| Offline rl without off-policy evaluation D Brandfonbrener, W Whitney, R Ranganath, J Bruna Advances in neural information processing systems 34, 4933-4946, 2021 | 239 | 2021 |
| Frequentist regret bounds for randomized least-squares value iteration A Zanette*, D Brandfonbrener*, E Brunskill, M Pirotta, A Lazaric International Conference on Artificial Intelligence and Statistics, 1954-1964, 2020 | 178 | 2020 |
| Repeat after me: Transformers are better than state space models at copying S Jelassi, D Brandfonbrener, SM Kakade, E Malach arXiv preprint arXiv:2402.01032, 2024 | 152 | 2024 |
| Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning D Yarats*, D Brandfonbrener*, H Liu, M Laskin, P Abbeel, A Lazaric, ... arXiv preprint arXiv:2201.13425, 2022 | 141 | 2022 |
| Soap: Improving and stabilizing shampoo using adam N Vyas, D Morwani, R Zhao, M Kwun, I Shapira, D Brandfonbrener, ... arXiv preprint arXiv:2409.11321, 2024 | 121 | 2024 |
| When does return-conditioned supervised learning work for offline reinforcement learning? D Brandfonbrener, A Bietti, J Buckman, R Laroche, J Bruna Advances in Neural Information Processing Systems 35, 1542-1553, 2022 | 120 | 2022 |
| Deconstructing what makes a good optimizer for language models R Zhao*, D Morwani*, D Brandfonbrener*, N Vyas*, S Kakade arXiv preprint arXiv:2407.07972, 2024 | 52 | 2024 |
| Psychrnn: An accessible and flexible python package for training recurrent neural network models on cognitive tasks DB Ehrlich, JT Stone, D Brandfonbrener, A Atanasov, JD Murray eneuro 8 (1), 2021 | 40 | 2021 |
| VerMCTS: Synthesizing Multi-Step Programs using a Verifier, a Large Language Model, and Tree Search D Brandfonbrener, S Henniger, S Raja, T Prasad, C Loughridge, ... arXiv preprint arXiv:2402.08147, 2024 | 34* | 2024 |
| Evaluating representations by the complexity of learning low-loss predictors WF Whitney, MJ Song, D Brandfonbrener, J Altosaar, K Cho arXiv preprint arXiv:2009.07368, 2020 | 32 | 2020 |
| Geometric insights into the convergence of nonlinear TD learning D Brandfonbrener, J Bruna International Conference on Learning Representations (ICLR), 2020 | 31* | 2020 |
| Inverse dynamics pretraining learns good representations for multitask imitation D Brandfonbrener, O Nachum, J Bruna Advances in Neural Information Processing Systems 36, 2023 | 24 | 2023 |
| Offline Contextual Bandits with Overparameterized Models D Brandfonbrener, WF Whitney, R Ranganath, J Bruna International Conference on Machine Learning (ICML), 2021, 2020 | 21* | 2020 |
| Color-filter: Conditional loss reduction filtering for targeted language model pre-training D Brandfonbrener, H Zhang, A Kirsch, JR Schwarz, S Kakade Advances in Neural Information Processing Systems 37, 97618-97649, 2024 | 18 | 2024 |
| Universal length generalization with turing programs K Hou, D Brandfonbrener, S Kakade, S Jelassi, E Malach arXiv preprint arXiv:2407.03310, 2024 | 14 | 2024 |
| Visual backtracking teleoperation: A data collection protocol for offline image-based reinforcement learning D Brandfonbrener, S Tu, A Singh, S Welker, C Boodoo, N Matni, J Varley arXiv preprint arXiv:2210.02343, 2022 | 14 | 2022 |
| Mixture of parrots: Experts improve memorization more than reasoning S Jelassi, C Mohri, D Brandfonbrener, A Gu, N Vyas, N Anand, ... arXiv preprint arXiv:2410.19034, 2024 | 12 | 2024 |
| Q-probe: A lightweight approach to reward maximization for language models K Li, S Jelassi, H Zhang, S Kakade, M Wattenberg, D Brandfonbrener arXiv preprint arXiv:2402.14688, 2024 | 12 | 2024 |
| Quantile filtered imitation learning D Brandfonbrener, WF Whitney, R Ranganath, J Bruna arXiv preprint arXiv:2112.00950, 2021 | 12 | 2021 |
| The art of scaling reinforcement learning compute for llms D Khatri, L Madaan, R Tiwari, R Bansal, SS Duvvuri, M Zaheer, IS Dhillon, ... arXiv preprint arXiv:2510.13786, 2025 | 11 | 2025 |
Sham M KakadeHarvard UniversityVerified email at seas.harvard.edu
