MetaCart Sign in to MyCiteSeerX

Documents
Authors
Tables !

Searching for authors named "Ralf Schoknecht" – sorted by Relevance.

Order by: Citations | Year (Descending) | Year (Ascending) | Recency

Try your query at: Scholar | Yahoo! | Ask | Bing | CSB

8 documents found, showing 1 through 8.

ATOM

Speeding-up Reinforcement Learning with Multi-step Actions
by Ralf Schoknecht, Martin Riedmiller — 2002 — Proceedings of the Twelfth International Conference on Arti Neural Networks (ICANN), Lecture Notes in Computer Science (LNCS) 2415
…Speeding-up Reinforcement Learning with Multi-step Actions Ralf Schoknecht and Martin Riedmiller…
Cited by 3 (2 self) – Add To MetaCart

Using Reinforcement Learning For Engine Control
by Ralf Schoknecht, Martin Riedmiller — 1999 — In Ninth International Conference on Arti Neural Networks (ICANN '99
…Using Reinforcement Learning For Engine Control Ralf Schoknecht Martin Riedmiller Institut f…
Cited by 1 (1 self) – Add To MetaCart

TD(0) converges provably faster than the residual gradient algorithm
by Ralf Schoknecht, Artur Merke — 2003 — Proceedings of the Twentieth International Conference on Machine Learning (ICML-03
…TD(0) Converges Provably Faster than the Residual Gradient Algorithm Ralf Schoknecht ralf.schoknecht…
Cited by 1 (0 self) – Add To MetaCart

Approaches for the Integration of a Priori Knowledge Into an Autonomously Learning Control Architecture
by Martin Spott, Ralf Schoknecht Martin Riedmiller, Ralf Schoknecht, Martin Riedmiller — 1999
… architecture Martin Spott 1 , Ralf Schoknecht 2 and Martin Riedmiller 2 1 Institut fur…
Cited by 2 (2 self) – Add To MetaCart

Learning to Control at Multiple Time Scales
by Ralf Schoknecht, Martin Riedmiller, Lehrstuhl Informatik — 2003 — Artificial Neural Networks and Neural Information Processing - ICANN/ICONIP 2003, Joint International Conference ICANN/ICONIP 2003
…Learning to Control at Multiple Time Scales Ralf Schoknecht 1 and Martin Riedmiller 2 1…
Cited by 3 (0 self) – Add To MetaCart

Search Space Reduction for Strategy Learning in Sequential Decision Processes
by Ralf Schoknecht, Martin Spott, Florian Liekweg, Martin Riedmiller — 1999 — In Proceedings of the International Conference on Neural Information Processing (ICONIP '99
…Search Space Reduction for Strategy Learning in Sequential Decision Processes Ralf Schoknecht…
Cited by 2 (1 self) – Add To MetaCart

Applying Machine Learning to Solve an Estimation Problem in Software Inspections
by Thomas Ragg, Frank Padberg, Ralf Schoknecht — 2002 — In Proceedings International Conference on Artificial Neural Networks ICANN
…,2 , Frank Padberg 2 , and Ralf Schoknecht 2 1 phase-it AG, Vangerowstrae 20, 69115 Heidelberg, Germany…
Cited by 1 (0 self) – Add To MetaCart

Speeding-up Reinforcement Learning with
by Multi-Step Actions Ralf, Ralf Schoknecht, Martin Riedmiller — 2001 — Proceedings of the Twelfth International Conference on Arti Neural Networks (ICANN), Lecture Notes in Computer Science (LNCS) 2415
…Speeding-up Reinforcement Learning with Multi-step Actions Ralf Schoknecht and Martin Riedmiller…
Add To MetaCart

Showing 1 through 8.

ATOM

Try your query at: Scholar | Yahoo! | Ask | Bing | CSB