Awesome Robotics Manipulation · full_paper

Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language

作者：Minyoung Hwang, Alexandra Forsey-Smerek, Nathaniel Dennler, Andreea Bobu · 单位：MIT CSAIL · 会议/期刊：arXiv · 日期：2025-11-18 · 来源：Low-Level Learning-Based Action Modelling / Learning Strategy / Imitation Learning from Action with Rewards / Inverse Reinforcement Learning (IRL)

模仿学习强化学习触觉语言条件机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language figure
AlphaXiv 中文论文页面（可滚动查看）