Header logo is


2011


no image
Optimal Reinforcement Learning for Gaussian Systems

Hennig, P.

In Advances in Neural Information Processing Systems 24, pages: 325-333, (Editors: J Shawe-Taylor and RS Zemel and P Bartlett and F Pereira and KQ Weinberger), Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

Abstract
The exploration-exploitation trade-off is among the central challenges of reinforcement learning. The optimal Bayesian solution is intractable in general. This paper studies to what extent analytic statements about optimal learning are possible if all beliefs are Gaussian processes. A first order approximation of learning of both loss and dynamics, for nonlinear, time-varying systems in continuous time and space, subject to a relatively weak restriction on the dynamics, is described by an infinite-dimensional partial differential equation. An approximate finitedimensional projection gives an impression for how this result may be helpful.

ei pn

PDF Web [BibTex]

2011


PDF Web [BibTex]


no image
Tipping the Scales: Guidance and Intrinsically Motivated Behavior

Martius, G., Herrmann, J. M.

In Advances in Artificial Life, ECAL 2011, pages: 506-513, (Editors: Tom Lenaerts and Mario Giacobini and Hugues Bersini and Paul Bourgine and Marco Dorigo and René Doursat), MIT Press, 2011 (incollection)

al

[BibTex]

[BibTex]


no image
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers

Rolinek, M., Swoboda, P., Zietlow, D., Paulus, A., Musil, V., Martius, G.

Arxiv (article)

Abstract
Building on recent progress at the intersection of combinatorial optimization and deep learning, we propose an end-to-end trainable architecture for deep graph matching that contains unmodified combinatorial solvers. Using the presence of heavily optimized combinatorial solvers together with some improvements in architecture design, we advance state-of-the-art on deep graph matching benchmarks for keypoint correspondence. In addition, we highlight the conceptual advantages of incorporating solvers into deep learning architectures, such as the possibility of post-processing with a strong multi-graph matching solver or the indifference to changes in the training setting. Finally, we propose two new challenging experimental setups

al

Arxiv [BibTex]