6 papers
DF-ExpEnse: Diffusion Filtered Exploration for Sample Efficient Finetuning
Calvin Luo, Chen Sun, Shuran Song
A natural recipe for intelligent robotic decision-making is initializing from pretrained generative control policies, which have summarized offline experience, and adapting them to…
Learning Parameterized Skills from Demonstrations
Vedant Gupta, Haotian Fu, Calvin Luo +2
We present DEPS, an end-to-end algorithm for discovering parameterized skills from expert demonstrations. Our method learns parameterized skill policies jointly with a meta-policy…
Self-Improving Loops for Visual Robotic Planning
Calvin Luo, Zilai Zeng, Mingxi Jia +2
Video generative models trained on expert demonstrations have been utilized as performant text-conditioned visual planners for solving robotic tasks. However, generalization to uns…
Solving New Tasks by Adapting Internet Video Knowledge
Calvin Luo, Zilai Zeng, Yilun Du +1
Video generative models demonstrate great promise in robotics by serving as visual planners or as policy supervisors. When pretrained on internet-scale data, such video models inti…
Text-Aware Diffusion for Policy Learning
Calvin Luo, Mandy He, Zilai Zeng +1
Training an agent to achieve particular goals or perform desired behaviors is often accomplished through reinforcement learning, especially in the absence of expert demonstrations.…
Self-Correcting Self-Consuming Loops for Generative Model Training
Nate Gillman, Michael Freeman, Daksh Aggarwal +4
As synthetic data becomes higher quality and proliferates on the internet, machine learning models are increasingly trained on a mix of human- and machine-generated data. Despite t…