TD(0) converges provably faster than the residual gradient algorithm
Year: 2003
Type: conference-paper
Authors: Ralf Schoknecht, Artur Merke
Institutions: Karlsruhe Institute of Technology, TU Dortmund University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: closed
OpenAlex ID: W2170902787
