CoRL 2020, Spotlight Talk 217: Sample-efficient Cross-Entropy Method for Real-time Planning

CoRL 2020

CoRL 2020, Spotlight Talk 217: Sample-efficient Cross-Entropy Method for Real-time Planning

Dec 16, 2020
|
37 views
|
Details
"**Sample-efficient Cross-Entropy Method for Real-time Planning** Cristina Pinneri (Max Planck Institute for Intelligent Systems)*; Shambhuraj Sawant (Max Planck Institute for Intelligent Systems); Sebastian Blaes (Max Planck Institute for Intelligent Systems); Jan Achterhold (Max Planck Institute for Intelligent Systems); Joerg Stueckler (Max-Planck-Institute for Intelligent Systems); Michal Rolinek (Max Planck Institute for Intelligent Systems); Georg Martius (Max Planck Institute for Intelligent Systems) Publication: http://corlconf.github.io/paper_217/ **Abstract** Trajectory optimizers for model-based reinforcement learning, such as the Cross-Entropy Method (CEM), can yield compelling results even in high-dimensional control tasks and sparse-reward environments. However, their sampling inefficiency prevents them from being used for real-time planning and control. We propose an improved version of the CEM algorithm for fast planning, with novel additions including temporally-correlated actions and memory, requiring 2.7-22x less samples and yielding a performance increase of 1.2-10x in high-dimensional control problems.

Comments
loading...