Sample-efficient Cross-Entropy Method for Real-time Planning
2020
Conference Paper
al
ev
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.
Author(s): | Cristina Pinneri and Shambhuraj Sawant and Sebastian Blaes and Jan Achterhold and Joerg Stueckler and Michal Rolinek and Georg Martius |
Book Title: | Conference on Robot Learning 2020 |
Year: | 2020 |
Department(s): | Autonomous Learning, Embodied Vision |
Research Project(s): |
Model-based Reinforcement Learning and Planning
|
Bibtex Type: | Conference Paper (inproceedings) |
State: | Published |
URL: | https://corlconf.github.io/corl2020/paper_217/ |
Links: |
Paper
Code Spotlight-Video |
Video: | |
BibTex @inproceedings{PinneriEtAl2020:iCEM, title = {Sample-efficient Cross-Entropy Method for Real-time Planning}, author = {Pinneri, Cristina and Sawant, Shambhuraj and Blaes, Sebastian and Achterhold, Jan and Stueckler, Joerg and Rolinek, Michal and Martius, Georg}, booktitle = {Conference on Robot Learning 2020}, year = {2020}, doi = {}, url = {https://corlconf.github.io/corl2020/paper_217/ } } |