7 papers
Bilinear Flow Policy: Distributional Extrapolation for Goal-Conditioned Visuomotor Imitation
Wonsuhk Jung, Sundhar Vinodh Sangeetha, Chen Xu +4
Goal-conditioned imitation learning (GCIL) with flow matching is a promising framework that can represent multimodal behaviors while adapting to diverse, user-specified goals, yet…
Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning
Kevin Huang, Rosario Scalise, Cleah Winston +9
Imitation learning has proven effective for training robots to perform complex tasks from expert human demonstrations. However, it remains limited by its reliance on high-quality,…
Steering Your Diffusion Policy with Latent Space Reinforcement Learning
Andrew Wagenmaker, Mitsuhiko Nakamoto, Yunchu Zhang +5
Robotic control policies learned from human demonstrations have achieved impressive results in many real-world applications. However, in scenarios where initial performance is not…
ATK: Automatic Task-driven Keypoint Selection for Robust Policy Learning
Yunchu Zhang, Shubham Mittal, Zhengyu Zhang +3
Visuomotor policies often suffer from perceptual challenges, where visual differences between training and evaluation environments degrade policy performance. Policies relying on s…
Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL
Andrew Wagenmaker, Kevin Huang, Liyiming Ke +3
In order to mitigate the sample complexity of real-world reinforcement learning, common practice is to first train a policy in a simulator where samples are cheap, and then deploy…
Data Efficient Behavior Cloning for Fine Manipulation via Continuity-based Corrective Labels
Abhay Deshpande, Liyiming Ke, Quinn Pfeifer +2
We consider imitation learning with access only to expert demonstrations, whose real-world application is often limited by covariate shift due to compounding errors during executio…
CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning
Liyiming Ke, Yunchu Zhang, Abhay Deshpande +2
We present a new technique to enhance the robustness of imitation learning methods by generating corrective data to account for compounding errors and disturbances. While existing…