Login / Signup
A Strategy for Converging Dynamic Action Policies.
Richardson Ribeiro
André Pinz Borges
Alessandro L. Koerich
Edson Emílio Scalabrin
Fabrício Enembreck
Published in:
IEEE IA (2009)
Keyphrases
</>
real time
database
learning algorithm
social networks
hidden markov models
optimal policy
search strategy