| 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 | 3067* | 2019 |
| Openai baselines P Dhariwal, C Hesse, O Klimov, A Nichol, M Plappert, A Radford, ... | 1569* | 2017 |
| On the opportunities and risks of foundation models R Bommasani, DA Hudson, E Adeli, R Altman, S Arora, S von Arx, ... arXiv preprint arXiv:2108.07258, 2021 | 658 | 2021 |
| Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation Y Wu, E Mansimov, RB Grosse, S Liao, J Ba Advances in Neural Information Processing Systems, 5283-5292, 2017 | 654 | 2017 |
| Backpropagation through the void: Optimizing control variates for black-box gradient estimation W Grathwohl, D Choi, Y Wu, G Roeder, D Duvenaud ICLR2018, 2017 | 251 | 2017 |
| On the quantitative analysis of decoder-based generative models Y Wu, Y Burda, R Salakhutdinov, R Grosse 5th International Conference on Learning Representations (ICLR 2017), 2016 | 238 | 2016 |
| Sticking the landing: Simple, lower-variance gradient estimators for variational inference G Roeder, Y Wu, DK Duvenaud Advances in Neural Information Processing Systems 30, 2017 | 197* | 2017 |
| Architectural complexity measures of recurrent neural networks S Zhang, Y Wu, T Che, Z Lin, R Memisevic, RR Salakhutdinov, Y Bengio Advances in neural information processing systems 29, 2016 | 172 | 2016 |
| On multiplicative integration with recurrent neural networks Y Wu, S Zhang, Y Zhang, Y Bengio, RR Salakhutdinov Advances in neural information processing systems 29, 2016 | 160 | 2016 |
| STDP-compatible approximation of backpropagation in an energy-based model Y Bengio, T Mesnard, A Fischer, S Zhang, Y Wu Neural computation 29 (3), 555-577, 2017 | 159* | 2017 |
| The Importance of Sampling in Meta-Reinforcement Learning B Stadie, G Yang, R Houthooft, P Chen, Y Duan, Y Wu, P Abbeel, ... Advances in Neural Information Processing Systems, 9299-9309, 2018 | 132* | 2018 |
| Understanding Short-Horizon Bias in Stochastic Meta-Optimization Y Wu, M Ren, R Liao, RB Grosse Sixth International Conference on Learning Representations (ICLR 2018), 2018 | 97 | 2018 |
| Solving quantitative reasoning problems with language models A Lewkowycz, A Andreassen, D Dohan, E Dyer, H Michalewski, ... arXiv preprint arXiv:2206.14858, 2022 | 51* | 2022 |
| Invariant Causal Representation Learning for Out-of-Distribution Generalization C Lu, Y Wu, JM Hernández-Lobato, B Schölkopf International Conference on Learning Representations, 2022 | 48* | 2022 |
| STaR: Bootstrapping reasoning with reasoning E Zelikman, Y Wu, ND Goodman arXiv preprint arXiv:2203.14465, 2022 | 43* | 2022 |
| IsarStep: a Benchmark for High-level Mathematical Reasoning W Li, L Yu, Y Wu, LC Paulson ICLR 2021, 2021 | 36* | 2021 |
| Path-normalized optimization of recurrent neural networks with relu activations Y Wu, B Neyshabur, RR Salakhutdinov, N Srebro Advances in Neural Information Processing Systems, 3477-3485, 2016 | 35* | 2016 |
| OPtions as REsponses: Grounding Behavioural Hierarchies in Multi-Agent Reinforcement Learning Y Wu, A Vezhnevets, M Eckstein, R Leblond, JZ Leibo ICML2020, 2020 | 33* | 2020 |
| Memorizing Transformers Y Wu, MN Rabe, DL Hutchins, C Szegedy International Conference on Learning Representations 2022, 2022 | 31 | 2022 |
| The scattering compositional learner: Discovering objects, attributes, relationships in analogical reasoning Y Wu, H Dong, R Grosse, J Ba arXiv preprint arXiv:2007.04212, 2020 | 26 | 2020 |
Roger GrosseAssociate Professor, University of TorontoVerified email at cs.toronto.edu
