Guided Reinforcement Learning: A Review and Evaluation for Efficient and Effective Real-World Robotics [Survey]

Recent successes aside, reinforcement learning (RL) still faces significant challenges in its application to the real-world robotics domain. Guiding the learning process with additional knowledge offers a potential solution, thus leveraging the strengths of data- and knowledge-driven approaches. However, this field of research encompasses several disciplines and hence would benefit from a structured overview.
In this article, we propose a concept of guided RL that provides a systematic approach toward accelerating the training process and improving performance for real-world robotics settings. We introduce a taxonomy that structures guided RL approaches and shows how different sources of knowledge can be integrated into the learning pipeline in a practical way. Based on this, we describe available approaches in this field and quantitatively evaluate their specific impact in terms of efficiency, effectiveness, and sim-to-real transfer within the robotics domain.

  • Published in:
    IEEE Robotics and Automation Magazine
  • Type:
    Article
  • Authors:
    Eßer, Julian; Bach, Nicolas; Jestel, Christian; Urbann, Oliver; Kerner, Sören
  • Year:
    2023

Citation information

Eßer, Julian; Bach, Nicolas; Jestel, Christian; Urbann, Oliver; Kerner, Sören: Guided Reinforcement Learning: A Review and Evaluation for Efficient and Effective Real-World Robotics [Survey], IEEE Robotics and Automation Magazine, 2023, 30, 2, 67--85, https://ieeexplore.ieee.org/abstract/document/9926159, Esser.etal.2023a,

Associated Lamarr Researchers

lamarr institut team autor esser julian - Lamarr Institute for Machine Learning (ML) and Artificial Intelligence (AI)

Julian Eßer

Scientific Coordinator Embodied AI to the profile
Sören Kerner

Dr. Sören Kerner

Area Chair Planning & Logistics to the profile