| Grandmaster level in StarCraft II using multi-agent reinforcement learning O Vinyals, I Babuschkin, WM Czarnecki, M Mathieu, A Dudzik, J Chung, ... Nature 575 (7782), 350-354, 2019 | 791 | 2019 |
| Alphastar: Mastering the real-time strategy game starcraft ii O Vinyals, I Babuschkin, J Chung, M Mathieu, M Jaderberg, ... DeepMind blog 2, 2019 | 311 | 2019 |
| Do deep neural networks learn facial action units when doing expression recognition? P Khorrami, T Paine, T Huang Proceedings of the IEEE international conference on computer vision …, 2015 | 219 | 2015 |
| Seq-nms for video object detection W Han*, P Khorrami*, TL Paine*, P Ramachandran, M Babaeizadeh, ... arXiv preprint arXiv:1602.08465, 2016 | 171 | 2016 |
| Playing hard exploration games by watching youtube Y Aytar, T Pfaff, D Budden, TL Paine, Z Wang, N de Freitas arXiv preprint arXiv:1805.11592, 2018 | 151 | 2018 |
| Optimized preload leakage-correction methods to improve the diagnostic accuracy of dynamic susceptibility-weighted contrast-enhanced perfusion MR imaging in posttreatment gliomas LS Hu, LC Baxter, DS Pinnaduwage, TL Paine, JP Karis, BG Feuerstein, ... American Journal of Neuroradiology 31 (1), 40-48, 2010 | 130 | 2010 |
| GPU asynchronous stochastic gradient descent to speed up neural network training TL Paine, H Jin, J Yang, Z Lin, T Huang arXiv preprint arXiv:1312.6186, 2013 | 93 | 2013 |
| How deep neural networks can improve emotion recognition on video data P Khorrami, T Le Paine, K Brady, C Dagli, TS Huang 2016 IEEE international conference on image processing (ICIP), 619-623, 2016 | 92 | 2016 |
| Fast wavenet generation algorithm TL Paine, P Khorrami, S Chang, Y Zhang, P Ramachandran, ... arXiv preprint arXiv:1611.09482, 2016 | 68 | 2016 |
| Fast generation for convolutional autoregressive models P Ramachandran*, TL Paine*, P Khorrami, M Babaeizadeh, S Chang, ... arXiv preprint arXiv:1704.06001, 2017 | 61 | 2017 |
| Large-scale visual speech recognition B Shillingford, Y Assael, MW Hoffman, T Paine, C Hughes, U Prabhu, ... arXiv preprint arXiv:1807.05162, 2018 | 58 | 2018 |
| Few-shot autoregressive density estimation: Towards learning to learn distributions S Reed, Y Chen, T Paine, A Oord, SM Eslami, D Rezende, O Vinyals, ... arXiv preprint arXiv:1710.10304, 2017 | 57 | 2017 |
| An analysis of unsupervised pre-training in light of recent advances TL Paine*, P Khorrami*, W Han, TS Huang arXiv preprint arXiv:1412.6597, 2014 | 52 | 2014 |
| Acme: A research framework for distributed reinforcement learning M Hoffman, B Shahriari, J Aslanides, G Barth-Maron, F Behbahani, ... arXiv preprint arXiv:2006.00979, 2020 | 27 | 2020 |
| Simultaneous dynamic and functional MRI scanning (SimulScan) of natural swallows TL Paine, CA Conway, GA Malandraki, BP Sutton Magnetic resonance in medicine 65 (5), 1247-1252, 2011 | 17 | 2011 |
| Making Efficient Use of Demonstrations to Solve Hard Exploration Problems TL Paine*, C Gulcehre*, B Shahriari, M Denil, M Hoffman, H Soyer, ... arXiv preprint arXiv:1909.01387, 2019 | 15 | 2019 |
| Hyperparameter selection for offline reinforcement learning TL Paine*, C Paduraru*, A Michi, C Gulcehre, K Zolna, A Novikov, Z Wang, ... arXiv preprint arXiv:2007.09055, 2020 | 13 | 2020 |
| Rl unplugged: Benchmarks for offline reinforcement learning C Gulcehre*, Z Wang*, A Novikov*, TL Paine*, SG Colmenarejo, K Zolna, ... arXiv preprint arXiv:2006.13888, 2020 | 13 | 2020 |
| Image classification using images with separate grayscale and color channels H Jin, T Le Paine, J Yang, Z Lin, JW Brandt US Patent 9,230,192, 2016 | 13 | 2016 |
| One-shot high-fidelity imitation: Training large-scale deep nets with rl TL Paine*, SG Colmenarejo*, Z Wang, S Reed, Y Aytar, T Pfaff, ... arXiv preprint arXiv:1810.05017, 2018 | 12 | 2018 |
Pooya KhorramiMIT Lincoln LaboratoryVerified email at ll.mit.edu
