Learning Robot Grasping from a Random Pile with Deep Q-Learning.
Bin ChenJianhua SuLili WangQipeng GuPublished in: ICIRA (2) (2021)
Keyphrases
- learning algorithm
- reinforcement learning
- autonomous robots
- vision system
- learning systems
- learning process
- online learning
- multi agent
- supervised learning
- learning tasks
- motor skills
- reinforcement learning methods
- robot navigation
- deep architectures
- sensory motor
- temporal difference learning
- robot control
- solving problems
- function approximation
- learning problems
- dynamic environments