Issued Patents All Time
Showing 25 most recent of 39 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 12147899 | Training action selection neural networks using look-ahead search | Karen Simonyan, Julian Schrittwieser | 2024-11-19 |
| 12141677 | Environment prediction using reinforcement learning | Tom Schaul, Matteo Hessel, Hado Philip van Hasselt | 2024-11-12 |
| 12086714 | Training neural networks using a prioritized experience memory | Tom Schaul, John Quan | 2024-09-10 |
| 12067491 | Multi-agent reinforcement learning with matchmaking policies | Oriol Vinyals, Maxwell Elliot Jaderberg | 2024-08-20 |
| 12020155 | Reinforcement learning using baseline and policy neural networks | Volodymyr Mnih, Adrià Puigdomènech Badia, Alexander Benjamin Graves, Timothy James Alexander Harley, Koray Kavukcuoglu | 2024-06-25 |
| 11842281 | Reinforcement learning with auxiliary tasks | Volodymyr Mnih, Wojciech Czarnecki, Maxwell Elliot Jaderberg, Tom Schaul, Koray Kavukcuoglu | 2023-12-12 |
| 11836625 | Training action selection neural networks using look-ahead search | Karen Simonyan, Julian Schrittwieser | 2023-12-05 |
| 11836620 | Meta-gradient updates for training return functions for reinforcement learning systems | Zhongwen Xu, Hado Philip van Hasselt | 2023-12-05 |
| 11803750 | Continuous control with deep reinforcement learning | Timothy Paul Lillicrap, Jonathan James Hunt, Alexander Pritzel, Nicolas Manfred Otto Heess, Tom Erez +2 more | 2023-10-31 |
| 11783182 | Asynchronous deep reinforcement learning | Volodymyr Mnih, Adrià Puigdomènech Badia, Alexander Benjamin Graves, Timothy James Alexander Harley, Koray Kavukcuoglu | 2023-10-10 |
| 11651208 | Training action selection neural networks using a differentiable credit function | Zhongwen Xu, Hado Phillip van Hasselt, Joseph Varughese Modayil, Andre da Motta Salles Barreto | 2023-05-16 |
| 11627165 | Multi-agent reinforcement learning with matchmaking policies | Oriol Vinyals, Maxwell Elliot Jaderberg | 2023-04-11 |
| 11568250 | Training neural networks using a prioritized experience memory | Tom Schaul, John Quan | 2023-01-31 |
| 11507827 | Distributed training of reinforcement learning systems | Praveen Srinivasan, Rory Fearon, Cagdas Alcicek, Arun Sarath Nair, Samuel Blackwell +5 more | 2022-11-22 |
| 11449750 | Training action selection neural networks using look-ahead search | Karen Simonyan, Julian Schrittwieser | 2022-09-20 |
| 11334792 | Asynchronous deep reinforcement learning | Volodymyr Mnih, Adrià Puigdomènech Badia, Alexander Benjamin Graves, Timothy James Alexander Harley, Koray Kavukcuoglu | 2022-05-17 |
| 10956820 | Reinforcement learning with auxiliary tasks | Volodymyr Mnih, Wojciech Czarnecki, Maxwell Elliot Jaderberg, Tom Schaul, Koray Kavukcuoglu | 2021-03-23 |
| 10936946 | Asynchronous deep reinforcement learning | Volodymyr Mnih, Adrià Puigdomènech Badia, Alexander Benjamin Graves, Timothy James Alexander Harley, Koray Kavukcuoglu | 2021-03-02 |
| 10867242 | Selecting actions to be performed by a reinforcement learning agent using tree search | Thore Graepel, Shih-Chieh Huang, Arthur Clement Guez, Laurent Sifre, Ilya Sutskever +1 more | 2020-12-15 |
| 10860926 | Meta-gradient updates for training return functions for reinforcement learning systems | Zhongwen Xu, Hado Philip van Hasselt | 2020-12-08 |
| 10776692 | Continuous control with deep reinforcement learning | Timothy Paul Lillicrap, Jonathan James Hunt, Alexander Pritzel, Nicolas Manfred Otto Heess, Tom Erez +2 more | 2020-09-15 |
| 10733501 | Environment prediction using reinforcement learning | Tom Schaul, Matteo Hessel, Hado Philip van Hasselt | 2020-08-04 |
| 10650310 | Training neural networks using a prioritized experience memory | Tom Schaul, John Quan | 2020-05-12 |
| 10628733 | Selecting reinforcement learning actions using goals and observations | Tom Schaul, Daniel George Horgan, Karol Gregor | 2020-04-21 |
| 10445641 | Distributed training of reinforcement learning systems | Praveen Srinivasan, Rory Fearon, Cagdas Alcicek, Arun Sarath Nair, Samuel Blackwell +5 more | 2019-10-15 |