The Differentiable Cross-Entropy Method
From MaRDI portal
Publication:6326136
arXiv1909.12830MaRDI QIDQ6326136
Author name not available (Why is that?)
Publication date: 27 September 2019
Abstract: We study the cross-entropy method (CEM) for the non-convex optimization of a continuous and parameterized objective function and introduce a differentiable variant that enables us to differentiate the output of CEM with respect to the objective function's parameters. In the machine learning setting this brings CEM inside of the end-to-end learning pipeline where this has otherwise been impossible. We show applications in a synthetic energy-based structured prediction task and in non-convex continuous control. In the control setting we show how to embed optimal action sequences into a lower-dimensional space. DCEM enables us to fine-tune CEM-based controllers with policy optimization.
Has companion code repository: https://github.com/facebookresearch/dcem
This page was built for publication: The Differentiable Cross-Entropy Method
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6326136)
