Number of the records: 1
Q-learning: from discrete to continuous representation
- 1.
SYSNO ASEP 0103681 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Ostatní články Title Q-learning: from discrete to continuous representation Title Q-učení: z diskrétní do spojité reprezentace Author(s) Věchet, S. (CZ)
Krejsa, Jiří (UT-L) RID, ORCIDSource Title Elektronika - ISSN 0033-2089
Roč. 2004, 8-9 (2004), s. 12-14Number of pages 3 s. Action Mechatronics 2004 Event date 23.09.2004-25.09.2004 VEvent location Warsaw Country PL - Poland Event type WRD Language eng - English Country PL - Poland Keywords Q-learning ; control Subject RIV BC - Control Systems Theory CEZ AV0Z2076919 - UT-L Annotation Q-learning standard algorithm is restricted by using discrete states and actions. Problems with continuous variables can be avoided if the continuous algorithm of Q-learning is used. In this paper we discus method, which is used to convert discrete to continuous algorithm. The method used suitable approximator to replace the discrete table. Workplace Institute of Thermomechanics Contact Marie Kajprová, kajprova@it.cas.cz, Tel.: 266 053 154 ; Jana Lahovská, jaja@it.cas.cz, Tel.: 266 053 823 Year of Publishing 2005
Number of the records: 1