The kNN-TD Reinforcement Learning Algorithm

Authors:
José Antonio Martín H.;Javier Lope;Darío Maravall
Affiliations:
Dep. Sistemas Informáticos y Computación, Universidad Complutense de Madrid,;Perception for Computers and Robots, Universidad Politécnica de Madrid,;Perception for Computers and Robots, Universidad Politécnica de Madrid,
Venue:
IWINAC '09 Proceedings of the 3rd International Work-Conference on The Interplay Between Natural and Artificial Computation: Part I: Methods and Models in Artificial and Natural Computation. A Homage to Professor Mira's Scientific Legacy
Year:
2009

Citing 6
Cited 2

Technical Note: \cal Q-Learning

Machine Learning
Reinforcement learning with replacing eligibility traces

Machine Learning - Special issue on reinforcement learning
Locally Weighted Learning

Artificial Intelligence Review - Special issue on lazy learning
Approximate nearest neighbors: towards removing the curse of dimensionality

STOC '98 Proceedings of the thirtieth annual ACM symposium on Theory of computing
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
A k-NN based perception scheme for reinforcement learning

EUROCAST'07 Proceedings of the 11th international conference on Computer aided systems theory

Robust high performance reinforcement learning through weighted k-nearest neighbors

Neurocomputing
A novel modular Q-learning architecture to improve performance under incomplete learning in a grid soccer game

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

A reinforcement learning algorithm called k NN-TD is introduced. This algorithm has been developed using the classical formulation of temporal difference methods and a k -nearest neighbors scheme as its expectations memory. By means of this kind of memory the algorithm is able to generalize properly over continuous state spaces and also take benefits from collective action selection and learning processes. Furthermore, with the addition of probability traces, we obtain the k NN-TD(*** ) algorithm which exhibits a state of the art performance. Finally the proposed algorithm has been tested on a series of well known reinforcement learning problems and also at the Second Annual RL Competition with excellent results.