Inventor · disambiguated record
Koray Kavukcuoglu
Also filed as: KAVUKCUOGLU KORAY
37 granted patents·8 pending applications·198 citations·filing 2011–2024
97Inventor score
Top patents by PatentIndex Score
45 records- 0197US9679258B2Methods and apparatus for reinforcement learningGOOGLE INC·Filed 2013·Granted Jun 13, 2017·68 cites·30 claims
- 0292US11049008B2Reinforcement learning using target neural networksDEEPMIND TECH LTD·Filed 2017·Granted Jun 29, 2021·10 cites·29 claims
- 0391US10223617B1Image processing with recurrent attentionDEEPMIND TECH LTD·Filed 2015·Granted Mar 5, 2019·9 cites·17 claims
- 0490US10445641B2Distributed training of reinforcement learning systemsDEEPMIND TECH LTD·Filed 2016·Granted Oct 15, 2019·18 cites·20 claims
- 0589US10346741B2Asynchronous deep reinforcement learningDEEPMIND TECH LTD·Filed 2018·Granted Jul 9, 2019·7 cites·22 claims
- 0689US10032089B2Spatial transformer modulesDEEPMIND TECH LTD·Filed 2016·Granted Jul 24, 2018·8 cites·22 claims
- 0789US8463025B2Distributed artificial intelligence services on a cell phoneMELVIN IAIN·Filed 2011·Granted Jun 11, 2013·28 cites·18 claims
- 0888US10748029B2Spatial transformer modulesDEEPMIND TECH LTD·Filed 2018·Granted Aug 18, 2020·6 cites·20 claims
- 0987US10679126B2Action selection for reinforcement learning using neural networksDEEPMIND TECH LTD·Filed 2019·Granted Jun 9, 2020·8 cites·19 claims
- 1084US12406031B1Generating predictions characterizing images using glimpses extracted from the imagesDEEPMIND TECH LTD·Filed 2024·Granted Sep 2, 2025·0 cites·20 claims
- 1184US10748041B1Image processing with recurrent attentionDEEPMIND TECH LTD·Filed 2019·Granted Aug 18, 2020·3 cites·20 claims
- 1283US11783182B2Asynchronous deep reinforcement learningDEEPMIND TECH LTD·Filed 2021·Granted Oct 10, 2023·1 cites·20 claims
- 1383US11354548B1Image processing with recurrent attentionDEEPMIND TECH LTD·Filed 2020·Granted Jun 7, 2022·1 cites·20 claims
- 1483US2024362481A1Reinforcement learning using baseline and policy neural networksDEEPMIND TECH LTD·Filed 2024·Application pending·0 cites
- 1582US11948075B2Generating discrete latent representations of input data itemsDEEPMIND TECH LTD·Filed 2018·Granted Apr 2, 2024·4 cites·20 claims
- 1681US11842281B2Reinforcement learning with auxiliary tasksDEEPMIND TECH LTD·Filed 2021·Granted Dec 12, 2023·1 cites·20 claims
- 1781US10956820B2Reinforcement learning with auxiliary tasksDEEPMIND TECH LTD·Filed 2019·Granted Mar 23, 2021·3 cites·20 claims
- 1881US10936946B2Asynchronous deep reinforcement learningDEEPMIND TECH LTD·Filed 2016·Granted Mar 2, 2021·3 cites·20 claims
- 1980US11734572B2Spatial transformer modulesDEEPMIND TECH LTD·Filed 2020·Granted Aug 22, 2023·1 cites·20 claims
- 2080US11074481B2Environment navigation using reinforcement learningDEEPMIND TECH LTD·Filed 2020·Granted Jul 27, 2021·2 cites·20 claims
- 2177US11907853B2Using hierarchical representations for neural network architecture searchingDEEPMIND TECH LTD·Filed 2018·Granted Feb 20, 2024·3 cites·19 claims
- 2277US2024144015A1Reinforcement learning with auxiliary tasksDEEPMIND TECH LTD·Filed 2023·Application pending·0 cites
- 2376US12299574B2Distributed training using actor-critic reinforcement learning with off-policy correction factorsDEEPMIND TECH LTD·Filed 2023·Granted May 13, 2025·0 cites·19 claims
- 2476US11941088B1Image processing of an environment to select an action to be performed by an agent interacting with the environmentDEEPMIND TECH LTD·Filed 2022·Granted Mar 26, 2024·0 cites·20 claims
- 2576US2024354566A1Generating discrete latent representations of input data itemsDEEPMIND TECH LTD·Filed 2024·Application pending·0 cites
- 2675US12462145B2Progressive neural networksDEEPMIND TECH LTD·Filed 2023·Granted Nov 4, 2025·0 cites·20 claims
- 2775US12020155B2Reinforcement learning using baseline and policy neural networksDEEPMIND TECH LTD·Filed 2022·Granted Jun 25, 2024·0 cites·20 claims
- 2875US10572776B2Environment navigation using reinforcement learningDEEPMIND TECH LTD·Filed 2019·Granted Feb 25, 2020·2 cites·20 claims
- 2973US11593646B2Distributed training using actor-critic reinforcement learning with off-policy correction factorsDEEPMIND TECH LTD·Filed 2019·Granted Feb 28, 2023·2 cites·23 claims
- 3072US11868894B2Distributed training using actor-critic reinforcement learning with off-policy correction factorsDEEPMIND TECH LTD·Filed 2023·Granted Jan 9, 2024·0 cites·20 claims
- 3172US2024249146A1Using Hierarchical Representations for Neural Network Architecture SearchingDEEPMIND TECH LTD·Filed 2024·Application pending·0 cites
- 3271US2023090824A1Action selection for reinforcement learning using a manager neural network that generates goal vectors defining agent objectivesDEEPMIND TECH LTD·Filed 2022·Application pending·0 cites
- 3369US2021374538A1Reinforcement learning using target neural networksDEEPMIND TECH LTD·Filed 2021·Application pending·0 cites
- 3467US8838508B2Two-stage multiple kernel learning methodNEC LAB AMERICA INC·Filed 2012·Granted Sep 16, 2014·4 cites·2 claims
- 3566US11775804B2Progressive neural networksDEEPMIND TECH LTD·Filed 2021·Granted Oct 3, 2023·0 cites·20 claims
- 3665US11507827B2Distributed training of reinforcement learning systemsDEEPMIND TECH LTD·Filed 2019·Granted Nov 22, 2022·1 cites·20 claims
- 3763US11537887B2Action selection for reinforcement learning using a manager neural network that generates goal vectors defining agent objectivesDEEPMIND TECH LTD·Filed 2020·Granted Dec 27, 2022·0 cites·20 claims
- 3862US11715009B2Training neural networks using synthetic gradientsDEEPMIND TECH LTD·Filed 2017·Granted Aug 1, 2023·1 cites·18 claims
- 3961US8977579B2Latent factor dependency structure determinationNEC LAB AMERICA INC·Filed 2012·Granted Mar 10, 2015·3 cites·3 claims
- 4061US2021150355A1Training machine learning models using task selection policies to increase learning progressDEEPMIND TECH LTD·Filed 2021·Application pending·0 cites
- 4159US11334792B2Asynchronous deep reinforcement learningDEEPMIND TECH LTD·Filed 2019·Granted May 17, 2022·0 cites·20 claims
- 4259US10762421B2Whitened neural network layersDEEPMIND TECH LTD·Filed 2016·Granted Sep 1, 2020·1 cites·20 claims
- 4354US10936949B2Training machine learning models using task selection policies to increase learning progressDEEPMIND TECH LTD·Filed 2019·Granted Mar 2, 2021·0 cites·22 claims
- 4450US10949734B2Progressive neural networksDEEPMIND TECH LTD·Filed 2016·Granted Mar 16, 2021·0 cites·23 claims
- 4538US2015095017A1System and method for learning word embeddings using neural language modelsGOOGLE INC·Filed 2013·Application pending·0 cites
Identity basis: PatentsView inventor disambiguation (2025Q4-odp release). How scoring works →