Scaling Instructable Agents Across Many Simulated Worlds.

Karol Gregor

SIMA Team Maria Abi Raad Arun Ahuja Catarina Barros Frederic Besse Andrew Bolt Adrian Bolton Bethanie Brownfield Gavin Buttimore Max Cant Sarah Chakera Stephanie C. Y. Chan Jeff Clune Adrian Collister Vikki Copeman Alex Cullum Ishita Dasgupta 0001 Dario de Cesare Julia Di Trapani Yani Donchev Emma Dunleavy Martin Engelcke Ryan Faulkner 0001 Frankie Garcia Charles Gbadamosi Zhitao Gong Lucy Gonzalez Kshitij Gupta Karol Gregor Arne Olav Hallingstad Tim Harley Sam Haves Felix Hill Ed Hirst Drew A. Hudson Jony Hudson Steph Hughes-Fitt Danilo J. Rezende Mimi Jasarevic Laura Kampis Nan Rosemary Ke Thomas Keck Junkyung Kim Oscar Knagg Kavya Kopparapu Andrew K. Lampinen Shane Legg Alexander Lerchner Marjorie Limont Yulan Liu Maria Loks-Thompson Joseph Marino Kathryn Martin Cussons Loic Matthey Siobhan Mcloughlin Piermaria Mendolicchio Hamza Merzic Anna Mitenkova Alexandre Moufarek Valéria Oliveira Yanko Gitahy Oliveira Hannah Openshaw Renke Pan Aneesh Pappu Alex Platonov Ollie Purkiss David P. Reichert John Reid Pierre Harvey Richemond Tyson Roberts Giles Ruscoe Jaume Sanchez Elias Tasha Sandars Daniel P. Sawyer Tim Scholtes Guy Simmons Daniel Slater Hubert Soyer Heiko Strathmann Peter Stys Allison C. Tam Denis Teplyashin Tayfun Terzi Davide Vercelli Bojan Vujatovic Marcus Wainwright Jane X. Wang Zhengdong Wang Daan Wierstra Duncan Williams Nathaniel Wong Sarah York Nick Young Scaling Instructable Agents Across Many Simulated Worlds. 2024 abs/2404.10179 CoRR https://doi.org/10.48550/arXiv.2404.10179 db/journals/corr/corr2404.html#abs-2404-10179

Jakob Bauer Kate Baumli Feryal M. P. Behbahani Avishkar Bhoopchand Nathalie Bradley-Schmieg Michael Chang Natalie Clay Adrian Collister Vibhavari Dasagi Lucy Gonzalez Karol Gregor Edward Hughes 0001 Sheleem Kashem Maria Loks-Thompson Hannah Openshaw Jack Parker-Holder Shreya Pathak Nicolas Perez Nieves Nemanja Rakicevic Tim Rocktäschel Yannick Schroecker Satinder Singh 0001 Jakub Sygnowski Karl Tuyls Sarah York Alexander Zacherl Lei M. Zhang Human-Timescale Adaptation in an Open-Ended Task Space. 1887-1935 2023 ICML https://proceedings.mlr.press/v202/bauer23a.html conf/icml/2023 db/conf/icml/icml2023.html#BauerBBBBCCCDGG23

Adaptive Agent Team Jakob Bauer Kate Baumli Satinder Baveja Feryal M. P. Behbahani Avishkar Bhoopchand Nathalie Bradley-Schmieg Michael Chang Natalie Clay Adrian Collister Vibhavari Dasagi Lucy Gonzalez Karol Gregor Edward Hughes 0001 Sheleem Kashem Maria Loks-Thompson Hannah Openshaw Jack Parker-Holder Shreya Pathak Nicolas Perez Nieves Nemanja Rakicevic Tim Rocktäschel Yannick Schroecker Jakub Sygnowski Karl Tuyls Sarah York Alexander Zacherl Lei Zhang Human-Timescale Adaptation in an Open-Ended Task Space. 2023 abs/2301.07608 CoRR https://doi.org/10.48550/arXiv.2301.07608 db/journals/corr/corr2301.html#abs-2301-07608

Karol Gregor Frederic Besse Self-Organizing Intelligent Matter: A blueprint for an AI generating algorithm. 2021 abs/2101.07627 CoRR https://arxiv.org/abs/2101.07627 db/journals/corr/corr2101.html#abs-2101-07627

Danilo J. Rezende Ivo Danihelka George Papamakarios Nan Rosemary Ke Ray Jiang Theophane Weber Karol Gregor Hamza Merzic Fabio Viola Jane Wang 0001 Jovana Mitrovic Frederic Besse Ioannis Antonoglou Lars Buesing Causally Correct Partial Models for Reinforcement Learning. 2020 abs/2002.02836 CoRR https://arxiv.org/abs/2002.02836 db/journals/corr/corr2002.html#abs-2002-02836

Karol Gregor Finding online neural update rules by learning to remember. 2020 abs/2003.03124 CoRR https://arxiv.org/abs/2003.03124 db/journals/corr/corr2003.html#abs-2003-03124

Karol Gregor George Papamakarios Frederic Besse Lars Buesing Theophane Weber Temporal Difference Variational Auto-Encoder. 2019 ICLR https://openreview.net/forum?id=S1x4ghC9tQ conf/iclr/2019 db/conf/iclr/iclr2019.html#GregorPBBW19 Arthur Guez Mehdi Mirza Karol Gregor Rishabh Kabra Sébastien Racanière Theophane Weber David Raposo Adam Santoro Laurent Orseau Tom Eccles Greg Wayne David Silver 0001 Timothy P. Lillicrap An Investigation of Model-Free Planning. 2464-2473 2019 ICML http://proceedings.mlr.press/v97/guez19a.html conf/icml/2019 db/conf/icml/icml2019.html#GuezMGKRWRSOEWS19 Karol Gregor Danilo Jimenez Rezende Frederic Besse Yan Wu 0010 Hamza Merzic Aäron van den Oord Shaping Belief States with Generative Environment Models for RL. 13475-13487 2019 NeurIPS https://proceedings.neurips.cc/paper/2019/hash/2c048d74b3410237704eb7f93a10c9d7-Abstract.html http://papers.nips.cc/paper/9503-shaping-belief-states-with-generative-environment-models-for-rl conf/nips/2019 db/conf/nips/nips2019.html#GregorRBWMO19

Arthur Guez Mehdi Mirza Karol Gregor Rishabh Kabra Sébastien Racanière Théophane Weber David Raposo Adam Santoro Laurent Orseau Tom Eccles Greg Wayne David Silver 0001 Timothy P. Lillicrap An investigation of model-free planning. 2019 abs/1901.03559 CoRR http://arxiv.org/abs/1901.03559 db/journals/corr/corr1901.html#abs-1901-03559

Karol Gregor Danilo Jimenez Rezende Frederic Besse Yan Wu 0010 Hamza Merzic Aäron van den Oord Shaping Belief States with Generative Environment Models for RL. 2019 abs/1906.09237 CoRR http://arxiv.org/abs/1906.09237 db/journals/corr/corr1906.html#abs-1906-09237

Yan Wu 0010 Gregory Wayne Karol Gregor Timothy P. Lillicrap Learning Attractor Dynamics for Generative Memory. 9401-9410 2018 NeurIPS https://proceedings.neurips.cc/paper/2018/hash/6e4243f5511fd6ef0f03e9f386d54403-Abstract.html http://papers.nips.cc/paper/8149-learning-attractor-dynamics-for-generative-memory conf/nips/2018 db/conf/nips/nips2018.html#WuWGL18

Lars Buesing Theophane Weber Sébastien Racanière S. M. Ali Eslami Danilo Jimenez Rezende David P. Reichert Fabio Viola Frederic Besse Karol Gregor Demis Hassabis Daan Wierstra Learning and Querying Fast Generative Models for Reinforcement Learning. 2018 abs/1802.03006 CoRR http://arxiv.org/abs/1802.03006 db/journals/corr/corr1802.html#abs-1802-03006

Karol Gregor Frederic Besse Temporal Difference Variational Auto-Encoder. 2018 abs/1806.03107 CoRR http://arxiv.org/abs/1806.03107 db/journals/corr/corr1806.html#abs-1806-03107

Yan Wu 0010 Greg Wayne Karol Gregor Timothy P. Lillicrap Learning Attractor Dynamics for Generative Memory. 2018 abs/1811.09556 CoRR http://arxiv.org/abs/1811.09556 db/journals/corr/corr1811.html#abs-1811-09556

Karol Gregor Danilo Jimenez Rezende Daan Wierstra Variational Intrinsic Control. 2017 ICLR (Workshop) https://openreview.net/forum?id=Skc-Fo4Yg conf/iclr/2017w db/conf/iclr/iclr2017w.html#GregorRW17

Benigno Uria Marc-Alexandre Côté Karol Gregor Iain Murray 0001 Hugo Larochelle Neural Autoregressive Distribution Estimation. 205:1-205:37 2016 17 J. Mach. Learn. Res. https://jmlr.org/papers/v17/16-272.html db/journals/jmlr/jmlr17.html#UriaCGML16

Danilo Jimenez Rezende Shakir Mohamed Ivo Danihelka Karol Gregor Daan Wierstra One-Shot Generalization in Deep Generative Models. 1521-1529 2016 ICML http://proceedings.mlr.press/v48/rezende16.html conf/icml/2016 db/conf/icml/icml2016.html#RezendeMDGW16 Karol Gregor Frederic Besse Danilo Jimenez Rezende Ivo Danihelka Daan Wierstra Towards Conceptual Compression. 3549-3557 2016 NIPS https://proceedings.neurips.cc/paper/2016/hash/4abe17a1c80cbdd2aa241b70840879de-Abstract.html http://papers.nips.cc/paper/6542-towards-conceptual-compression conf/nips/2016 db/conf/nips/nips2016.html#GregorBRDW16

Danilo Jimenez Rezende Shakir Mohamed Ivo Danihelka Karol Gregor Daan Wierstra One-Shot Generalization in Deep Generative Models. 2016 abs/1603.05106 CoRR http://arxiv.org/abs/1603.05106 db/journals/corr/corr1603.html#RezendeMDGW16

Karol Gregor Frederic Besse Danilo Jimenez Rezende Ivo Danihelka Daan Wierstra Towards Conceptual Compression. 2016 abs/1604.08772 CoRR http://arxiv.org/abs/1604.08772 db/journals/corr/corr1604.html#GregorBRDW16

Benigno Uria Marc-Alexandre Côté Karol Gregor Iain Murray 0001 Hugo Larochelle Neural Autoregressive Distribution Estimation. 2016 abs/1605.02226 CoRR http://arxiv.org/abs/1605.02226 db/journals/corr/corr1605.html#UriaCGML16

Kevin Jarrett Koray Kavukcuoglu Karol Gregor Yann LeCun What is the Best Feature Learning Procedure in Hierarchical Recognition Architectures? 2016 abs/1606.01535 CoRR http://arxiv.org/abs/1606.01535 db/journals/corr/corr1606.html#JarrettKGL16

Karol Gregor Danilo Jimenez Rezende Daan Wierstra Variational Intrinsic Control. 2016 abs/1611.07507 CoRR http://arxiv.org/abs/1611.07507 db/journals/corr/corr1611.html#GregorRW16

Mathieu Germain Karol Gregor Iain Murray 0001 Hugo Larochelle MADE: Masked Autoencoder for Distribution Estimation. 881-889 2015 ICML http://proceedings.mlr.press/v37/germain15.html conf/icml/2015 db/conf/icml/icml2015.html#GermainGML15 Tom Schaul Daniel Horgan Karol Gregor David Silver 0001 Universal Value Function Approximators. 1312-1320 2015 ICML http://proceedings.mlr.press/v37/schaul15.html conf/icml/2015 db/conf/icml/icml2015.html#SchaulHGS15 Karol Gregor Ivo Danihelka Alex Graves Danilo Jimenez Rezende Daan Wierstra DRAW: A Recurrent Neural Network For Image Generation. 1462-1471 2015 ICML http://proceedings.mlr.press/v37/gregor15.html conf/icml/2015 db/conf/icml/icml2015.html#GregorDGRW15

Mathieu Germain Karol Gregor Iain Murray 0001 Hugo Larochelle MADE: Masked Autoencoder for Distribution Estimation. 2015 abs/1502.03509 CoRR http://arxiv.org/abs/1502.03509 db/journals/corr/corr1502.html#GermainGML15

Karol Gregor Ivo Danihelka Alex Graves Daan Wierstra DRAW: A Recurrent Neural Network For Image Generation. 2015 abs/1502.04623 CoRR http://arxiv.org/abs/1502.04623 db/journals/corr/corr1502.html#GregorDGW15

Ilya Sutskever Rafal Józefowicz Karol Gregor Danilo Jimenez Rezende Timothy P. Lillicrap Oriol Vinyals Towards Principled Unsupervised Learning. 2015 abs/1511.06440 CoRR http://arxiv.org/abs/1511.06440 db/journals/corr/corr1511.html#SutskeverJGRLV15

Karol Gregor Ivo Danihelka Andriy Mnih Charles Blundell Daan Wierstra Deep AutoRegressive Networks. 1242-1250 2014 ICML http://proceedings.mlr.press/v32/gregor14.html conf/icml/2014 db/conf/icml/icml2014.html#GregorDMBW14 Andriy Mnih Karol Gregor Neural Variational Inference and Learning in Belief Networks. 1791-1799 2014 ICML http://proceedings.mlr.press/v32/mnih14.html conf/icml/2014 db/conf/icml/icml2014.html#MnihG14

Andriy Mnih Karol Gregor Neural Variational Inference and Learning in Belief Networks. 2014 abs/1402.0030 CoRR http://arxiv.org/abs/1402.0030 db/journals/corr/corr1402.html#MnihG14

Karol Gregor Andriy Mnih Daan Wierstra Deep AutoRegressive Networks. 2013 CoRR http://arxiv.org/abs/1310.8499 abs/1310.8499 db/journals/corr/corr1310.html#GregorMW13

Arthur Szlam Karol Gregor Yann LeCun Fast Approximations to Structured Sparse Coding and Applications to Object Classification. 200-213 2012 ECCV (5) https://doi.org/10.1007/978-3-642-33715-4_15 conf/eccv/2012-5 db/conf/eccv/eccv2012-5.html#SzlamGL12 Karol Gregor Dmitri B. Chklovskii A lattice filter model of the visual pathway. 1718-1726 2012 NIPS https://proceedings.neurips.cc/paper/2012/hash/31839b036f63806cba3f47b93af8ccb5-Abstract.html http://papers.nips.cc/paper/4759-a-lattice-filter-model-of-the-visual-pathway conf/nips/2012 db/conf/nips/nips2012.html#GregorC12

Arthur Szlam Karol Gregor Yann LeCun Fast approximations to structured sparse coding and applications to object classification http://arxiv.org/abs/1202.6384 2012 CoRR abs/1202.6384 db/journals/corr/corr1202.html#abs-1202-6384

Arthur Szlam Karol Gregor Yann LeCun Structured sparse coding via lateral inhibition. 1116-1124 2011 NIPS https://proceedings.neurips.cc/paper/2011/hash/fae0b27c451c728867a567e8c1bb4e53-Abstract.html http://papers.nips.cc/paper/4271-structured-sparse-coding-via-lateral-inhibition conf/nips/2011 db/conf/nips/nips2011.html#SzlamGL11

Karol Gregor Yann LeCun Efficient Learning of Sparse Invariant Representations http://arxiv.org/abs/1105.5307 2011 CoRR abs/1105.5307 db/journals/corr/corr1105.html#abs-1105-5307

Karol Gregor Yann LeCun Learning Representations by Maximizing Compression http://arxiv.org/abs/1108.1169 2011 CoRR abs/1108.1169 db/journals/corr/corr1108.html#abs-1108-1169

Karol Gregor Yann LeCun Learning Fast Approximations of Sparse Coding. 399-406 2010 ICML https://icml.cc/Conferences/2010/papers/449.pdf conf/icml/2010 db/conf/icml/icml2010.html#GregorL10 Koray Kavukcuoglu Pierre Sermanet Y-Lan Boureau Karol Gregor Michaël Mathieu Yann LeCun Learning Convolutional Feature Hierarchies for Visual Recognition. 1090-1098 2010 NIPS https://proceedings.neurips.cc/paper/2010/hash/a01610228fe998f515a72dd730294d87-Abstract.html http://papers.nips.cc/paper/4133-learning-convolutional-feature-hierarchies-for-visual-recognition conf/nips/2010 db/conf/nips/nips2010.html#KavukcuogluSBGML10

Karol Gregor Yann LeCun Emergence of Complex-Like Cells in a Temporal Product Network with Local Receptive Fields http://arxiv.org/abs/1006.0448 2010 CoRR abs/1006.0448 db/journals/corr/corr1006.html#abs-1006-0448

Karol Gregor Gregory Griffin Behavior and performance of the deep belief networks on image classification http://arxiv.org/abs/0912.0717 2009 CoRR abs/0912.0717 db/journals/corr/corr0912.html#abs-0912-0717

Arun Ahuja Ioannis Antonoglou Catarina Barros Jakob Bauer Kate Baumli Satinder Baveja Feryal M. P. Behbahani Frederic Besse Avishkar Bhoopchand Charles Blundell Andrew Bolt Adrian Bolton Y-Lan Boureau Nathalie Bradley-Schmieg Bethanie Brownfield Lars Buesing Gavin Buttimore Max Cant Dario de Cesare Sarah Chakera Stephanie C. Y. Chan Michael Chang Dmitri B. Chklovskii Natalie Clay Jeff Clune Adrian Collister Vikki Copeman Marc-Alexandre Côté Alex Cullum Kathryn Martin Cussons Ivo Danihelka Vibhavari Dasagi Ishita Dasgupta 0001 Yani Donchev Emma Dunleavy Tom Eccles Jaume Sanchez Elias Martin Engelcke S. M. Ali Eslami Ryan Faulkner 0001 Frankie Garcia Charles Gbadamosi Mathieu Germain Zhitao Gong Lucy Gonzalez Alex Graves Gregory Griffin Arthur Guez Kshitij Gupta Arne Olav Hallingstad Tim Harley Demis Hassabis Sam Haves Felix Hill Ed Hirst Daniel Horgan Drew A. Hudson Jony Hudson Edward Hughes 0001 Steph Hughes-Fitt Kevin Jarrett Mimi Jasarevic Ray Jiang Rafal Józefowicz Rishabh Kabra Laura Kampis Sheleem Kashem Koray Kavukcuoglu Nan Rosemary Ke Thomas Keck Junkyung Kim Oscar Knagg Kavya Kopparapu Andrew K. Lampinen Hugo Larochelle Yann LeCun Shane Legg Alexander Lerchner Timothy P. Lillicrap Marjorie Limont Yulan Liu Maria Loks-Thompson Joseph Marino Michaël Mathieu Loïc MattheyLoic Matthey Siobhan Mcloughlin Piermaria Mendolicchio Hamza Merzic Mehdi Mirza Anna Mitenkova Jovana Mitrovic Andriy Mnih Shakir Mohamed Alexandre Moufarek Iain Murray 0001 Nicolas Perez Nieves Valéria Oliveira Yanko Gitahy Oliveira Aäron van den Oord Hannah Openshaw Laurent Orseau Renke Pan George Papamakarios Aneesh Pappu Jack Parker-Holder Shreya Pathak Alex Platonov Ollie Purkiss Maria Abi Raad Sébastien Racanière Nemanja Rakicevic David Raposo David P. Reichert John Reid Danilo Jimenez RezendeDanilo J. Rezende Pierre H. RichemondPierre Harvey Richemond Tyson Roberts Tim Rocktäschel Giles Ruscoe Tasha Sandars Adam Santoro Daniel P. Sawyer Tom Schaul Tim Scholtes Yannick Schroecker Pierre Sermanet David Silver 0001 Guy Simmons Satinder Singh 0001 Daniel Slater Hubert Soyer Heiko Strathmann Peter Stys Ilya Sutskever Jakub Sygnowski Arthur Szlam Allison C. Tam Adaptive Agent Team SIMA Team Denis Teplyashin Tayfun Terzi Julia Di Trapani Karl Tuyls Benigno Uria Davide Vercelli Oriol Vinyals Fabio Viola Bojan Vujatovic Marcus Wainwright Jane X. WangJane Wang 0001 Zhengdong Wang Greg WayneGregory Wayne Theophane WeberThéophane Weber Daan Wierstra Duncan Williams Nathaniel Wong Yan Wu 0010 Sarah York Nick Young Alexander Zacherl Lei Zhang Lei M. Zhang