A GPT-style model pre-trained on large video datasets achieves 94.9% success on CALVIN multi-task manipulation and 85.4% zero-shot generalization, outperforming prior baselines.
2017 IEEE International Conference on Robotics and Automation (ICRA) , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.
citing papers explorer
-
Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation
A GPT-style model pre-trained on large video datasets achieves 94.9% success on CALVIN multi-task manipulation and 85.4% zero-shot generalization, outperforming prior baselines.
-
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.