EP for Efficient Stochastic Control with Obstacles

Thomas Mensink 1 Jakob Verbeek 2 Bert Kappen 3
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We address the problem of continuous stochastic optimal control in the presence of hard obstacles. Due to the non-smooth character of the obstacles, the traditional approach using dynamic programming in combination with function approximation tends to fail. We consider a recently introduced special class of control problems for which the optimal control computation is reformulated in terms of a path integral. The path integral is typically intractable, but amenable to techniques developed for approximate inference.We argue that the variational approach fails in this case due to the nonsmooth cost function. Sampling techniques are simple to implement and converge to the exact results given enough samples. However, the infinite cost associated with hard obstacles renders the sampling procedures inefficient in practice. We suggest Expectation Propagation (EP) as a suitable approximation method, and compare the quality and efficiency of the resulting control with an MC sampler on a car steering task and a ball throwing task.We conclude that EP can solve these challenging problems much better than a sampling approach.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [17 references]  Display  Hide  Download


https://hal.inria.fr/inria-00548631
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 10:22:12 AM
Last modification on : Tuesday, February 12, 2019 - 10:30:05 AM
Document(s) archivé(s) le : Monday, November 5, 2012 - 2:36:31 PM

Files

MVK10.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Thomas Mensink, Jakob Verbeek, Bert Kappen. EP for Efficient Stochastic Control with Obstacles. ECAI 2010 - 19th European Conference on Artificial Intelligence, Aug 2010, Lisbon, Portugal. pp.675-680, ⟨10.3233/978-1-60750-606-5-675⟩. ⟨inria-00548631⟩

Share

Metrics

Record views

587

Files downloads

494