Data-driven Construction of Symbolic Process Models for Reinforcement Learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F18%3A00324236" target="_blank" >RIV/68407700:21230/18:00324236 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/18:00324236

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ICRA.2018.8461182" target="_blank" >http://dx.doi.org/10.1109/ICRA.2018.8461182</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICRA.2018.8461182" target="_blank" >10.1109/ICRA.2018.8461182</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Data-driven Construction of Symbolic Process Models for Reinforcement Learning

Popis výsledku v původním jazyce

Reinforcement learning (RL) is a suitable approach for controlling systems with unknown or time-varying dynamics. RL in principle does not require a model of the system, but before it learns an acceptable policy, it needs many unsuccessful trials, which real robots usually cannot withstand. It is well known that RL can be sped up and made safer by using models learned online. In this paper, we propose to use symbolic regression to construct compact, parsimonious models described by analytic equations, which are suitable for real-time robot control. Single node genetic programming (SNGP) is employed as a tool to automatically search for equations fitting the available data. We demonstrate the approach on two benchmark examples: a simulated mobile robot and the pendulum swing-up problem; the latter both in simulations and real-time experiments. The results show that through this approach we can find accurate models even for small batches of training data. Based on the symbolic model found, RL can control the system well.

Název v anglickém jazyce

Data-driven Construction of Symbolic Process Models for Reinforcement Learning

Popis výsledku anglicky

Reinforcement learning (RL) is a suitable approach for controlling systems with unknown or time-varying dynamics. RL in principle does not require a model of the system, but before it learns an acceptable policy, it needs many unsuccessful trials, which real robots usually cannot withstand. It is well known that RL can be sped up and made safer by using models learned online. In this paper, we propose to use symbolic regression to construct compact, parsimonious models described by analytic equations, which are suitable for real-time robot control. Single node genetic programming (SNGP) is employed as a tool to automatically search for equations fitting the available data. We demonstrate the approach on two benchmark examples: a simulated mobile robot and the pendulum swing-up problem; the latter both in simulations and real-time experiments. The results show that through this approach we can find accurate models even for small batches of training data. Based on the symbolic model found, RL can control the system well.

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)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 2018 IEEE International Conference on Robotics and Automation

ISBN

978-1-5386-3081-5

ISSN

1050-4729

e-ISSN

—

Počet stran výsledku

8

Strana od-do

5105-5112

Název nakladatele

IEEE

Místo vydání

Piscataway, NJ

Místo konání akce

Brisbane

Datum konání akce

21. 5. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000446394503126