A Hilbert Space Embedding for Distributions
ALT '07 Proceedings of the 18th international conference on Algorithmic Learning Theory
Hilbert space embeddings of conditional distributions with applications to dynamical systems
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Robot trajectory optimization using approximate inference
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Action and behavior: a free-energy formulation
Biological Cybernetics
EP for Efficient Stochastic Control with Obstacles
Proceedings of the 2010 conference on ECAI 2010: 19th European Conference on Artificial Intelligence
A Generalized Path Integral Control Approach to Reinforcement Learning
The Journal of Machine Learning Research
Hi-index | 0.00 |
We present an embedding of stochastic optimal control problems, of the so called path integral form, into reproducing kernel Hilbert spaces. Using consistent, sample based estimates of the embedding leads to a model-free, non-parametric approach for calculation of an approximate solution to the control problem. This formulation admits a decomposition of the problem into an invariant and task dependent component. Consequently, we make much more efficient use of the sample data compared to previous sample based approaches in this domain, e.g., by allowing sample re-use across tasks. Numerical examples on test problems, which illustrate the sample efficiency, are provided.