A Framework for Efficient Robotic Manipulation

90 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning (2021, background): “…2018, 2019, Yan et al., 2020, Finn et al., 2015, Pinto et al., 2016, Agrawal et al., 2016] and other auxiliary objectives [Jaderberg et al., 2016, Zhan et al., 2020, Young et al., 2020, Chen et al., 2020] have shown improvements on a variety of problems ranging from gameplay, continuous…”
Real-World Robot Learning with Masked Visual Pre-training (2022, background): “Self-supervised learning in robotics has been explored in a number of settings: learning a dynamic models [31]; learning visual representations from interaction with the environment [32]; learning vision-based grasping policies [33, 34]; learning visual autoencoders [35]; learning spatiotemporal rep”
MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations (2023, methodology): “In fact, this can be complementary to MimicGen— we leverage pixel shift randomization [7,36–39] when training image-based agents on MimicGen data.”