• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes.
Chen
Tang, Ben Abbatematteo, Jiaheng Hu, Rohan
Chandra, Roberto Martín-Martín, and Peter Stone.
Annual Review
of Control, Robotics, and Autonomous Systems (ARCRAS), 8:153–88, 2024.
Presented in Senior member track at
AAAI 2025
Official
version on publisher's website
[PDF]4.3MB [slides.pdf]2.9MB [poster.pdf]604.3kB
Reinforcement learning (RL), particularly its combination with deep neural networks referred to as deep RL (DRL), has shown tremendous promise across a wide range of applications, suggesting its potential for enabling the development of sophisticated robotic behaviors. Robotics problems, however, pose fundamental difficulties for the application of RL, stemming from the complexity and cost of interacting with the physical world. This article provides a modern survey of DRL for robotics, with a particular focus on evaluating the real-world successes achieved with DRL in realizing several key robotic competencies. Our analysis aims to identify the key factors underlying those exciting successes, reveal underexplored areas, and provide an overall characterization of the status of DRL in robotics. We highlight several important avenues for future work, emphasizing the need for stable and sample-efficient real-world RL paradigms, holistic approaches for discovering and integrating various competencies to tackle complex long-horizon, open-world tasks, and principled development and evaluation procedures. This survey is designed to offer insights for both RL practitioners and roboticists toward harnessing RL's power to create generally capable real-world robotic systems.
@Article{chen_tang_ARCRAS2024,
author = {Chen Tang and Ben Abbatematteo and Jiaheng Hu and Rohan Chandra and Roberto MartÃn-MartÃn and Peter Stone},
title = {Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes},
journal = {Annual Review of Control, Robotics, and Autonomous Systems (ARCRAS)},
volume = {8},
pages = {153--88},
year = {2024},
doi = {https://doi.org/10.1146/annurev-control-030323-022510},
abstract = {Reinforcement learning (RL), particularly its combination with deep neural networks referred to as deep RL (DRL), has shown tremendous promise across a wide range of applications, suggesting its potential for enabling the development of sophisticated robotic behaviors. Robotics problems, however, pose fundamental difficulties for the application of RL, stemming from the complexity and cost of interacting with the physical world. This article provides a modern survey of DRL for robotics, with a particular focus on evaluating the real-world successes achieved with DRL in realizing several key robotic competencies. Our analysis aims to identify the key factors underlying those exciting successes, reveal underexplored areas, and provide an overall characterization of the status of DRL in robotics. We highlight several important avenues for future work, emphasizing the need for stable and sample-efficient real-world RL paradigms, holistic approaches for discovering and integrating various competencies to tackle complex long-horizon, open-world tasks, and principled development and evaluation procedures. This survey is designed to offer insights for both RL practitioners and roboticists toward harnessing RL's power to create generally capable real-world robotic systems.},
wwwnote={Presented in Senior member track at <a href="https://ojs.aaai.org/index.php/AAAI/article/view/35095">AAAI 2025</a><br>
<a href="https://www.annualreviews.org/content/journals/10.1146/annurev-control-030323-022510">Official version</a> on publisher's website},
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Jun 10, 2026 15:26:41