Improvement of Particle Filter for Reinforcement Learning

In this paper, we propose a novel framework of learning that uses a particle filter. In a real-world situation, it is difficult to express a continuous state and a continuous action. The problem is solved by using our particle filter, which is one of the methods for dividing a continuous state and a...

Full description

Saved in:
Bibliographic Details
Published in2011 10th International Conference on Machine Learning and Applications and Workshops Vol. 1; pp. 454 - 457
Main Authors Notsu, A., Honda, K., Ichihashi, H., Komori, Y., Iwamoto, Y.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2011
Subjects
Equations
Learning
Mathematical model
Memory management
Particle filters
Particle-Filter
Reinforcement Learning
Robots
Space Segmentation
Torque
Online AccessGet full text

Cover

More Information
Summary:In this paper, we propose a novel framework of learning that uses a particle filter. In a real-world situation, it is difficult to express a continuous state and a continuous action. The problem is solved by using our particle filter, which is one of the methods for dividing a continuous state and a continuous action. Our method needs only a small number of memories and parameters for searching the solution in the space. We conducted pendulum and double-pendulum simulations and observed the difference between the conventional method and the proposed method. Simulation results show there was no bad effect on the received reward.
ISBN:9781457721342
1457721341
DOI:10.1109/ICMLA.2011.75