| Offline reinforcement learning: Tutorial, review, and perspectives on open problems S Levine, A Kumar, G Tucker, J Fu arXiv preprint arXiv:2005.01643, 2020 | 1654 | 2020 |
| Conservative q-learning for offline reinforcement learning A Kumar, A Zhou, G Tucker, S Levine Advances in Neural Information Processing Systems 33, 1179-1191, 2020 | 1495 | 2020 |
| Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction A Kumar, J Fu, G Tucker, S Levine NeuRIPS 2019, arXiv:1906.00949, 2019 | 937 | 2019 |
| D4rl: Datasets for deep data-driven reinforcement learning J Fu, A Kumar, O Nachum, G Tucker, S Levine arXiv preprint arXiv:2004.07219, 2020 | 924 | 2020 |
| Gemini: a family of highly capable multimodal models G Team, R Anil, S Borgeaud, Y Wu, JB Alayrac, J Yu, R Soricut, ... arXiv preprint arXiv:2312.11805, 2023 | 564 | 2023 |
| Advantage-weighted regression: Simple and scalable off-policy reinforcement learning XB Peng, A Kumar, G Zhang, S Levine arXiv preprint arXiv:1910.00177, 2019 | 421 | 2019 |
| Combo: Conservative offline model-based policy optimization T Yu, A Kumar, R Rafailov, A Rajeswaran, S Levine, C Finn Advances in neural information processing systems 34, 28954-28967, 2021 | 326 | 2021 |
| Trainable calibration measures for neural networks from kernel mean embeddings A Kumar, S Sarawagi, U Jain International Conference on Machine Learning, 2805-2814, 2018 | 261 | 2018 |
| Graph Normalizing Flows J Liu, A Kumar, J Ba, J Kiros, K Swersky NeurIPS 2019, arxiv:1905.13177, 2019 | 260* | 2019 |
| Opal: Offline primitive discovery for accelerating offline reinforcement learning A Ajay, A Kumar, P Agrawal, S Levine, O Nachum arXiv preprint arXiv:2010.13611, 2020 | 153 | 2020 |
| Diagnosing Bottlenecks in Deep Q-learning Algorithms J Fu, A Kumar, M Soh, S Levine International Conference on Machine Learning (ICML) 2019, https://arxiv.org …, 2019 | 147 | 2019 |
| Conservative safety critics for exploration H Bharadhwaj, A Kumar, N Rhinehart, S Levine, F Shkurti, A Garg arXiv preprint arXiv:2010.14497, 2020 | 121 | 2020 |
| When should we prefer offline reinforcement learning over behavioral cloning? A Kumar, J Hong, A Singh, S Levine arXiv preprint arXiv:2204.05618, 2022 | 116* | 2022 |
| Discor: Corrective feedback in reinforcement learning via distribution correction A Kumar, A Gupta, S Levine Advances in Neural Information Processing Systems 33, 18560-18572, 2020 | 106 | 2020 |
| Cog: Connecting new skills to past experience with offline reinforcement learning A Singh, A Yu, J Yang, J Zhang, A Kumar, S Levine arXiv preprint arXiv:2010.14500, 2020 | 97 | 2020 |
| Why generalization in rl is difficult: Epistemic pomdps and implicit partial observability D Ghosh, J Rahme, A Kumar, A Zhang, RP Adams, S Levine Advances in neural information processing systems 34, 25502-25515, 2021 | 91 | 2021 |
| Calibration of Encoder Decoder Models for Neural Machine Translation A Kumar, S Sarawagi https://arxiv.org/abs/1903.00802, 2019 | 85 | 2019 |
| Reward-conditioned policies A Kumar, XB Peng, S Levine arXiv preprint arXiv:1912.13465, 2019 | 83 | 2019 |
| A workflow for offline model-free robotic reinforcement learning A Kumar, A Singh, S Tian, C Finn, S Levine arXiv preprint arXiv:2109.10813, 2021 | 80 | 2021 |
| Implicit under-parameterization inhibits data-efficient deep reinforcement learning A Kumar, R Agarwal, D Ghosh, S Levine arXiv preprint arXiv:2010.14498, 2020 | 79 | 2020 |
Sergey LevineUC Berkeley, Physical IntelligenceCorreu electrònic verificat a eecs.berkeley.edu
