#### Filter Results:

- Full text PDF available (96)

#### Publication Year

1990

2018

- This year (6)
- Last 5 years (33)
- Last 10 years (72)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Brain Region

#### Cell Type

#### Method

Learn More

- Hilbert J. Kappen
- Physical review letters
- 2005

We address the role of noise and the issue of efficient computation in stochastic optimal control problems. We consider a class of nonlinear control problems that can be formulated as a path integralâ€¦ (More)

This paper considers linear-quadratic control of a non-linear dynamical system subject to arbitrary cost. I show that for this class of stochastic control problems the non-linearâ€¦ (More)

- Joris M. Mooij, Hilbert J. Kappen
- IEEE Transactions on Information Theory
- 2007

Novel conditions are derived that guarantee convergence of the sum-product algorithm (also known as loopy belief propagation or simply belief propagation (BP)) to a unique fixed point, irrespectiveâ€¦ (More)

We formulate tempo tracking in a Bayesian framework where a tempo tracker is modeled as a stochastic dynamical system. The tempo is modeled as a hidden state variable of the system and is estimatedâ€¦ (More)

- Tom Heskes, Kees Albers, Hilbert J. Kappen
- UAI
- 2003

Loopy and generalized belief propaÂ gation are popular algorithms for apÂ proximate inference in Markov ranÂ dom fields and Bayesian networks. Fixed points of these algorithms corÂ respond to extremaâ€¦ (More)

- Joris M. Mooij, Hilbert J. Kappen
- UAI
- 2005

We derive novel sufficient conditions for convergence of Loopy Belief Propagation (also known as the Sum-Product algorithm) to a unique fixed point. Our results improve upon previously knownâ€¦ (More)

- Mohammad Gheshlaghi Azar, VicenÃ§ GÃ³mez, Hilbert J. Kappen
- Journal of Machine Learning Research
- 2012

- Hilbert J. Kappen, VicenÃ§ GÃ³mez, Manfred Opper
- Machine Learning
- 2012

We reformulate a class of non-linear stochastic optimal control problems introduced by Todorov (in Advances in Neural Information Processing Systems, vol.Â 19, pp.Â 1369â€“1376, 2007) as aâ€¦ (More)

We analyse the local stability of the high-temperature fixed point of the loopy belief propagation (LBP) algorithm and how this relates to the properties of the Bethe free energy which LBP tries toâ€¦ (More)

- Mohammad Gheshlaghi Azar, VicenÃ§ GÃ³mez, Hilbert J. Kappen
- AISTATS
- 2011

In this paper, we consider the problem of planning in the infinite-horizon discountedreward Markov decision problems. We propose a novel iterative method, called dynamic policy programming (DPP),â€¦ (More)