arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.06389cs.LGcs.ROstat.ML
收藏

实时的规划的样本有效交叉熵方法

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

Max Planck ETH Center for Learning Systems(马克斯·普朗克ETH学习系统中心);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)

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

摘要:

基于基于模型的强化学习的轨迹优化器,如交叉熵方法(CEM),即使在高维控制任务和稀疏奖励环境中也可以产生令人信服的结果。然而,它们的采样效率低,使它们不能用于实时的【形】形规划和控制。我们提出了一个改进版本的CEM算法的快速规划,与新的补充,包括时间相关的行动和内存,需要2.7- 22倍的样本,并产生1.2- 10倍的性能提高高维控制问题。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑