LayoutRL: A Reinforcement Learning-Based Approach to Keyboard Layout Optimization
Keywords: Layout Optimization, Ergonomics, Data-driven Optimization, Interaction Design, Reinforcement learning, HCI
TL;DR: We propose a reinforcement learning-based approach to designing optimized keyboard layouts that demonstrates approximately an 11% improvement in ergonomic parameters over traditional keyboards
Abstract: Keyboards are a key interface between humans and computers, with character arrangements offering numerous layout possibilities. Many existing designs follow standardized ergonomic principles and explore Pareto-optimality in multi-objective functions using metaheuristics or deep learning. In this work, we propose a reinforcement learning-based approach to designing optimized keyboard layouts that integrate both technical and ergonomic considerations. Our results demonstrate that reinforcement learning optimization can produce layouts more efficiently than conventional designs, such as the "QWERTY" keyboard. Specifically, our approach achieves approximately an 12.4\% improvement in ergonomic parameters over traditional keyboards, underscoring the potential for a more data-driven, systematic approach to keyboard layout optimization.
Primary Area: reinforcement learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 11473
Loading