Call for Papers: Special Issue on Reinforcement Learning for Real Life

Reinforcement learning (RL) is a general learning, predicting, and decision making paradigm and applies broadly in science, engineering and arts. RL has seen prominent successes in many problems, such as Atari games, AlphaGo, robotics, recommender systems, and AutoML. However, applying RL in the real world remains challenging, and a natural question is:

What are the issues and how to solve them?

The main goals of the special issue are to: (1) identify key research problems that are critical for the success of real-world applications; (2) report progress on addressing these critical issues; and (3) have practitioners share their success stories of applying RL to real-world problems, and the insights gained from the applications.

We invite submissions successfully applying RL algorithms to real-life problems by addressing practically relevant RL issues. Our topics of interest are general, including but not limited to topics below:

  • Practical RL algorithms , which covers all algorithmic challenges of RL, especially those that directly address challenges faced by real-world applications;
  • Practical issues: generalization, sample/time/space efficiency, exploration vs. exploitation, reward specification and shaping, scalability, model-based learning (model validation and model error estimation), prior knowledge, safety, accountability, interpretability, reproducibility, hyper-parameter tuning;
  • Applications: recommender systems, advertisements, conversational AI, business, finance, healthcare, education, robotics, autonomous driving, transportation, energy, chemical synthesis, drug design, industrial control, drawing, music, or other problems in science, engineering and arts.

Submissions should be made via the Machine Learning journal website at When submitting your paper, be sure to specify that the paper is a contribution for the Special Issue "SI: Reinforcement Learning For Real Life" so that your paper will be assigned to the guest editors.

Springer does not require authors to submit their papers in a prescribed template. If the paper is accepted for publication the source files will be converted by the typesetter and prepared in Springer's format for the online platform, SpringerLink. Accepted papers will be published online, before print publication. Resources for journal authors, including templates and style files, as well as frequently asked questions can be found at: Journal Author Resources, https://, in particular, Submission Guidelines for Machine Learning Journal:

The deadline for submission has been extended to May 15, 2020 AOE. 

For any inquiry about the special issue, please contact us at We are looking forward to receiving your contribution.

Guest Editors:

Alborz Geramifard (Facebook)

Lihong Li (Google Research)

Yuxi Li (Attain.AI)

Csaba Szepesvari (DeepMind & University of Alberta)

Tao Wang (Apple)