16/11/2020

Sample-efficient Cross-Entropy Method for Real-time Planning

Cristina Pinneri, Shambhuraj Sawant, Sebastian Blaes, Jan Achterhold, Joerg Stueckler, Michal Rolinek, Georg Martius

Keywords:

Abstract Paper Code Similar Papers

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.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at CoRL 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 3:12 
 0
 0
 0
 0
 14:16 
 0
 0
 0
 0
 6:14 
 0
 0
 0
 2
 4:57 
 0
 0
 0
 0
 3:10 
 0
 0
 0
 0
 3:05 
 0
 0
 0
 0
 16:26 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 16:27 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 2:59 
 1
 0
 0
 0
 7:03 
 0
 0
 0
 0
 9:59 
 0
 0
 0
 0
 4:17 
 0
 0
 0
 0
 16:56 
 0
 0
 0
 0
 3:03 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 14:41 
 0
 0
 0
 0
 5:03 
 0
 0
 0
 0
 11:33 
 0
 0
 0
 0
 19:54 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 3:29 
 0
 0
 0
 0
 4:49 
 0
 0
 0
 1
 10:04 
 0
 0
 0
 0
 11:43 
 0
 0
 0
 0
 14:21 
 0
 0
 0
 0
 15:30 
 0
 0
 0
 0
 7:04 
 1
 0
 0
 0
 4:45 
 0
 0
 0
 0
 15:35 
 0
 0
 0
 0
 13:39 
 0
 0
 0
 0
 10:59 
 0
 0
 0
 0
 14:50 
 0
 0
 0
 0
 14:23 
 0
 0
 0
 0
 5:20 
 0
 1
 1
 0
 4:24