Reinforcement Learning for Continuous Stochastic Actions--An Approximation of Probability Density Function by Orthogonal Wave Function Expansion--

Hideki SATOH

doi:10.1093/ietfec/e89-a.8.2173

Reinforcement Learning for Continuous Stochastic Actions--An Approximation of Probability Density Function by Orthogonal Wave Function Expansion--

Hideki SATOH

Full Text Views

0

Share
Cite this

Summary :

A function approximation based on an orthonormal wave function expansion in a complex space is derived. Although a probability density function (PDF) cannot always be expanded in an orthogonal series in a real space because a PDF is a positive real function, the function approximation can approximate an arbitrary PDF with high accuracy. It is applied to an actor-critic method of reinforcement learning to derive an optimal policy expressed by an arbitrary PDF in a continuous-action continuous-state environment. A chaos control problem and a PDF approximation problem are solved using the actor-critic method with the function approximation, and it is shown that the function approximation can approximate a PDF well and that the actor-critic method with the function approximation exhibits high performance.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E89-A No.8 pp.2173-2180

Publication Date: 2006/08/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1093/ietfec/e89-a.8.2173

Type of Manuscript: PAPER

Category: Nonlinear Problems

Cite this

Copy

Hideki SATOH, "Reinforcement Learning for Continuous Stochastic Actions--An Approximation of Probability Density Function by Orthogonal Wave Function Expansion--" in IEICE TRANSACTIONS on Fundamentals, vol. E89-A, no. 8, pp. 2173-2180, August 2006, doi: 10.1093/ietfec/e89-a.8.2173.
Abstract: A function approximation based on an orthonormal wave function expansion in a complex space is derived. Although a probability density function (PDF) cannot always be expanded in an orthogonal series in a real space because a PDF is a positive real function, the function approximation can approximate an arbitrary PDF with high accuracy. It is applied to an actor-critic method of reinforcement learning to derive an optimal policy expressed by an arbitrary PDF in a continuous-action continuous-state environment. A chaos control problem and a PDF approximation problem are solved using the actor-critic method with the function approximation, and it is shown that the function approximation can approximate a PDF well and that the actor-critic method with the function approximation exhibits high performance.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e89-a.8.2173/_p

Copy

@ARTICLE{e89-a_8_2173,
author={Hideki SATOH, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Reinforcement Learning for Continuous Stochastic Actions--An Approximation of Probability Density Function by Orthogonal Wave Function Expansion--},
year={2006},
volume={E89-A},
number={8},
pages={2173-2180},
abstract={A function approximation based on an orthonormal wave function expansion in a complex space is derived. Although a probability density function (PDF) cannot always be expanded in an orthogonal series in a real space because a PDF is a positive real function, the function approximation can approximate an arbitrary PDF with high accuracy. It is applied to an actor-critic method of reinforcement learning to derive an optimal policy expressed by an arbitrary PDF in a continuous-action continuous-state environment. A chaos control problem and a PDF approximation problem are solved using the actor-critic method with the function approximation, and it is shown that the function approximation can approximate a PDF well and that the actor-critic method with the function approximation exhibits high performance.},
keywords={},
doi={10.1093/ietfec/e89-a.8.2173},
ISSN={1745-1337},
month={August},}

Copy

TY - JOUR
TI - Reinforcement Learning for Continuous Stochastic Actions--An Approximation of Probability Density Function by Orthogonal Wave Function Expansion--
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2173
EP - 2180
AU - Hideki SATOH
PY - 2006
DO - 10.1093/ietfec/e89-a.8.2173
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E89-A
IS - 8
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - August 2006
AB - A function approximation based on an orthonormal wave function expansion in a complex space is derived. Although a probability density function (PDF) cannot always be expanded in an orthogonal series in a real space because a PDF is a positive real function, the function approximation can approximate an arbitrary PDF with high accuracy. It is applied to an actor-critic method of reinforcement learning to derive an optimal policy expressed by an arbitrary PDF in a continuous-action continuous-state environment. A chaos control problem and a PDF approximation problem are solved using the actor-critic method with the function approximation, and it is shown that the function approximation can approximate a PDF well and that the actor-critic method with the function approximation exhibits high performance.
ER -