| Cal-ql: Calibrated offline rl pre-training for efficient online fine-tuning M Nakamoto, S Zhai, A Singh, M Sobol Mark, Y Ma, C Finn, A Kumar, ... Advances in Neural Information Processing Systems 36, 2024 | 89 | 2024 |
| Unsupervised learning from video with deep neural embeddings C Zhuang, T She, A Andonian, MS Mark, D Yamins Proceedings of the ieee/cvf conference on computer vision and pattern …, 2020 | 74 | 2020 |
| Robot fine-tuning made easy: Pre-training rewards and policies for autonomous real-world reinforcement learning J Yang, MS Mark, B Vu, A Sharma, J Bohg, C Finn 2024 IEEE International Conference on Robotics and Automation (ICRA), 4804-4811, 2024 | 15 | 2024 |
| Fine-tuning offline policies with optimistic action selection MS Mark, A Ghadirzadeh, X Chen, C Finn Deep Reinforcement Learning Workshop NeurIPS 2022, 2022 | 15 | 2022 |
| Offline retraining for online rl: Decoupled policy learning to mitigate exploration bias MS Mark, A Sharma, F Tajwar, R Rafailov, S Levine, C Finn arXiv preprint arXiv:2310.08558, 2023 | 3 | 2023 |
| Offline RL for Online RL: Decoupled Policy Learning for Mitigating Exploration Bias MS Mark, A Sharma, F Tajwar, R Rafailov, S Levine, C Finn | 1 | |
| Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias M Sobol Mark, A Sharma, F Tajwar, R Rafailov, S Levine, C Finn arXiv e-prints, arXiv: 2310.08558, 2023 | | 2023 |
