Issued Patents All Time
Showing 1–23 of 23 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 12367391 | Selecting reinforcement learning actions using a low-level controller | Nicolas Manfred Otto Heess, Gregory Duncan Wayne, Yuval Tassa | 2025-07-22 |
| 12346786 | Data-efficient reinforcement learning for continuous control tasks | Martin Riedmiller, Roland Hafner, Mel Vecerik, Thomas Lampe, Ivaylo Popov +2 more | 2025-07-01 |
| 12277487 | Energy-based associative memory neural networks | Sergey Bartunov, Jack William Rae, Simon Osindero | 2025-04-15 |
| 12240113 | Deep reinforcement learning for robotic manipulation | Sergey Levine, Ethan Holly, Shixiang Gu | 2025-03-04 |
| 12189870 | Learned computer control using pointing device and keyboard actions | Peter Humphreys, Tobias Markus Pohlen, Adam Anthony Santoro | 2025-01-07 |
| 12159221 | Training an unsupervised memory-based prediction system to learn compressed representations of an environment | Gregory Duncan Wayne, Chia-Chun Hung, David Antony Amos, Mehdi Mirza Mohammadi, Arun Ahuja | 2024-12-03 |
| 12032523 | Compressed sensing using neural networks | Yan Wu, Mihaela Rosca | 2024-07-09 |
| 11983617 | Scalable and compressive neural network data storage system | Jack William Rae, Sergey Bartunov | 2024-05-14 |
| 11897133 | Deep reinforcement learning for robotic manipulation | Sergey Levine, Ethan Holly, Shixiang Gu | 2024-02-13 |
| 11875258 | Selecting reinforcement learning actions using a low-level controller | Nicolas Manfred Otto Heess, Gregory Duncan Wayne, Yuval Tassa | 2024-01-16 |
| 11829884 | Augmenting attentioned-based neural networks to selectively attend to past inputs | Jack William Rae, Anna Potapenko | 2023-11-28 |
| 11803750 | Continuous control with deep reinforcement learning | Jonathan James Hunt, Alexander Pritzel, Nicolas Manfred Otto Heess, Tom Erez, Yuval Tassa +2 more | 2023-10-31 |
| 11769049 | Controlling agents over long time scales using temporal value transport | Gregory Duncan Wayne, Chia-Chun Hung, Joshua Simon Abramson | 2023-09-26 |
| 11741334 | Data-efficient reinforcement learning for continuous control tasks | Martin Riedmiller, Roland Hafner, Mel Vecerik, Thomas Lampe, Ivaylo Popov +2 more | 2023-08-29 |
| 11400587 | Deep reinforcement learning for robotic manipulation | Sergey Levine, Ethan Holly, Shixiang Gu | 2022-08-02 |
| 11288568 | Reinforcement learning using advantage estimates | Shixiang Gu, Ilya Sutskever, Sergey Levine | 2022-03-29 |
| 11210585 | Selecting reinforcement learning actions using a low-level controller | Nicolas Manfred Otto Heess, Gregory Duncan Wayne, Yuval Tassa | 2021-12-28 |
| 11151443 | Augmenting neural networks with sparsely-accessed external memory | Ivo Danihelka, Gregory Duncan Wayne, Fu-Min Wang, Edward Thomas Grefenstette, Jack William Rae +3 more | 2021-10-19 |
| 10885426 | Augmenting neural networks with external memory | Adam Anthony Santoro, Daniel Pieter Wiestra, Sergey Bartunov, Ivo Danihelka | 2021-01-05 |
| 10846588 | Scalable and compressive neural network data storage system | Jack William Rae, Sergey Bartunov | 2020-11-24 |
| 10789511 | Controlling agents over long time scales using temporal value transport | Gregory Duncan Wayne, Chia-Chun Hung, Joshua Simon Abramson | 2020-09-29 |
| 10776692 | Continuous control with deep reinforcement learning | Jonathan James Hunt, Alexander Pritzel, Nicolas Manfred Otto Heess, Tom Erez, Yuval Tassa +2 more | 2020-09-15 |
| 10664725 | Data-efficient reinforcement learning for continuous control tasks | Martin Riedmiller, Roland Hafner, Mel Vecerik, Thomas Lampe, Ivaylo Popov +2 more | 2020-05-26 |