| PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings N Rhinehart, R McAllister, K Kitani, S Levine Proceedings of the IEEE International Conference on Computer Vision, 2019 | 269 | 2019 |
| R2P2: A Reparameterized Pushforward Policy for Diverse, Precise Generative Path Forecasting N Rhinehart, KM Kitani, P Vernaza Proceedings of the European Conference on Computer Vision (ECCV), 772-788, 2018 | 214 | 2018 |
| N2N learning: Network to Network Compression via Policy Gradient Reinforcement Learning A Ashok, N Rhinehart, F Beainy, KM Kitani International Conference on Learning Representations (ICLR), 2018 | 170 | 2018 |
| First-Person Activity Forecasting with Online Inverse Reinforcement Learning N Rhinehart, KM Kitani The IEEE International Conference on Computer Vision (ICCV), 3716-3725, 2017 | 140 | 2017 |
| Can autonomous vehicles identify, recover from, and adapt to distribution shifts? A Filos, P Tigkas, R McAllister, N Rhinehart, S Levine, Y Gal International Conference on Machine Learning, 3145-3153, 2020 | 122 | 2020 |
| Deep Imitative Models for Flexible Inference, Planning, and Control N Rhinehart, R McAllister, S Levine International Conference on Learning Representations (ICLR), 2020 | 117 | 2020 |
| Parrot: Data-driven behavioral priors for reinforcement learning A Singh, H Liu, G Zhou, A Yu, N Rhinehart, S Levine arXiv preprint arXiv:2011.10024, 2020 | 81 | 2020 |
| Conservative safety critics for exploration H Bharadhwaj, A Kumar, N Rhinehart, S Levine, F Shkurti, A Garg arXiv preprint arXiv:2010.14497, 2020 | 78 | 2020 |
| Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information A Sharma, M Sharma, N Rhinehart, KM Kitani International Conference on Learning Representations (ICLR), 2019 | 53 | 2019 |
| Learning Action Maps of Large Environments Via First-Person Vision N Rhinehart, KM Kitani The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 | 48 | 2016 |
| Inverting the pose forecasting pipeline with SPF2: Sequential pointcloud forecasting for sequential pose forecasting X Weng, J Wang, S Levine, K Kitani, N Rhinehart Conference on robot learning, 11-20, 2021 | 41* | 2021 |
| Predictive-state decoders: Encoding the future into recurrent networks A Venkatraman*, N Rhinehart*, W Sun, L Pinto, M Hebert, B Boots, ... Advances in Neural Information Processing Systems, 1172-1183, 2017 | 41 | 2017 |
| Ving: Learning open-world navigation with visual goals D Shah, B Eysenbach, G Kahn, N Rhinehart, S Levine 2021 IEEE International Conference on Robotics and Automation (ICRA), 13215 …, 2021 | 33 | 2021 |
| SMiRL: Surprise Minimizing RL in Dynamic Environments G Berseth, D Geng, C Devin, N Rhinehart, C Finn, D Jayaraman, S Levine arXiv preprint arXiv:1912.05510, 2019 | 28* | 2019 |
| First-Person Activity Forecasting from Video with Online Inverse Reinforcement Learning N Rhinehart, K Kitani IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018 | 28 | 2018 |
| RECON: rapid exploration for open-world navigation with latent goal models D Shah, B Eysenbach, N Rhinehart, S Levine arXiv preprint arXiv:2104.05859, 2021 | 22 | 2021 |
| Generative Hybrid Representations for Activity Forecasting with No-Regret Learning J Guan, Y Yuan, KM Kitani, N Rhinehart arXiv preprint arXiv:1904.06250, 2019 | 21 | 2019 |
| Human-Interactive Subgoal Supervision for Efficient Inverse Reinforcement Learning X Pan, E Ohn-Bar, N Rhinehart, Y Xu, Y Shen, KM Kitani Proceedings of the 17th International Conference on Autonomous Agents and …, 2018 | 12 | 2018 |
| Contingencies from observations: Tractable contingency planning with learned behavior models N Rhinehart, J He, C Packer, MA Wright, R McAllister, JE Gonzalez, ... 2021 IEEE International Conference on Robotics and Automation (ICRA), 13663 …, 2021 | 10 | 2021 |
| Information is power: intrinsic control via information capture N Rhinehart, J Wang, G Berseth, J Co-Reyes, D Hafner, C Finn, S Levine Advances in Neural Information Processing Systems 34, 10745-10758, 2021 | 7* | 2021 |
Sergey LevineUC Berkeley, GoogleVerified email at eecs.berkeley.edu
