A connectionist model for learning robotic grasps using reinforcement learning.
Medhat A. MoussaMohamed S. KamelPublished in: ICNN (1996)
Keyphrases
- reinforcement learning
- learning mechanism
- high level
- supervised learning
- learning process
- mathematical model
- probability distribution
- decision theoretic
- learning problems
- active learning
- prior knowledge
- expert systems
- learning algorithm
- connectionist networks
- learning systems
- adaptation process
- markov decision process
- action selection
- model free
- autonomous learning
- autonomous robots
- learning tasks
- transfer learning
- real time
- online learning
- dynamic programming
- neural network