| Learning from demonstrations for real world reinforcement learning T Hester, M Vecerik, O Pietquin, M Lanctot, T Schaul, B Piot, A Sendonaris, ... | 695* | 2017 |
| Deep reinforcement learning in large discrete action spaces G Dulac-Arnold, R Evans, H van Hasselt, P Sunehag, T Lillicrap, J Hunt, ... arXiv preprint arXiv:1512.07679, 2015 | 322* | 2015 |
| Challenges of real-world reinforcement learning G Dulac-Arnold, D Mankowitz, T Hester ICML Workshop on Real-Life RL, 2019 | 249 | 2019 |
| The predictron: End-to-end learning and planning D Silver, H Hasselt, M Hessel, T Schaul, A Guez, T Harley, ... International Conference on Machine Learning, 3191-3199, 2017 | 216 | 2017 |
| Datum-wise classification: a sequential approach to sparsity G Dulac-Arnold, L Denoyer, P Preux, P Gallinari Joint European conference on machine learning and knowledge discovery in …, 2011 | 46 | 2011 |
| Challenges of real-world reinforcement learning: definitions, benchmarks and analysis G Dulac-Arnold, N Levine, DJ Mankowitz, J Li, C Paduraru, S Gowal, ... Machine Learning, 1-50, 2021 | 41* | 2021 |
| RL Unplugged: A Collection of Benchmarks for Offline Reinforcement Learning C Gulcehre, Z Wang, A Novikov, T Paine, S Gómez, K Zolna, R Agarwal, ... Advances in Neural Information Processing Systems 33, 2020 | 36* | 2020 |
| Text classification: A sequential reading approach G Dulac-Arnold, L Denoyer, P Gallinari European Conference on Information Retrieval, 411-423, 2011 | 35 | 2011 |
| Model-based offline planning A Argenson, G Dulac-Arnold ICLR 2021, 2020 | 27 | 2020 |
| Deep reinforcement learning with attention for slate markov decision processes with high-dimensional states and actions P Sunehag, R Evans, G Dulac-Arnold, Y Zwols, D Visentin, B Coppin arXiv preprint arXiv:1512.01124, 2015 | 24 | 2015 |
| Sequential approaches for learning datum-wise sparse representations G Dulac-Arnold, L Denoyer, P Preux, P Gallinari Machine learning 89 (1-2), 87-122, 2012 | 22 | 2012 |
| Sequentially Generated Instance-Dependent Image Representations for Classification M Cord, N Thome, L Denoyer, G Dulac-Arnold ICLR, 2013 | 21* | 2013 |
| Fast reinforcement learning with large action sets using error-correcting output codes for mdp factorization G Dulac-Arnold, L Denoyer, P Preux, P Gallinari Joint European Conference on Machine Learning and Knowledge Discovery in …, 2012 | 17 | 2012 |
| Deep multi-class learning from label proportions G Dulac-Arnold, N Zeghidour, M Cuturi, L Beyer, JP Vert arXiv preprint arXiv:1905.12909, 2019 | 10 | 2019 |
| Differentiable deep clustering with cluster size constraints A Genevay, G Dulac-Arnold, JP Vert arXiv preprint arXiv:1910.09036, 2019 | 9 | 2019 |
| Learning to run a Power Network Challenge: a Retrospective Analysis A Marot, B Donnot, G Dulac-Arnold, A Kelly, A O'Sullivan, J Viebahn, ... arXiv preprint arXiv:2103.03104, 2021 | 6 | 2021 |
| ICUBAM: ICU Bed Availability Monitoring and analysis in the Grand Est region of France during the COVID-19 epidemic. L Bonnasse-Gahot, M Dénčs, G Dulac-Arnold, S Girgin, F Husson, ... | 4 | 2020 |
| Learning dynamics models for model predictive agents M Lutter, L Hasenclever, A Byravan, G Dulac-Arnold, P Trochim, N Heess, ... arXiv preprint arXiv:2109.14311, 2021 | 2 | 2021 |
| AI-based mobile application to fight antibiotic resistance M Pascucci, G Royer, J Adamek, M Al Asmar, D Aristizabal, L Blanche, ... Nature communications 12 (1), 1-10, 2021 | 2* | 2021 |
| Optimizing data center controls using neural networks RA Evans, J Gao, MC Ryan, G Dulac-Arnold, JK Scholz, TA Hester US Patent 10,643,121, 2020 | 2 | 2020 |
Todd HesterApplied Scientist, Amazon ScoutVerified email at amazon.com
