Login / Signup
Higher-level application of Adaptive Dynamic Programming/Reinforcement Learning - a next phase for controls and system identification?
George G. Lendaris
Published in:
ADPRL (2011)
Keyphrases
</>
dynamic programming
reinforcement learning
higher level
markov decision processes
low level
optimal control
neural network
linear programming
machine learning
lower bound
search space
evolutionary algorithm
decision support
phase information