Sample-efficient Cross-Entropy Method for Real-time Planning
Authors
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)
Interactive Session
2020-11-16, 11:10 - 11:40 PST | PheedLoop Session
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.