Use of the knowledge which is independence on reward in reinforcement learning.
Yoshiki MiyazakiKentarou KurashigePublished in: CIRA (2009)
Keyphrases
- reinforcement learning
- knowledge acquisition
- expert systems
- domain knowledge
- function approximation
- state space
- knowledge management
- partially observable environments
- machine learning
- partially observable
- knowledge transfer
- knowledge based systems
- knowledge discovery
- knowledge base
- dynamic programming
- multi agent
- knowledge extraction
- long run
- case study
- complex domains