ADP policy iteration solves hierarchical zero-sum and nonzero-sum games for nonlinear systems with disturbances, reducing neural network usage by about 30% with Lyapunov convergence analysis.
Continuous-time q-learning for infinite-horizon discounted cost linear quadratic regulator problems,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust On-Line ADP-based Solution of a Class of Hierarchical Nonlinear Differential Game
ADP policy iteration solves hierarchical zero-sum and nonzero-sum games for nonlinear systems with disturbances, reducing neural network usage by about 30% with Lyapunov convergence analysis.