US Patent Issued to Salesforce on June 30 for "Systems and methods for end-to-end multi-agent reinforcement learning on a graphics processing unit" (California Inventors)

ALEXANDRIA, Va., July 16 -- United States Patent no. 12,670,418, issued on June 30, was assigned to Salesforce Inc. (San Francisco).

"Systems and methods for end-to-end multi-agent reinforcement learning on a graphics processing unit" was invented by Tian Lan (Pleasanton, Calif.), Stephan Tao Zheng (San Francisco) and Sunil Srinivasa (Palo Alto, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments provide a fast multi-agent reinforcement learning (RL) pipeline that runs the full RL workflow end-to-end on a single GPU, using a single store of data for simulation roll-outs, inference, and training. Specifically, simulations and agents in each simulation are run in tandem, taking advantage of the p...