Publication detail

Continuous Q-learning application

VĚCHET, S. KREJSA, J.

Czech title

Praktická aplikace Q-učení

English title

Continuous Q-learning application

Type

conference paper

Language

en

Original abstract

Standard algorithm of Q-Learning is limited by discrete states and actions and Q-function is usually represented as discrete table. To avoid this obstacle and extend the use of Q-learning for continuous states and actions the algorithm must be modified and such modification is presented in the paper. Straightforward way is to replace discrete table with suitable approximator. A number of approximators can be used, with respect to memory and computational requirements the local approximator is particularly favorable. We have used Locally Weighted Regression (LWR) algorithm. The paper discusses advantages and disadvantages of modified algorithm demonstrated on simple control task.

Czech abstract

Standardní algoritmus metody Q-učení je omezen používáním diskrétních stavů a akcí. V tomto případě je Q-funkce representována jako diskrétní tabulka. Metoda popisovaná v tomto příspěvku se snaží obejít problém s diskretizací tím, že je od počátku navržena jako spojitá. Diskrétní tabulka Q-hodnot je nahrazena vhodným aproximátorem. V tomto příspěvku hodnotíme výhody a nevýhody spojitého Q-učení oproti jeho diskrétní variantě.

English abstract

Standard algorithm of Q-Learning is limited by discrete states and actions and Q-function is usually represented as discrete table. To avoid this obstacle and extend the use of Q-learning for continuous states and actions the algorithm must be modified and such modification is presented in the paper. Straightforward way is to replace discrete table with suitable approximator. A number of approximators can be used, with respect to memory and computational requirements the local approximator is particularly favorable. We have used Locally Weighted Regression (LWR) algorithm. The paper discusses advantages and disadvantages of modified algorithm demonstrated on simple control task.

Keywords in English

Q-learning, Machine learning, Locall approximators

RIV year

2004

Released

10.05.2004

Publisher

Institute of Thermonechanics Academy of Sciences of the Czech Republic, Prague 2004

Location

Prague

ISBN

80-85918-88-9

Book

Engineering Mechanics 2004

Edition number

1

Pages count

2

BIBTEX


@inproceedings{BUT14018,
  author="Stanislav {Věchet} and Jiří {Krejsa},
  title="Continuous Q-learning application",
  booktitle="Engineering Mechanics 2004",
  year="2004",
  month="May",
  publisher="Institute of Thermonechanics Academy of Sciences of the Czech Republic, Prague 2004",
  address="Prague",
  isbn="80-85918-88-9"
}