Automated Reinforcement Learning (AutoRL): A Survey and Open Problems

Research output: Contribution to journalResearch articleContributedpeer-review


  • Jack Parker-Holder - , University of Oxford (Author)
  • Raghu Rajan - , University of Freiburg (Author)
  • Xingyou Song - , Alphabet Inc. (Author)
  • André Biedenkapp - , University of Freiburg (Author)
  • Yingjie Miao - , Alphabet Inc. (Author)
  • Theresa Eimer - , Leibniz University Hannover (LUH) (Author)
  • Baohe Zhang - , University of Freiburg (Author)
  • Vu Nguyen - , Amazon (Author)
  • Roberto Calandra - , Meta (Author)
  • Aleksandra Faust - , Alphabet Inc. (Author)
  • Frank Hutter - , University of Freiburg (Author)
  • Marius Lindauer - , Leibniz University Hannover (LUH) (Author)


The combination of Reinforcement Learning (RL) with deep learning has led to a series of impressive feats, with many believing (deep) RL provides a path towards generally capable agents. However, the success of RL agents is often highly sensitive to design choices in the training process, which may require tedious and error-prone manual tuning. This makes it challenging to use RL for new problems and also limits its full potential. In many other areas of machine learning, AutoML has shown that it is possible to automate such design choices, and AutoML has also yielded promising initial results when applied to RL. However, Automated Reinforcement Learning (AutoRL) involves not only standard applications of AutoML but also includes additional challenges unique to RL, that naturally produce a different set of methods. As such, AutoRL has been emerging as an important area of research in RL, providing promise in a variety of applications from RNA design to playing games, such as Go. Given the diversity of methods and environments considered in RL, much of the research has been conducted in distinct subfields, ranging from meta-learning to evolution. In this survey, we seek to unify the field of AutoRL, provide a common taxonomy, discuss each area in detail and pose open problems of interest to researchers going forward.


Original languageEnglish
Pages (from-to)517-568
Number of pages52
JournalJournal of Artificial Intelligence Research
Issue number74
Publication statusPublished - 2022
Externally publishedYes

External IDs

ORCID /0000-0001-9430-8433/work/158768048