Adaptive path-integral autoencoder: representation learning and planning for dynamical systems

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 65
  • Download : 0
We present a representation learning algorithm that learns a low-dimensional latent dynamical system from high-dimensional sequential raw data, e.g. video. The framework builds upon recent advances in amortized inference methods that use both an inference network and a refinement procedure to output samples from a variational distribution given an observation sequence, and takes advantage of the duality between control and inference to approximately solve the intractable inference problem using the path integral control approach. The learned dynamical model can be used to predict and plan the future states; we also present the efficient planning method that exploits the learned low-dimensional latent dynamics. Numerical experiments show that the proposed path-integral control based variational inference method leads to tighter lower bounds in statistical model learning of sequential data.
Publisher
IOP PUBLISHING LTD
Issue Date
2019-12
Language
English
Article Type
Article
Citation

JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT, v.2019, no.12

ISSN
1742-5468
DOI
10.1088/1742-5468/ab3455
URI
http://hdl.handle.net/10203/272620
Appears in Collection
AE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0