.png){kind=icon}
Return
Learning generalizable agents via self-supervised exploration
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2025.107787.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A self-supervised exploration framework to improve the generalization performance and sample efficiency of visual RL. • Devising a visual discrepancy inference module to learn features shared across different views. • Designing an exploration via distributional discrepancy module to identify the changed features. • Experiments are conducted on the DMControl-GB, Robotic Manipulation tasks and CARLA Autonomous Driving tasks.
Journal
IF:
6.3
Papers:
8.2K
Citations:
3.0W
Organization
No organization information available
Cited Papers
ShareSaveMultimodal information bottleneck for deep reinforcement learning with multiple sensors.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
ShareSaveShareSaveLook Closer: Bridging Egocentric and Third-Person Views With Transformers for Robotic Manipulation
OAAI
OAAIShareSaveShareSaveShareSave
ShareSave
View more