| Grandmaster level in StarCraft II using multi-agent reinforcement learning O Vinyals*, I Babuschkin*, WM Czarnecki*, M Mathieu*, A Dudzik*, ... Nature 575, 350–354, 2019 | 5377* | 2019 |
| Value-decomposition networks for cooperative multi-agent learning P Sunehag, G Lever, A Gruslys, WM Czarnecki, V Zambaldi, M Jaderberg, ... AAMAS 2018, 2017 | 1928 | 2017 |
| Reinforcement learning with unsupervised auxiliary tasks M Jaderberg*, V Mnih*, WM Czarnecki*, T Schaul, JZ Leibo, D Silver, ... ICLR 2017, 2017 | 1454 | 2017 |
| Human-level performance in 3D multiplayer games with population-based reinforcement learning M Jaderberg*, WM Czarnecki*, I Dunning*, L Marris, G Lever, ... Science 364 (6443), 859-865, 2019 | 1010 | 2019 |
| On loss functions for deep neural networks in classification K Janocha, WM Czarnecki TFML 2017, 2017 | 963 | 2017 |
| Progress & Compress: A scalable framework for continual learning J Schwarz, J Luketina, WM Czarnecki, A Grabska-Barwinska, YW Teh, ... ICML 2018, 2018 | 957 | 2018 |
| Population based training of neural networks M Jaderberg, V Dalibard, S Osindero, WM Czarnecki, J Donahue, ... arXiv preprint arXiv:1711.09846, 2017 | 930 | 2017 |
| Distral: Robust Multitask Reinforcement Learning YW Teh, V Bapst, WM Czarnecki, J Quan, J Kirkpatrick, R Hadsell, ... NIPS 2017, 2017 | 633 | 2017 |
| Decoupled neural interfaces using synthetic gradients M Jaderberg, WM Czarnecki, S Osindero, O Vinyals, A Graves, ... ICML 2017, 2017 | 435 | 2017 |
| Grounded language learning in a simulated 3d world KM Hermann, F Hill, S Green, F Wang, R Faulkner, H Soyer, D Szepesvari, ... CoRR, abs/1706.06551, 2017 | 347* | 2017 |
| Multi-task deep reinforcement learning with popart M Hessel, H Soyer, L Espeholt, W Czarnecki, S Schmitt, H van Hasselt AAAI 2019, 2018 | 323 | 2018 |
| Sobolev Training for Neural Networks WM Czarnecki, S Osindero, M Jaderberg, G Świrszcz, R Pascanu NIPS 2017, 2017 | 285 | 2017 |
| Open-ended Learning in Symmetric Zero-sum Games D Balduzzi, M Garnelo, Y Bachrach, WM Czarnecki, J Perolat, ... ICML 2019, 2019 | 189 | 2019 |
| Adapting auxiliary losses using gradient similarity Y Du, WM Czarnecki, SM Jayakumar, R Pascanu, B Lakshminarayanan NeurIPS 2018 MetaLearning Workshop, 2018 | 168 | 2018 |
| Discovering Reinforcement Learning Algorithms J Oh, M Hessel, WM Czarnecki, Z Xu, H van Hasselt, S Singh, D Silver NeurIPS 2020, 2020 | 165 | 2020 |
| Open-Ended Learning Leads to Generally Capable Agents OEL Team, A Stooke, A Mahajan, C Barros, C Deck, J Bauer, J Sygnowski, ... arXiv preprint arXiv:2107.12808, 2021 | 164 | 2021 |
| Kickstarting Deep Reinforcement Learning S Schmitt, JJ Hudson, A Zidek, S Osindero, C Doersch, WM Czarnecki, ... NIPS 2018 DL Workshop, 2018 | 152 | 2018 |
| Distilling Policy Distillation WM Czarnecki, R Pascanu, S Osindero, SM Jayakumar, G Swirszcz, ... AISTATS 2019, 2019 | 151 | 2019 |
| α-Rank: Multi-Agent Evaluation by Evolution S Omidshafiei, C Papadimitriou, G Piliouras, K Tuyls, M Rowland, ... Nature Scientific Reports, 2019 | 143 | 2019 |
| Multiplicative interactions and where to find them SM Jayakumar, WM Czarnecki, J Menick, J Schwarz, J Rae, S Osindero, ... ICLR 2020, 2019 | 136 | 2019 |
Max JaderbergChief AI Officer, Isomorphic LabsAdresse e-mail validée de robots.ox.ac.uk