Folgen
Paul Wagner
Paul Wagner
Bestätigte E-Mail-Adresse bei aalto.fi
Titel
Zitiert von
Zitiert von
Jahr
A reinterpretation of the policy oscillation phenomenon in approximate policy iteration
P Wagner
Advances in Neural Information Processing Systems, 2573-2581, 2011
352011
Compact modeling of data using independent variable group analysis
E Alhoniemi, A Honkela, K Lagus, SJ Seppä, P Wagner, H Valpola
IEEE Transactions on Neural Networks 18 (6), 1762-1776, 2007
172007
Optimistic policy iteration and natural actor-critic: A unifying view and a non-optimality result
P Wagner
Advances in Neural Information Processing Systems 26, 2013
132013
Policy oscillation is overshooting
P Wagner
Neural Networks 52, 43-61, 2014
112014
Independent variable group analysis in learning compact representations for data
K Lagus, E Alhoniemi, J Seppä, A Honkela, P Wagner
Proceedings of the International and Interdisciplinary Conference on …, 2005
82005
A gaussian process reinforcement learning algorithm with adaptability and minimal tuning requirements
J Strahl, T Honkela, P Wagner
Artificial Neural Networks and Machine Learning–ICANN 2014: 24th …, 2014
62014
On the stability of reinforcement learning under partial observability and generalizing representations
P Wagner
AALTO UNIVERSITY, 2010
2010
A reinterpretation of the policy oscillation phenomenon in approximate policy iteration (extended)
P Wagner
Computational Cognitive Systems
T Honkela, K Lagus, M Dobrinkat, O Kohonen, M Kumlander, ...
Adaptive Informatics Research Centre Department of Information and Computer …, 0
Optimistic policy iteration and natural actor-critic: A unifying view and a non-optimality result (extended)
P Wagner
Conceptual modeling and learning
K Lagus, T Honkela, T Lindh-Knuutila, MS Paukkeri, J Raitio, O Kohonen, ...
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–11