Learning to grasp everyday objects using reinforcement-learning with automatic value cut-off.
Tim Baier-LöwensteinJianwei ZhangPublished in: IROS (2007)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- online learning
- learning problems
- supervised learning
- reinforcement learning algorithms
- function approximation
- everyday objects
- reinforcement learning methods
- active learning
- multi agent
- transfer learning
- markov decision processes
- learning tasks
- tabu search
- optimal policy
- data processing
- function approximators
- learning agents