VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training YJ Ma, S Sodhani, D Jayaraman, O Bastani, V Kumar, A Zhang ICLR 2023; arXiv preprint arXiv:2210.00030, 2022 | 136 | 2022 |
Open x-embodiment: Robotic learning datasets and rt-x models A Padalkar, A Pooley, A Jain, A Bewley, A Herzog, A Irpan, A Khazatsky, ... arXiv preprint arXiv:2310.08864, 2023 | 80 | 2023 |
Conservative offline distributional reinforcement learning Y Ma, D Jayaraman, O Bastani NeurIPS 2021; Advances in Neural Information Processing Systems 34, 2021 | 69 | 2021 |
Eureka: Human-level reward design via coding large language models YJ Ma, W Liang, G Wang, DA Huang, O Bastani, D Jayaraman, Y Zhu, ... ICLR 2024; arXiv preprint arXiv:2310.12931, 2023 | 68 | 2023 |
Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence? A Majumdar, K Yadav, S Arnaud, YJ Ma, C Chen, S Silwal, A Jain, ... NeurIPS 2023; arXiv preprint arXiv:2303.18240, 2023 | 67 | 2023 |
LIV: Language-Image Representations and Rewards for Robotic Control YJ Ma, W Liang, V Som, V Kumar, A Zhang, O Bastani, D Jayaraman ICML 2023; arXiv preprint arXiv:2306.00958, 2023 | 53 | 2023 |
How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via -Advantage Regression YJ Ma, J Yan, D Jayaraman, O Bastani NeurIPS 2022; arXiv preprint arXiv:2206.03023, 2022 | 44* | 2022 |
Versatile Offline Imitation from Observations and Examples YJ Ma, A Shen, D Jayaraman, O Bastani ICML 2022; arXiv preprint arXiv:2202.02433, 2022 | 40* | 2022 |
Likelihood-Based Diverse Sampling for Trajectory Forecasting YJ Ma, JP Inala, D Jayaraman, O Bastani ICCV 2021; Proceedings of the IEEE/CVF International Conference on Computer …, 2021 | 27* | 2021 |
Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning YJ Ma, A Shen, O Bastani, D Jayaraman AAAI 2022; arXiv preprint arXiv:2112.07701, 2022 | 19 | 2022 |
Safely bridging offline and online reinforcement learning W Xu, YJ Ma, K Xu, H Bastani, O Bastani AISTAT 2023; arXiv preprint arXiv:2110.13060, 2021 | 16* | 2021 |
Regret Bounds for Risk-Sensitive Reinforcement Learning O Bastani, YJ Ma, E Shen, W Xu NeurIPS 2022; arXiv preprint arXiv:2210.05650, 2022 | 9 | 2022 |
Safe Human-Interactive Control via Shielding J Priya Inala, YJ Ma, O Bastani, X Zhang, A Solar-Lezama arXiv e-prints, arXiv: 2110.05440, 2021 | 5* | 2021 |
TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching YJ Ma, K Sivakumar, J Yan, O Bastani, D Jayaraman L4DC 2023; arXiv preprint arXiv:2305.12663, 2023 | 3 | 2023 |
State Relevance for Off-Policy Evaluation SP Shen, Y Ma, O Gottesman, F Doshi-Velez ICML 2021; International Conference on Machine Learning (ICML), 9537-9546, 2021 | 2 | 2021 |
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset A Khazatsky, K Pertsch, S Nair, A Balakrishna, S Dasari, S Karamcheti, ... arXiv preprint arXiv:2403.12945, 2024 | 1 | 2024 |
Composing Pre-Trained Object-Centric Representations for Robotics From" What" and" Where" Foundation Models J Shi, J Qian, YJ Ma, D Jayaraman arXiv preprint arXiv:2404.13474, 2024 | | 2024 |
Universal Visual Decomposer: Long-Horizon Manipulation Made Easy Z Zhang, Y Li, O Bastani, A Gupta, D Jayaraman, YJ Ma, L Weihs ICRA 2024; arXiv preprint arXiv:2310.08581, 2023 | | 2023 |
Learning a Structured Policy with an Implicit Value Function O Biza, T Kelestemur, YJ Ma, K Schmeckpeper, LLS Wong, R Platt | | |