Inventor · London, GB

Tom Schaul

15Patents
3h-index
29Co-inventors
52Inventor score

Filing activity: Apr 17, 2015 → Mar 8, 2023

Most-cited inventions

PatentTitleAreaCited byStatus
US10628733B2 Selecting reinforcement learning actions using goals and observations Physics 14 Active
US10282662B2 Training neural networks using a prioritized experience memory Emerging Cross-Sectional Technologies 8 Active
US10733501B2 Environment prediction using reinforcement learning Physics 3 Active
US10650310B2 Training neural networks using a prioritized experience memory Emerging Cross-Sectional Technologies 3 Active
US10956820B2 Reinforcement learning with auxiliary tasks Physics 2 Active
US12154029B2 Continual reinforcement learning with a multi-task agent Physics 1 Active
US12061964B2 Modulating agent behavior to optimize learning progress Physics 1 Active
US12141677B2 Environment prediction using reinforcement learning Physics 1 Active
US12086714B2 Training neural networks using a prioritized experience memory Emerging Cross-Sectional Technologies 0 Active
US11615310B2 Training machine learning models by determining update rules using recurrent neural networks Physics 0 Active
US10055687B2 Method for creating predictive knowledge structures from experience in an artificial agent Physics 0 Active
US11568250B2 Training neural networks using a prioritized experience memory Emerging Cross-Sectional Technologies 0 Active
US11842281B2 Reinforcement learning with auxiliary tasks Physics 0 Active
US11676035B2 Learning non-differentiable weights of neural networks using evolutionary strategies Physics 0 Active
US12271823B2 Training machine learning models by determining update rules using neural networks Physics 0 Active

Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.