Inverse Reinforcement Learning from Diverse Third-Person Videos via Graph Abstraction
Inverse Reinforcement Learning from Diverse Third-Person Videos via Graph Abstraction
Sateesh Kumar,Jonathan Zamora,2 Authors,Xiaolong Wang
2022 · DOI: 10.48550/arXiv.2207.14299
arXiv.org · 0 Citations
TLDR
This paper argues that the true potential of third-person IRL lies in increasing the diversity of videos for better scaling, and proposes to perform graph abstraction on the videos followed by temporal matching in the graph space to measure the task progress.