This inventor holds 1 USPTO granted patent. Top assignee: Preferred Networks, Inc.. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Kota Uenishi: Distributed Reinforcement Learning Innovation
Introduction
Kota Uenishi is an inventor based in Tokyo, Japan, associated with Preferred Networks, Inc. His patent work addresses distributed reinforcement learning, a field focused on training models using experience gathered across multiple devices and computing nodes.
Latest Patents
Uenishi is associated with 1 patent: “Distributed Reinforcement Learning System and Distributed Reinforcement Learning Method.” The invention describes a system in which actor devices acquire experience data based on actions determined by a model being trained. Multiple replay buffers store that data across distributed nodes, while learner devices use the stored experience to train the model.
Career Highlights
Uenishi’s listed invention concerns the organization of reinforcement-learning components across distributed computing resources. By distributing replay buffers among multiple nodes, the system provides a method for storing and using experience data in model training.
Collaborations
Uenishi is associated with Preferred Networks, Inc. His listed coworker is Yasuhiro Fujita.
Conclusion
Kota Uenishi’s patent highlights an approach to distributed reinforcement learning that coordinates actor devices, replay buffers, and learner devices across multiple nodes.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
