Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Adaptive Path-Integral Approach for Representation Learning and Planning
Jung-Su Ha, Young-Jin Park, Hyeok-Joo Chae, Soon-Seo Park, Han-Lim Choi
Feb 12, 2018 (modified: Jun 04, 2018)ICLR 2018 Workshop Submissionreaders: everyoneShow Bibtex
Abstract:We present a novel framework for representation learning that builds a low-dimensional latent dynamical model from high-dimensional sequential raw data, e.g., video. The framework builds upon recent advances in amortized inference methods that use a differentiable network to output samples from a variational distribution given observations as inputs, and takes advantage of the duality between control and inference to approximately solve the intractable inference problem using the path integral control approach. We also present an efficient planning method that exploits the learned low-dimensional latent dynamics.
Keywords:Representation learning for planning, Unsupervised learning, Approximate inference via stochastic optimal control
TL;DR:We propose a novel stochastic optimal control-based framework for representation learning and planning of dynamical systems.
Enter your feedback below and we'll get back to you as soon as possible.