Continuous-action Q-learning

DOI10.1023/A:1017988514716zbMath1014.68073OpenAlexW1531900088MaRDI QIDQ1604822

José del R. Millán, Daniele Posenato, Eric Dedieu

Publication date: 8 July 2002

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1023/a:1017988514716

zbMATH Keywords

Q-learning method

Mathematics Subject Classification ID

Computational learning theory (68Q32)

Related Items (7)

Guiding exploration by pre-existing knowledge without modifying reward ⋮ Restricted gradient-descent algorithm for value-function approximation in reinforcement learning ⋮ Automatic generation of fuzzy inference systems via unsupervised learning ⋮ An Ensemble of Cooperative Extended Kohonen Maps for Complex Robot Motion Tasks ⋮ Adaptive stock trading with dynamic asset allocation using reinforcement learning ⋮ Accelerating autonomous learning by using heuristic selection of actions ⋮ Reinforcement distribution in fuzzy Q-learning

This page was built for publication: Continuous-action Q-learning