US Patent Issued to Salesforce on Jan. 20 for "Systems and methods for safe policy improvement for task oriented dialogues" (California Inventors)

ALEXANDRIA, Va., Jan. 20 -- United States Patent no. 12,530,565, issued on Jan. 20, was assigned to Salesforce Inc. (San Francisco).

"Systems and methods for safe policy improvement for task oriented dialogues" was invented by Govardana Sachithanandam Ramachandran (Palo Alto, Calif.), Kazuma Hashimoto (Menlo Park, Calif.), Caiming Xiong (Menlo Park, Calif.) and Richard Socher (Menlo Park, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments described herein provide safe policy improvement (SPI) in a batch reinforcement learning framework for a task-oriented dialogue. Specifically, a batch reinforcement learning framework for dialogue policy learning is provided, which improves the performance of...