Publication

Reinforcement learning for robot control using probability density estimations

Conference Article

Conference

International Conference on Informatics in Control, Automation and Robotics (ICINCO)

Edition

7th

Pages

160-168

Doc link

http://www.icinco.org/Abstracts/2010/ICINCO_2010_Abstracts.htm

File

Download the digital copy of the doc pdf document

Abstract

The successful application of Reinforcement Learning (RL) techniques to robot control is limited by the fact that, in most robotic tasks, the state and action spaces are continuous, multidimensional, and in essence, too large for conventional RL algorithms to work. The well known curse of dimensionality makes infeasible using a tabular representation of the value function, which is the classical approach that provides convergence guarantees. When a function approximation technique is used to generalize among similar states, the convergence of the algorithm is compromised, since updates unavoidably affect an extended region of the domain, that is, some situations are modified in a way that has not been really experienced, and the update may degrade the approximation. We propose a RL algorithm that uses a probability density estimation in the joint space of states, actions and Q-values as a means of function approximation. This allows us to devise an updating approach that, taking into account the local sampling density, avoids an excessive modification of the approximation far from the observed sample.

Categories

generalisation (artificial intelligence), intelligent robots, learning (artificial intelligence).

Scientific reference

A. Agostini and E. Celaya. Reinforcement learning for robot control using probability density estimations, 7th International Conference on Informatics in Control, Automation and Robotics, 2010, Funchal, Madeira, pp. 160-168, INSTICC.