Rapid behavior learning in multi-agent environment based on state value estimation of others.
Yasutake TakahashiKentarou NomaMinoru AsadaPublished in: IROS (2007)
Keyphrases
- multi agent environment
- learning process
- learning systems
- reinforcement learning
- learning scheme
- online learning
- supervised learning
- knowledge acquisition
- state estimation
- neural network
- mobile robot
- np hard
- dynamic environments
- active learning
- background knowledge
- domain independent
- learning tasks
- learning problems
- inductive learning
- cooperative