Proxy Functions for Approximate Reinforcement Learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00337291" target="_blank" >RIV/68407700:21230/19:00337291 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/19:00337291

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S240589631930775X" target="_blank" >https://www.sciencedirect.com/science/article/pii/S240589631930775X</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.ifacol.2019.09.145" target="_blank" >10.1016/j.ifacol.2019.09.145</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Proxy Functions for Approximate Reinforcement Learning

Popis výsledku v původním jazyce

Approximate Reinforcement Learning (RL) is a method to solve sequential decisionmaking and dynamic control problems in an optimal way. This paper addresses RL for continuous state spaces which derive the control policy by using an approximate value function (V-function). The standard approach to derive a policy through the V-function is analogous to hill climbing: at each state the RL agent chooses the control input that maximizes the right-hand side of the Bellman equation. Although theoretically optimal, the actual control performance of this method is heavily influenced by the local smoothness of the V-function; a lack of smoothness results in undesired closed-loop behavior with input chattering or limit-cycles. To circumvent these problems, this paper provides a method based on Symbolic Regression to generate a locally smooth proxy to the V-function. The proposed method has been evaluated on two nonlinear control benchmarks: pendulum swing-up and magnetic manipulation. The new method has been compared with the standard policy derivation technique using the approximate V-function and the results show that the proposed approach outperforms the standard one with respect to the cumulative return.

Název v anglickém jazyce

Proxy Functions for Approximate Reinforcement Learning

Popis výsledku anglicky

Approximate Reinforcement Learning (RL) is a method to solve sequential decisionmaking and dynamic control problems in an optimal way. This paper addresses RL for continuous state spaces which derive the control policy by using an approximate value function (V-function). The standard approach to derive a policy through the V-function is analogous to hill climbing: at each state the RL agent chooses the control input that maximizes the right-hand side of the Bellman equation. Although theoretically optimal, the actual control performance of this method is heavily influenced by the local smoothness of the V-function; a lack of smoothness results in undesired closed-loop behavior with input chattering or limit-cycles. To circumvent these problems, this paper provides a method based on Symbolic Regression to generate a locally smooth proxy to the V-function. The proposed method has been evaluated on two nonlinear control benchmarks: pendulum swing-up and magnetic manipulation. The new method has been compared with the standard policy derivation technique using the approximate V-function and the results show that the proposed approach outperforms the standard one with respect to the cumulative return.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20204 - Robotics and automatic control

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

IFAC-PapersOnLine - 5th IFAC Conference on Intelligent Control and Automation Sciences ICONS 2019

ISBN

—

ISSN

2405-8963

e-ISSN

2405-8963

Počet stran výsledku

6

Strana od-do

224-229

Název nakladatele

Elsevier

Místo vydání

Lausanne

Místo konání akce

Belfast

Datum konání akce

21. 8. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000493064700039