Abstract | ||
---|---|---|
In this paper, we present a new model-free globalized dual heuristic dynamic programming (GDHP) approach for the discrete-time nonlinear zero-sum game problems. First, the online learning algorithm is proposed based on the GDHP method to solve the Hamilton-Jacobi-Isaacs equation associated with H∞ optimal regulation control problem. By setting backward one step of the definition of performance ind... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TCYB.2017.2712617 | IEEE Transactions on Cybernetics |
Keywords | Field | DocType |
Performance analysis,Game theory,Games,Mathematical model,Neural networks,Nonlinear systems,Optimal control | Mathematical optimization,Nonlinear system,Saddle point,Optimal control,Differential game,Zero-sum game,System dynamics,Adaptive control,Artificial neural network,Mathematics | Journal |
Volume | Issue | ISSN |
48 | 5 | 2168-2267 |
Citations | PageRank | References |
14 | 0.50 | 30 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiangnan Zhong | 1 | 346 | 16.35 |
Haibo He | 2 | 3653 | 213.96 |
Ding Wang | 3 | 1870 | 68.16 |
Zhen Ni | 4 | 525 | 33.47 |