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

2020-08-14Code Available1· sign in to hype

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

Code Available — Be the first to reproduce this paper.

Code

github.com/martius-lab/iCEM
Officialnone★ 84

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.

Tasks

Model-based Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

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

Code

Abstract

Tasks

Reproductions