Perceptrons: expanded edition
Technical Note: \cal Q-Learning
Machine Learning
Computational models of classical conditioning: a comparative study
Proceedings of the fifth international conference on simulation of adaptive behavior on From animals to animats 5
Fundamentals of Artificial Neural Networks
Fundamentals of Artificial Neural Networks
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
An Integrative Modelling Approach for Simulation and Analysis of Adaptive Agents
ANSS '06 Proceedings of the 39th annual Symposium on Simulation
A Computational Model of the Amygdala Nuclei's Role in Second Order Conditioning
SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Relating Cognitive Process Models to Behavioural Models of Agents
WI-IAT '08 Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 02
Anticipatory Behavior in Adaptive Learning Systems
Formalisation and analysis of the temporal dynamics of conditioning
AOSE'05 Proceedings of the 6th international conference on Agent-Oriented Software Engineering
| Hi-index | 0.00 |
Classical conditioning is a basic learning mechanism inanimals and can be found in almost all organisms. If we want toconstruct robots with abilities matching those of their biologicalcounterparts, this is one of the learning mechanisms that needs to beimplemented first. This article describes a computational model ofclassical conditioning where the goal of learning is assumed to be theprediction of a temporally discounted reward or punishment based onthe current stimulus situation.The model is well suited for robotic implementation as it models anumber of classical conditioning paradigms and learning in the modelis guaranteed to converge with arbitrarily complex stimulus sequences.This is an essential feature once the step is taken beyond the simplelaboratory experiment with two or three stimuli to the real worldwhere no such limitations exist. It is also demonstrated how the modelcan be included in a more complex system that includes various formsof sensory pre-processing and how it can handle reinforcementlearning, timing of responses and function as an adaptive world model.