| 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 | 3260* | 2019 |
| Reinforcement learning with unsupervised auxiliary tasks M Jaderberg*, V Mnih*, WM Czarnecki*, T Schaul, JZ Leibo, D Silver, ... ICLR 2017, 2017 | 1161 | 2017 |
| Value-decomposition networks for cooperative multi-agent learning P Sunehag, G Lever, A Gruslys, WM Czarnecki, V Zambaldi, M Jaderberg, ... AAMAS 2018, 2017 | 980 | 2017 |
| On loss functions for deep neural networks in classification K Janocha, WM Czarnecki TFML 2017, 2017 | 706 | 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 | 694 | 2019 |
| Population based training of neural networks M Jaderberg, V Dalibard, S Osindero, WM Czarnecki, J Donahue, ... arXiv preprint arXiv:1711.09846, 2017 | 668 | 2017 |
| Progress & Compress: A scalable framework for continual learning J Schwarz, J Luketina, WM Czarnecki, A Grabska-Barwinska, YW Teh, ... ICML 2018, 2018 | 583 | 2018 |
| Distral: Robust Multitask Reinforcement Learning YW Teh, V Bapst, WM Czarnecki, J Quan, J Kirkpatrick, R Hadsell, ... NIPS 2017, 2017 | 489 | 2017 |
| Decoupled neural interfaces using synthetic gradients M Jaderberg, WM Czarnecki, S Osindero, O Vinyals, A Graves, ... ICML 2017, 2017 | 318 | 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 | 280* | 2017 |
| Multi-task deep reinforcement learning with popart M Hessel, H Soyer, L Espeholt, W Czarnecki, S Schmitt, H van Hasselt AAAI 2019, 2018 | 218 | 2018 |
| Sobolev Training for Neural Networks WM Czarnecki, S Osindero, M Jaderberg, G Świrszcz, R Pascanu NIPS 2017, 2017 | 181 | 2017 |
| Open-ended Learning in Symmetric Zero-sum Games D Balduzzi, M Garnelo, Y Bachrach, WM Czarnecki, J Perolat, ... ICML 2019, 2019 | 111 | 2019 |
| Adapting auxiliary losses using gradient similarity Y Du, WM Czarnecki, SM Jayakumar, R Pascanu, B Lakshminarayanan NeurIPS 2018 MetaLearning Workshop, 2018 | 102 | 2018 |
| Kickstarting Deep Reinforcement Learning S Schmitt, JJ Hudson, A Zidek, S Osindero, C Doersch, WM Czarnecki, ... NIPS 2018 DL Workshop, 2018 | 100 | 2018 |
| α-Rank: Multi-Agent Evaluation by Evolution S Omidshafiei, C Papadimitriou, G Piliouras, K Tuyls, M Rowland, ... Nature Scientific Reports, 2019 | 95 | 2019 |
| Local minima in training of neural networks G Swirszcz, WM Czarnecki, R Pascanu arXiv preprint arXiv:1611.06310, 2016 | 93* | 2016 |
| Learning to SMILE (s) S Jastrzebski, D Lesniak, WM Czarnecki ICLR 2016 Workshop track, 2016 | 88* | 2016 |
| Information asymmetry in KL-regularized RL A Galashov, S Jayakumar, L Hasenclever, D Tirumala, J Schwarz, ... ICLR 2019, 2018 | 83 | 2018 |
| Discovering Reinforcement Learning Algorithms J Oh, M Hessel, WM Czarnecki, Z Xu, H van Hasselt, S Singh, D Silver NeurIPS 2020, 2020 | 82 | 2020 |
Max JaderbergIsomorphic LabsVerified email at robots.ox.ac.uk
