ALEXANDRIA, Va., June 5 -- United States Patent no. 12,277,194, issued on April 15, was assigned to SONY GROUP Corp. (Tokyo).

"Task prioritized experience replay algorithm for reinforcement learning" was invented by Varun Kompella (Kanata, Canada), James MacGlashan (Riverside, R.I.), Peter Wurman (Acton, Mass.) and Peter Stone (Austin, Texas).

According to the abstract* released by the U.S. Patent & Trademark Office: "A task prioritized experience replay (TaPER) algorithm enables simultaneous learning of multiple RL tasks off policy. The algorithm can prioritize samples that were part of fixed length episodes that led to the achievement of tasks. This enables the agent to quickly learn task policies by bootstrapping over its early success...