Some Insights into Lifelong Reinforcement Learning Systems

Changjian Li

Some Insights into Lifelong Reinforcement Learning Systems

Machine Learning 2020-01-28 v1 Machine Learning

Authors: Changjian Li

Abstract

A lifelong reinforcement learning system is a learning system that has the ability to learn through trail-and-error interaction with the environment over its lifetime. In this paper, I give some arguments to show that the traditional reinforcement learning paradigm fails to model this type of learning system. Some insights into lifelong reinforcement learning are provided, along with a simplistic prototype lifelong reinforcement learning system.

Keywords

reinforcement learning machine learning theory machine learning

Cite

@article{arxiv.2001.09608,
  title  = {Some Insights into Lifelong Reinforcement Learning Systems},
  author = {Changjian Li},
  journal= {arXiv preprint arXiv:2001.09608},
  year   = {2020}
}

Related papers

View all related →

Artificial Intelligence · Computer Science

Environments for Lifelong Reinforcement Learning

Khimya Khetarpal, Shagun Sodhani, Sarath Chandar, Doina Precup