H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation.
Yanjie ZeYuyao LiuRuizhe ShiJiaxin QinZhecheng YuanJiashun WangHuazhe XuPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- haptic feedback
- manipulation tasks
- visual representations
- mid level
- visual information
- function approximation
- state space
- function approximators
- visual features
- low level
- index structure
- visual feedback
- learning problems
- force feedback
- temporal difference
- multi agent
- high level
- object manipulation
- database
- learning process
- image retrieval
- object recognition
- learning algorithm
- machine learning