Scalable lifelong reinforcement learning

作者：

Highlights：

• Deriving a novel scalable algorithm for lifelong policy search in reinforcement learning.

• Acquiring linear convergence rate of our new algorithm

• Demonstrating the effectiveness of our technique dynamical systems and learning speed-ups on unobserved tasks.

摘要

•Deriving a novel scalable algorithm for lifelong policy search in reinforcement learning.•Acquiring linear convergence rate of our new algorithm•Demonstrating the effectiveness of our technique dynamical systems and learning speed-ups on unobserved tasks.

论文关键词：Reinforcement learning,Lifelong learning,Distributed optimization,Transfer learning

论文评审过程：Received 28 October 2016, Revised 23 July 2017, Accepted 27 July 2017, Available online 29 July 2017, Version of Record 17 August 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.07.031