurement and the explanation of adaptive and novel behaviors in real and artificial creatures

Authors:
Tony Savage
Affiliations:
School of Psychology, The Queen's University of Belfast, Belfast BT7 1NN, Northern Ireland
Venue:
Cognitive Systems Research
Year:
2004

Citing 15
Cited 0

Intelligence without representation

Artificial Intelligence
Automatic programming of behavior-based robots using reinforcement learning

Artificial Intelligence
Using genetic algorithms to learn reactive control parameters for autonomous robotic navigation

Adaptive Behavior
Hierarchical mixtures of experts and the EM algorithm

Neural Computation
Achieving rapid adaptations in robots by means of external tuition

SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
An evaluation of Maes's bottom-up mechanism for behavior selection

Adaptive Behavior
Using emergent modularity to develop control systems for mobile robots

Adaptive Behavior - Special issue on environment structure and behavior
HQ-learning

Adaptive Behavior
Design, observation, surprise! A test of emergence

Artificial Life
Multi-agent reinforcement learning: weighting and partitioning

Neural Networks
Robot Shaping: An Experiment in Behavior Engineering

Robot Shaping: An Experiment in Behavior Engineering
Multiagent Mission Specification and Execution

Autonomous Robots
Sensory-motor primitives as a basis for imitation: linking perception to action and biology to robotics

Imitation in animals and artifacts
Coevolving Predator and Prey Robots: Do "Arms Races" Arise in Artificial Evolution?

Artificial Life
Integrating behavioral, perceptual, and world knowledge in reactive navigation

Robotics and Autonomous Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper looks at the applicability of animal shaping techniques to promoting novel behaviors in robots and artificial creatures. Shaping techniques have long been used by psychologists and animal trainers to train flexible forms of behavior and to generate novel or original behaviors in animals. This paper examines several issues relating to the part played by behavior description and measurement in promoting flexibility or behavioral novelty using these shaping techniques. The issues considered include (i) the kinds of behavior scales employed in training response variability and novel behaviors and (ii) the explanations from animal psychology of the characteristics of response flexibility and novel behavior. The paper concludes with a discussion of how an appreciation of behavioral scaling issues might benefit robotics research.