US Patent Issued to Uber Technologies on May 12 for "Model based reinforcement learning based on generalized hidden parameter Markov decision processes" (California Inventors)

ALEXANDRIA, Va., May 12 -- United States Patent no. 12,626,181, issued on May 12, was assigned to Uber Technologies Inc. (San Francisco).

"Model based reinforcement learning based on generalized hidden parameter Markov decision processes" was invented by Theofanis Karaletsos (San Francisco), Felipe Petroski Such (San Francisco) and Christian Francisco Perez (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A machine learning model for reinforcement learning uses parameterized families of Markov decision processes (MDP) with latent variables. The system uses latent variables to improve ability of models to transfer knowledge and generalize to new tasks. Accordingly, trained machine learnin...