Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challenges
Not on the map. Why?
Abstract (arXiv)
Deep reinforcement learning (DRL), leveraging Deep Learning (DL) in reinforcement learning, has shown significant potential in achieving human-level autonomy in a wide range of domains, including robotics, computer vision, and computer games. This potential justifies the enthusiasm and growing interest in DRL in both academia and industry. However, the community currently focuses mostly on the development phase of DRL systems, with little attention devoted to DRL deployment. In this paper, we propose an empirical study on Stack Overflow (SO), the most popular Q&A forum for developers, to uncover and understand the challenges practitioners faced when deploying DRL systems. Specifically, we categorized relevant SO posts by deployment platforms: server/cloud, mobile/embedded system, browser, and game engine. After filtering and manual analysis, we examined 357 SO posts about DRL deployment, investigated the current state, and identified the challenges related to deploying DRL systems. Then, we investigate the prevalence and difficulty of these challenges. Results show that the general interest in DRL deployment is growing, confirming the study's relevance and importance. Results also show that DRL deployment is more difficult than other DRL issues. Additionally, we built a taxonomy of 31 unique challenges in deploying DRL to different platforms. On all platforms, RL environment-related challenges are the most popular, and communication-related challenges are the most difficult among practitioners. We hope our study inspires future research and helps the community overcome the most common and difficult challenges practitioners face when deploying DRL systems.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 24 of its 80 references that are in the map. First posted on arXiv 23 Aug 2023.
Builds on
24 of 80 references.
References · 24
- 2016OpenAI Gymcited by 1,736
- 2017A Brief Survey of Deep Reinforcement Learningcited by 483
- 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
- 2017Deep Reinforcement Learning: An Overviewcited by 333
- 2019Challenges of Real-World Reinforcement Learningcited by 291
- 2020TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systemscited by 165
- 2017Deep Learning with Low Precision by Half-wave Gaussian Quantizationcited by 117
- 2017TensorFlow-Serving: Flexible, High-Performance ML Servingcited by 85
- 2015Massively Parallel Methods for Deep Reinforcement Learningcited by 82
- 2019Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systemscited by 78
- 2018A Survey on Methods and Theories of Quantized Neural Networkscited by 75
- 2019A Survey of Deep Reinforcement Learning in Video Gamescited by 73
12 more
- 2018A First Look at Deep Learning Apps on Smartphonescited by 47
- 2019An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platformscited by 35
- 2019TensorFlow.js: Machine Learning for the Web and Beyondcited by 29
- 2018Inverse reinforcement learning for video gamescited by 26
- 2021An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applicationscited by 20
- 2021Faults in Deep Reinforcement Learning Programs: A Taxonomy and A Detection Approachcited by 18
- 2019Moving Deep Learning into Web Browser: How Far Can We Go?cited by 14
- 2022An Empirical Study of Challenges in Converting Deep Learning Modelscited by 8
- 2020Interpreting Cloud Computer Vision Pain-Points: A Mining Study of Stack Overflowcited by 6
- 2022Explaining Online Reinforcement Learning Decisions of Self-Adaptive Systemscited by 5
- 2022MR-iNet Gym: Framework for Edge Deployment of Deep Reinforcement Learning on Embedded Software Defined Radiocited by 4
- 2022GriddlyJS: A Web IDE for Reinforcement Learningcited by 4
Built on by
Citing papers per year: 2025: 2.
2 papers.