Similarity-based transfer learning of decision policies

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F20%3A00534000" target="_blank" >RIV/67985556:_____/20:00534000 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/SMC42975.2020.9283093" target="_blank" >http://dx.doi.org/10.1109/SMC42975.2020.9283093</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/SMC42975.2020.9283093" target="_blank" >10.1109/SMC42975.2020.9283093</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Similarity-based transfer learning of decision policies

Popis výsledku v původním jazyce

We consider a problem of learning decision policy from past experience available. Using the Fully Probabilistic Design (FPD) formalism, we propose a new general approach for finding a stochastic policy from the past data. The proposedapproach assigns degree of similarity to all of the past closed-loop behaviors. The degree of similarity expresses how close the current decision making task is to a past task. Then it is used by Bayesian estimation to learn an approximate optimal policy, which comprises the best past experience. The approach learns decision policy directly from the data without interacting with any supervisor/expert or using any reinforcement signal. The past experience may consider a decision objective different than the current one. Moreover the past decision policy need not to be optimal with respect to the past objective. We demonstrate our approach on simulated examples and show that the learned policy achieves better performance than optimal FPD policy whenever a mismodeling is present.

Název v anglickém jazyce

Similarity-based transfer learning of decision policies

Popis výsledku anglicky

We consider a problem of learning decision policy from past experience available. Using the Fully Probabilistic Design (FPD) formalism, we propose a new general approach for finding a stochastic policy from the past data. The proposedapproach assigns degree of similarity to all of the past closed-loop behaviors. The degree of similarity expresses how close the current decision making task is to a past task. Then it is used by Bayesian estimation to learn an approximate optimal policy, which comprises the best past experience. The approach learns decision policy directly from the data without interacting with any supervisor/expert or using any reinforcement signal. The past experience may consider a decision objective different than the current one. Moreover the past decision policy need not to be optimal with respect to the past objective. We demonstrate our approach on simulated examples and show that the learned policy achieves better performance than optimal FPD policy whenever a mismodeling is present.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10103 - Statistics and probability

Projekt

<a href="/cs/project/LTC18075" target="_blank" >LTC18075: Distribuované racionální rozhodování: kooperační aspekty</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS 2020

ISBN

978-1-7281-8527-9

ISSN

1062-922X

e-ISSN

—

Počet stran výsledku

8

Strana od-do

37-44

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Toronto

Datum konání akce

11. 10. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—