Mar 12, 2017 · Our approach is based on convolutional autoregressive models and variational autoencoders. It makes stable and accurate predictions over long ...

Abstract. We introduce a method for learning the dynamics of complex nonlinear systems based on deep gen- erative models over temporal segments of states.

We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions.

The learned dynamics model and action prior can be used for end-to-end, fully differentiable trajectory optimization and model-based policy optimization, ...

Aug 6, 2017 · Our approach is based on convolutional autoregressive models and variational autoencoders. It makes stable and accurate predictions over long ...

Jul 13, 2017 · Abstract. We introduce a method for learning the dynamics of complex nonlinear systems based on deep gen- erative models over temporal ...

Apr 3, 2019 · Bibliographic details on Prediction and Control with Temporal Segment Models.

We introduce a method for learning the dynamics of complex nonlinear systemsbased on deep generative models over temporal segments of states and actions.

Prediction and Control with Temporal Segment Models (arxiv) Nikhil Mishra, Pieter Abbeel, Igor Mordatch. In the proceedings of the International Conference ...