Towards a Multiple-Lookahead-Levels agent reinforcement-learning technique and its implementation in integrated circuits.
| Autor: | Al-Dayaa, H.1, Megherbi, D.1 dalila_megherbi@uml.edu |
|---|---|
| Zdroj: | Journal of Supercomputing. Oct2012, Vol. 62 Issue 1, p588-615. 28p. |
| Databáze: | Academic Search Ultimate |
| Externí odkaz: |
|