Self-Supervised Learning

TIMAR: Transition-Informed Representation for Sample-Efficient Multi-agent Reinforcement Learning
In MARL (Multi-Agent Reinforcement Learning), the trial-and-error learning paradigm based on multiple agents requires massive …
Cite
Neural Attention Field: Emerging Point Relevance in 3D Scenes for One-Shot Dexterous Grasping
One-shot transfer of dexterous grasps to novel scenes with object and context variations has been a challenging problem. While …
PDF Cite