Actor-Critic Off-Policy Learning for Optimal Control of Multiple-Model Discrete-Time Systems

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F18%3A43949872" target="_blank" >RIV/49777513:23520/18:43949872 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/TCYB.2016.2618926" target="_blank" >http://dx.doi.org/10.1109/TCYB.2016.2618926</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TCYB.2016.2618926" target="_blank" >10.1109/TCYB.2016.2618926</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Actor-Critic Off-Policy Learning for Optimal Control of Multiple-Model Discrete-Time Systems

Popis výsledku v původním jazyce

In this paper, motivated by human neurocognitive experiments, a model-free off-policy reinforcement learning algorithm is developed to solve the optimal tracking control of multiple-model linear discrete-time systems. First, an adaptive self-organizing map neural network is used to determine the system behavior from measured data and to assign a responsibility signal to each of system possible behaviors. A new model is added if a sudden change of system behavior is detected from the measured data and the behavior has not been previously detected. A value function is represented by partially weighted value functions. Then, the off-policy iteration algorithm is generalized to multiple-model learning to find a solution without any knowledge about the system dynamics or reference trajectory dynamics. The off-policy approach helps to increase data efficiency and speed of tuning since a stream of experiences obtained from executing a behavior policy is reused to update several value functions corresponding to different learning policies sequentially. Two numerical examples serve as a demonstration of the off-policy algorithm performance.

Název v anglickém jazyce

Actor-Critic Off-Policy Learning for Optimal Control of Multiple-Model Discrete-Time Systems

Popis výsledku anglicky

In this paper, motivated by human neurocognitive experiments, a model-free off-policy reinforcement learning algorithm is developed to solve the optimal tracking control of multiple-model linear discrete-time systems. First, an adaptive self-organizing map neural network is used to determine the system behavior from measured data and to assign a responsibility signal to each of system possible behaviors. A new model is added if a sudden change of system behavior is detected from the measured data and the behavior has not been previously detected. A value function is represented by partially weighted value functions. Then, the off-policy iteration algorithm is generalized to multiple-model learning to find a solution without any knowledge about the system dynamics or reference trajectory dynamics. The off-policy approach helps to increase data efficiency and speed of tuning since a stream of experiences obtained from executing a behavior policy is reused to update several value functions corresponding to different learning policies sequentially. Two numerical examples serve as a demonstration of the off-policy algorithm performance.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

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

2018

Kód důvěrnosti údajů

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

Název periodika

IEEE Transactions on Cybernetics

ISSN

2168-2267

e-ISSN

—

Svazek periodika

48

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

12

Strana od-do

29-40

Kód UT WoS článku

000418291400003

EID výsledku v databázi Scopus

2-s2.0-84994252445