Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey

Sanmit Narvekar, Bei Peng, Matteo Leonetti, Jivko Sinapov, Matthew E. Taylor, and Peter Stone. Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey. Journal of Machine Learning Research, 21(181):1–50, 2020.

Download

[PDF]1.4MB  

Abstract

Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback. Despite many advances over the past three decades, learning in many domains still requires a large amount of interaction with the environment, which can be prohibitively expensive in realistic scenarios. To address this problem, transfer learning has been applied to reinforcement learning such that experience gained in one task can be leveraged when starting to learn the next, harder task. More recently, several lines of research have explored how tasks, or data samples themselves, can be sequenced into a curriculum for the purpose of learning a problem that may otherwise be too difficult to learn from scratch. In this article, we present a framework for curriculum learning (CL) in reinforcement learning, and use it to survey and classify existing CL methods in terms of their assumptions, capabilities, and goals. Finally, we use our framework to find open problems and suggest directions for future RL curriculum learning research.

BibTeX Entry

@article{JMLR20-sanmit,
  author  = {Sanmit Narvekar and Bei Peng and Matteo Leonetti and Jivko Sinapov and Matthew E. Taylor and Peter Stone},
  title   = {Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey},
  journal = {Journal of Machine Learning Research},
  year    = {2020},
  volume  = {21},
  number  = {181},
  pages   = {1-50},
  url     = {http://jmlr.org/papers/v21/20-212.html},
  abstract = {
          Reinforcement learning (RL) is a popular paradigm for addressing
          sequential decision tasks in which the agent has only limited
          environmental feedback. Despite many advances over the past three
          decades, learning in many domains still requires a large amount of
          interaction with the environment, which can be prohibitively
          expensive in realistic scenarios.  To address this problem, transfer
          learning has been applied to reinforcement learning such that
          experience gained in one task can be leveraged when starting to learn
          the next, harder task. More recently, several lines of research have
          explored how tasks, or data samples themselves, can be sequenced into
          a curriculum for the purpose of learning a problem that may otherwise
          be too difficult to learn from scratch. In this article, we present a
          framework for curriculum learning (CL) in reinforcement learning, and
          use it to survey and classify existing CL methods in terms of their
          assumptions, capabilities, and goals. Finally, we use our framework
          to find open problems and suggest directions for future RL curriculum
          learning research.}, 
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Nov 25, 2020 21:30:58