A competitive strategy for function approximation in Q-learning
Document typeConference report
Rights accessOpen Access
In this work we propose an approach for generalization in continuous domain Reinforcement Learning that, instead of using a single function approximator, tries many different function approximators in parallel, each one defined in a different region of the domain. Associated with each approximator is a relevance function that locally quantifies the quality of its approximation, so that, at each input point, the approximator with highest relevance can be selected. The relevance function is defined using parametric estimations of the variance of the q-values and the density of samples in the input space, which are used to quantify the accuracy and the confidence in the approximation, respectively. These parametric estimations are obtained from a probability density distribution represented as a Gaussian Mixture Model embedded in the input-output space of each approximator. In our experiments, the proposed approach required a lesser number of experiences for learning and produced more stable convergence profiles than when using a single function approximator.
Showing items related by title, author, creator and subject.
Parada, Natalia; Gutierrez, Angel (Active Learning for Engineering Education (ALE), 2009)
Open AccessStarting with our work on organizational redesign in different Colombian organizations, we have advanced in the concepts of Learning Communities, Shared and Permanent Learning, Flexible Organizational Structure, Participative ...
Learning theory through videos: a teaching experience in a theoretical course based on self-learning videos and problem-solving sessions Arias Vicente, Marta; Creus López, Carles; Gascón Caro, Adrià; Godoy Balil, Guillem (SciTePress, 2011)
Restricted access - publisher's policyIn this paper we describe a teaching experience applied to a theoretical course tought in a computer science degree. The main feature of our experiment is the introduction of videos specifically designed for self-learning ...
Online learning in ergonomics and occupational risk prevention: facing the urgency and diversification of a massive learning demand Talavera Pedrol, Núria (2011-04-18)
External research report