Neural Networks for Model-free and Scale-free Automated Planning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00354896" target="_blank" >RIV/68407700:21230/21:00354896 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/s10115-021-01619-8" target="_blank" >https://doi.org/10.1007/s10115-021-01619-8</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s10115-021-01619-8" target="_blank" >10.1007/s10115-021-01619-8</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Neural Networks for Model-free and Scale-free Automated Planning

Popis výsledku v původním jazyce

Automated planning for problems without an explicit model is an elusive research challenge. However, if tackled, it could provide a general approach to problems in real-world unstructured environments. There are currently two strong research directions in the area of artificial intelligence (AI), namely machine learning and symbolic AI. The former provides techniques to learn models of unstructured data but does not provide further problem solving capabilities on such models. The latter provides efficient algorithms for general problem solving, but requires a model to work with. Creating the model can itself be a bottleneck of many problem domains. Complicated problems require an explicit description that can be very costly or even impossible to create. In this paper, we propose a combination of the two areas, namely deep learning and classical planning, to form a planning system that works without a human-encoded model for variably scaled problems. The deep learning part extracts the model in the form of a transition system and a goal-distance heuristic estimator; the classical planning part uses such a model to efficiently solve the planning problem. Both networks in the planning system, we introduced, work with a problem in its graphic form and there is no need for any additional information to create the state transition system or to estimate a heuristic value. We proposed three different architectures for the heuristic estimator to compare different characteristics of well-known deep learning techniques. Besides the design of such planning systems, we provide experimental evaluation comparing the implemented techniques to classical model-based methods.

Název v anglickém jazyce

Neural Networks for Model-free and Scale-free Automated Planning

Popis výsledku anglicky

Automated planning for problems without an explicit model is an elusive research challenge. However, if tackled, it could provide a general approach to problems in real-world unstructured environments. There are currently two strong research directions in the area of artificial intelligence (AI), namely machine learning and symbolic AI. The former provides techniques to learn models of unstructured data but does not provide further problem solving capabilities on such models. The latter provides efficient algorithms for general problem solving, but requires a model to work with. Creating the model can itself be a bottleneck of many problem domains. Complicated problems require an explicit description that can be very costly or even impossible to create. In this paper, we propose a combination of the two areas, namely deep learning and classical planning, to form a planning system that works without a human-encoded model for variably scaled problems. The deep learning part extracts the model in the form of a transition system and a goal-distance heuristic estimator; the classical planning part uses such a model to efficiently solve the planning problem. Both networks in the planning system, we introduced, work with a problem in its graphic form and there is no need for any additional information to create the state transition system or to estimate a heuristic value. We proposed three different architectures for the heuristic estimator to compare different characteristics of well-known deep learning techniques. Besides the design of such planning systems, we provide experimental evaluation comparing the implemented techniques to classical model-based methods.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GJ18-24965Y" target="_blank" >GJ18-24965Y: Multi-agentní plánování s ochranou soukromých informací</a><br>

Návaznosti

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

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název periodika

Knowledge and Information Systems

ISSN

0219-1377

e-ISSN

0219-3116

Svazek periodika

63

Číslo periodika v rámci svazku

12

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

36

Strana od-do

3103-3138

Kód UT WoS článku

000713906900001

EID výsledku v databázi Scopus

2-s2.0-85118454002