Login / Signup
Data-driven adaptive dynamic programming for partially observable nonzero-sum games via Q-learning method.
Wei Wang
Xin Chen
Hao Fu
Min Wu
Published in:
Int. J. Syst. Sci. (2019)
Keyphrases
</>
dynamic programming
data driven
state space
partially observable
optimal policy
stereo matching
machine learning
decision making
reinforcement learning
objective function
linear programming
mathematical model
markov decision processes
dynamic systems