RSS2024 Paper 104

POLICEd RL: Learning Closed-Loop Robot Control Policies with Provable Satisfaction of Hard Constraints

Jean-Baptiste Bouvier, Kartik Nagpal, Negar Mehr · ICON Lab, University of California Berkeley

机器人学习安全强化学习触觉控制人机交互
新标签打开 AlphaXiv新标签打开 arXiv新标签打开 Code
POLICEd RL: Learning Closed-Loop Robot Control Policies with Provable Satisfaction of Hard Constraints figure
AlphaXiv 中文概览（可滚动查看）