C
search
search
reviewers
reviewers
feeds
feeds
assignments
assignments
settings
logout
Off-Policy Integral Reinforcement Learning Method to Solve Nonlinear Continuous-Time Multiplayer Nonzero-Sum Games.
Ruizhuo Song
Frank L. Lewis
Qinglai Wei
Published in:
IEEE Trans. Neural Networks Learn. Syst. (2017)
Keyphrases
</>
reinforcement learning
cost function
objective function
preprocessing
significant improvement
high accuracy
dynamic programming
high order
pairwise
support vector machine svm
detection method
similarity measure
clustering method
optimal control