Osbert Bastani
収録論文 14本 ・ フィジカルAI/ロボット学習
※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。
論文
- Tether: Autonomous Functional Play with Correspondence-Driven Trajectory Warping2026/3/1
- Vision Language Models are In-Context Value Learners2024/11/1
- Eurekaverse: Environment Curriculum Generation via Large Language Models2024/11/1
- DrEureka: Language Model Guided Sim-To-Real Transfer2024/6/1
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset2024/3/1
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models2023/10/1
- Eureka: Human-Level Reward Design via Coding Large Language Models2023/10/1
- Universal Visual Decomposer: Long-Horizon Manipulation Made Easy2023/10/1
- LIV: Language-Image Representations and Rewards for Robotic Control2023/6/1
- VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training2022/10/1
- Safe Human-Interactive Control via Shielding2021/10/1
- Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics2019/10/1
- MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding2019/10/1
- Learning Safe Unlabeled Multi-Robot Planning with Motion Constraints2019/7/1