This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignees: Denso International America, Inc., University of California. 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: Jinning Li: Inventor in Hierarchical Planning and Reinforcement Learning.
Introduction
Jinning Li is an inventor based in Berkeley, California. His work includes a patented approach to hierarchical planning through goal-conditioned offline reinforcement learning.
Latest Patents
Li is associated with 1 patent: “Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning.” The invention describes a method and system for controlling a device. It trains a low-level policy and a goal-conditioned value function using a static dataset of goal-conditioned episodes. A high-level planner then selects reachable sub-goals across future time steps to maximize cumulative reward. After receiving an observation of the device, the system generates an executable action using the trained policy and planner.
Career Highlights
Li’s listed professional affiliations include Denso International America, Inc. and the University of California.
Collaborations
Li’s listed coworker is Wei Zhan.
Conclusion
Jinning Li’s patent combines offline reinforcement learning with hierarchical goal planning to generate actions for controlling devices.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile