loading
Documents

Research.Publish.Connect.

Paper

Authors: Johannes Nauta ; Yara Khaluf and Pieter Simoens

Affiliation: Department of Information Technology, Ghent University, Ghent and Belgium

ISBN: 978-989-758-366-7

Keyword(s): Brownian Motion, Exploration, Ornstein-Uhlenbeck Process.

Abstract: In model-based Reinforcement Learning, an agent aims to learn a transition model between attainable states. Since the agent initially has zero knowledge of the transition model, it needs to resort to random exploration in order to learn the model. In this work, we demonstrate how the Ornstein-Uhlenbeck process can be used as a sampling scheme to generate exploratory Brownian motion in the absence of a transition model. Whereas current approaches rely on knowledge of the transition model to generate the steps of Brownian motion, the Ornstein-Uhlenbeck process does not. Additionally, the Ornstein-Uhlenbeck process naturally includes a drift term originating from a potential function. We show that this potential can be controlled by the agent itself, and allows executing non-equilibrium behavior such as ballistic motion or local trapping.

PDF ImageFull Text

Download
Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.242.193.41

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Nauta, J.; Khaluf, Y. and Simoens, P. (2019). Using the Ornstein-Uhlenbeck Process for Random Exploration.In Proceedings of the 4th International Conference on Complexity, Future Information Systems and Risk - Volume 1: COMPLEXIS, ISBN 978-989-758-366-7, pages 59-66. DOI: 10.5220/0007724500590066

@conference{complexis19,
author={Johannes Nauta. and Yara Khaluf. and Pieter Simoens.},
title={Using the Ornstein-Uhlenbeck Process for Random Exploration},
booktitle={Proceedings of the 4th International Conference on Complexity, Future Information Systems and Risk - Volume 1: COMPLEXIS,},
year={2019},
pages={59-66},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007724500590066},
isbn={978-989-758-366-7},
}

TY - CONF

JO - Proceedings of the 4th International Conference on Complexity, Future Information Systems and Risk - Volume 1: COMPLEXIS,
TI - Using the Ornstein-Uhlenbeck Process for Random Exploration
SN - 978-989-758-366-7
AU - Nauta, J.
AU - Khaluf, Y.
AU - Simoens, P.
PY - 2019
SP - 59
EP - 66
DO - 10.5220/0007724500590066

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.