Learning and relearning of target decision strategies in continuous coordinated cleaning tasks with shallow coordination.
Keisuke YonedaAyumi SugiyamaChihiro KatoToshiharu SugawaraPublished in: Web Intell. (2015)
Keyphrases
- multiple tasks
- learning algorithm
- reinforcement learning
- multi agent
- cooperative
- multi task learning
- neural network
- coordination mechanisms
- decision makers
- online learning
- delayed feedback
- multi agent reinforcement learning
- inductive inference
- autonomous robots
- multi task
- learning problems
- learning systems
- supervised learning
- active learning
- learning process