Reinforcement distribution in continuous state action space fuzzy Q–learning: a novel approach

Authors:
Andrea Bonarini;Francesco Montrone;Marcello Restelli
Affiliations:
Politecnico di Milano Electronic and Information Department, Milan, Italy;Politecnico di Milano Electronic and Information Department, Milan, Italy;Politecnico di Milano Electronic and Information Department, Milan, Italy
Venue:
WILF'05 Proceedings of the 6th international conference on Fuzzy Logic and Applications
Year:
2005

Citing 3
Cited 1

Technical Note: \cal Q-Learning

Machine Learning
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
An approach to the design of reinforcement functions in real world,agent-based applications

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Multi-level cognitive machine-learning based concept for human-like "artificial" walking: Application to autonomous stroll of humanoid robots

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Fuzzy Q–learning extends the Q–learning algorithm to work in presence of continuous state and action spaces. A Takagi–Sugeno Fuzzy Inference System (FIS) is used to infer the continuous executed action and its action–value, by means of cooperation of several rules. Different kinds of evolution of the parameters of the FIS are possible, depending on different strategies of distribution of the reinforcement signal. In this paper, we compare two strategies: the classical one, focusing on rewarding the rules that have proposed the actions composed to produce the actual action, and a new one we are introducing, where reward goes to the rules proposing actions closest the ones actually executed.