![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Article
PAC-Bayesian offline Meta-reinforcement learning
Meta-reinforcement learning (Meta-RL) utilizes shared structure among tasks to enable rapid adaptation to new tasks with only a little experience. However, most existing Meta-RL algorithms lack theoretical gen...
-
Article
Primitive-contrastive network: data-efficient self-supervised learning from robot demonstration videos
Due to the costly collection of expert demonstrations for robots, robot imitation learning suffers from the demonstration-insufficiency problem. A promising solution to this problem is self-supervised learning...
-
Article
Cycle representation-disentangling network: learning to completely disentangle spatial-temporal features in video
Video representation learning is a significant problem of video understanding. However, the complex entangled spatiotemporal information in frames makes video representation learning a very tough task. Many st...