Abstract
In this paper, a novel optimal control scheme is established to solve the multi-player zero-sum game (ZSG) issue of continuous-time nonlinear systems with control constraints and unknown dynamics based on the adaptive critic technology. To relax the requirement of system dynamics, a neural network-based identifier is applied to reconstruct the unknown multi-player ZSG system. Then, by developing a new nonquadratic function, the associated Hamilton-Jacobi-Isaacs (HJI) equation of the constrained ZSG is derived. Moreover, an adaptive critic framework is constructed to approximate the optimal cost function. Meanwhile, the strategy sets of optimal control and the worst disturbance are estimated by utilizing the single-critic network, respectively. After that, a modified critic weight updating mechanism with experience replay technique is introduced to relax the requirement of the persistence of excitation condition. Theoretically, by employing the Lyapunov stability theorem, the uniform ultimate boundedness stability of the ZSG system state and the critic network weight approximation error are proved. Finally, a representative example is simulated to validate the efficacy of the constructed framework.
Similar content being viewed by others
Data availability statement
No data were used in this paper.
References
Denardo, E.V.: Introduction to Game Theory. Springer, Boston (2011)
Vamvoudakis, K.G., Modares, H., Kiumarsi, B., Lewis, F.L.: Game theory-based control system algorithms with real-time reinforcement learning: how to solve multiplayer games online. IEEE Control Syst. Mag. 37(1), 33–52 (2017)
Ni, Z., Paul, S.: A multistage game in smart grid security: a reinforcement learning solution. IEEE Trans. Neural Netw. Learn. Syst. 30(9), 2684–2695 (2019)
Bidram, A., Davoudi, A., Lewis, F.L., Guerrero, J.M.: Distributed cooperative secondary control of microgrids using feedback linearization. IEEE Trans. Power Syst. 28(3), 3462–3470 (2013)
Wei, Q., Li, H., Yang, X., He, H.: Continuous-time distributed policy iteration for multi-controller nonlinear systems. IEEE Trans. Cybern. 51(5), 2372–2383 (2021)
Liu, D., Li, H., Wang, D.: Online synchronous approximate optimal learning algorithm for multiplayer nonzero-sum games with unknown dynamics. IEEE Trans. Syst. Man Cybern. Syst. 44(8), 1015–1027 (2014)
Li, Y., Wei, C., An, T., Ma, B., Dong, B.: Event-triggered-based cooperative game optimal tracking control for modular robot manipulator with constrained input. Nonlinear Dyn. 109(4), 2759–2779 (2022)
Modares, H., Lewis, F.L., Sistani, M.B.N.: Online solution of nonquadratic two-player zero-sum games arising in the \(H_ \infty \) control of constrained input systems. Int. J. Adapt. Control Signal Process. 28(3), 232–254 (2014)
Vamvoudakis, K.G.: Non-zero sum Nash Q-learning for unknown deterministic continuous-time linear systems. Automatica 61, 274–281 (2015)
Wang, D., Ha, M., Zhao, M.: The intelligent critic framework for advanced optimal control. Artif. Intell. Rev. 55(1), 1–22 (2022)
Ha, M., Wang, D., Liu, D.: Discounted iterative adaptive critic designs with novel stability analysis for tracking control. IEEE/CAA J. Automatica Sinica 9(7), 1262–1272 (2022)
Li, Y., Liu, Y., Tong, S.: Observer-based neuro-adaptive optimized control of strict-feedback nonlinear systems with state constraints. IEEE Trans. Neural Netw. Learn. Syst. 33(7), 3131–3145 (2022)
Wang, H., Yang, C., Liu, X., Zhou, L.: Neural-network-based adaptive control of uncertain MIMO singularly perturbed systems with full-state constraints. IEEE Trans. Neural Netw. Learn. Syst. (2021). https://doi.org/10.1109/TNNLS.2021.3123361
Huo, Y., Wang, D., Qiao, J.: Adaptive critic optimization to decentralized event-triggered control of continuous-time nonlinear interconnected systems. Opt. Control Appl. Methods 43(1), 198–212 (2022)
Lv, Y., Na, J., Zhao, X., Huang, Y., Ren, X.: Multi-\(H_\infty \) controls for unknown input-interference nonlinear system with reinforcement learning. IEEE Trans. Neural Netw. Learn. Syst. (2021). https://doi.org/10.1109/TNNLS.2021.3130092
Wei, Q., Liu, D., Lin, Q., Song, R.: Adaptive dynamic programming for discrete-time zero-sum games. IEEE Trans. Neural Netw. Learn. Syst. 29(4), 957–969 (2018)
Dong, B., An, T., Zhou, F., Liu, K., Li, Y.: Decentralized robust zero-sum neuro-optimal control for modular robot manipulators in contact with uncertain environments: theory and experimental verification. Nonlinear Dyn. 97(1), 503–524 (2019)
Wu, H., Liu, Z.: Data-driven guaranteed cost control design via reinforcement learning for linear systems with parameter uncertainties. IEEE Trans. Syst. Man, Cybern. Syst. 50(11), 4151–4159 (2020)
Song, R., Lewis, F.L., Wei, Q.: Off-policy integral reinforcement learning method to solve nonlinear continuous-time multiplayer nonzero-sum games. IEEE Trans. Neural Netw. Learn. Syst. 28(3), 704–713 (2017)
Zhao, Q., Sun, J., Wang, G., Chen, J.: Event-triggered ADP for nonzero-sum games of unknown nonlinear systems. IEEE Trans. Neural Netw. Learn. Syst. 33(5), 1905–1913 (2022)
Wei, Q., Zhu, L., Song, R., Zhang, P., Liu, D., Xiao, J.: Model-free adaptive optimal control for unknown nonlinear multiplayer nonzero-sum game. IEEE Trans. Neural Netw. Learn. Syst. 33(2), 879–892 (2022)
Yang, X., He, H.: Event-driven \(H_\infty \) constrained control using adaptive critic learning. IEEE Trans. Cybern 51(10), 4860–4872 (2021)
Zhao, J., Lv, Y., Zhao, J.: Adaptive learning based output-feedback optimal control of CT two-player zero-sum games. IEEE Trans. Circuits Syst.-II: Express Briefs 69(3), 1437–1441 (2022)
Yazidi, A., Silvestre, D., Oommen, B.J.: Solving two-person zero-sum stochastic games with incomplete information using learning automata with artificial barriers. IEEE Trans. Neural Netw. Learn. Syst. (2021). https://doi.org/10.1109/TNNLS.2021.3099095
Guo, X., Yan, W., Cui, R.: Reinforcement learning-based nearly optimal control for constrained-input partially unknown systems using differentiator. IEEE Trans. Neural Netw. Learn. Syst. 31(11), 4713–4725 (2020)
Song, R., Li, J., Lewis, F.L.: Robust optimal control for disturbed nonlinear zero-sum differential games based on single NN and least squares. IEEE Trans. Syst. Man, Cybern. Syst. 50(11), 4009–4019 (2020)
Song, R., Wei, Q., Song, B.: Neural-network-based synchronous iteration learning method for multi-player zero-sum games. Neurocomputing 242(14), 73–82 (2017)
Zhang, Y., Zhao, B., Liu, D.: Event-triggered adaptive dynamic programming for multi-player zero-sum games with unknown dynamics. Soft. Comput. 25, 2237–2251 (2021)
Qiao, J., Li, M., Wang, D.: Asymmetric constrained optimal tracking control with critic learning of nonlinear multiplayer zero-sum games. IEEE Trans. Neural Netw. Learn. Syst. (2022). https://doi.org/10.1109/TNNLS.2022.3208611
Wei, Q., Song, R., Yan, P.: Data-driven zero-sum neuro-optimal control for a class of continuous-time unknown nonlinear systems with disturbance using ADP. IEEE Trans. Neural Netw. Learn. Syst. 27(2), 444–458 (2016)
Yang, X., Zhao, B.: Optimal neuro-control strategy for nonlinear systems with asymmetric input constraints. IEEE/CAA J. Automatica Sinica 7(2), 575–583 (2020)
Yang, Y., Ding, Z., Wang, R., Modares, H., Wunsch, D.C.: Data-driven human-robot interaction without velocity measurement using off-policy reinforcement learning. IEEE/CAA J. Autom. Sinica 9(1), 47–63 (2022)
Na, J., Lv, Y., Zhang, K., Zhao, J.: Adaptive identifier-critic-based optimal tracking control for nonlinear systems with experimental validation. IEEE Trans. Syst. Man, Cybern. Syst. 52(1), 459–472 (2022)
Xue, S., Luo, B., Liu, D.: Event-triggered adaptive dynamic programming for zero-sum game of partially unknown continuous-time nonlinear systems. IEEE Trans. Syst. Man, Cybern. Syst. 50(9), 3189–3199 (2020)
Wang, D.: Intelligent critic control with robustness guarantee of disturbed nonlinear plants. IEEE Trans. Cybern. 50(6), 2740–2748 (2020)
Huo, X., Karimi, H.R., Zhao, X., Wang, B., Zong, G.: Adaptive-critic design for decentralized event-triggered control of constrained nonlinear interconnected systems within an identifier-critic framework. IEEE Trans. Cybern. 52(8), 7478–7491 (2022)
Zhao, D., Zhang, Q., Wang, D., Zhu, Y.: Experience replay for optimal control of nonzero-sum game systems with unknown dynamics. IEEE Trans. Cybern. 46(3), 854–865 (2016)
Xue, S., Luo, B., Liu, D., Yang, Y.: Constrained event-triggered \(H_\infty \) control based on adaptive dynamic programming with concurrent learning. IEEE Trans. Syst. Man, Cybern. Syst. 52(1), 357–369 (2022)
Xu, Y., Li, T., Bai, W., Shan, Q., Yuan, L., Wu, Y.: Online event-triggered optimal control for multi-agent systems using simplified ADP and experience replay technique. Nonlinear Dyn. 106(1), 509–522 (2021)
Kamalapurkar, R., Reish, B., Chowdhary, G., Dixon, W.E.: Concurrent learning for parameter estimation using dynamic state-derivative estimators. IEEE Trans. Autom. Control 62(7), 3594–3601 (2017)
Zhang, Q., Zhao, D.: Data-based reinforcement learning for nonzero-sum games with unknown drift dynamics. IEEE Trans. Cybern. 49(8), 2874–2885 (2019)
Yang, X., He, H.: Adaptive critic learning and experience replay for decentralized event-triggered control of nonlinear interconnected systems. IEEE Trans. Syst. Man, Cybern. Syst. 50(11), 4043–4055 (2020)
Zhu, Y., Zhao, D., He, H., Ji, J.: Event-triggered optimal control for partially unknown constrained-input systems via adaptive dynamic programming. IEEE Trans. Industr. Electron. 64(5), 4101–4109 (2017)
Luo, B., Yang, Y., Liu, D.: Adaptive Q-learning for data-based optimal output regulation with experience replay. IEEE Trans. Cybern. 48(12), 3337–3348 (2018)
Xia, L., Li, Q., Song, R., Modares, H.: Optimal synchronization control of heterogeneous asymmetric input-constrained unknown nonlinear MASs via reinforcement learning. IEEE/CAA J. Autom. Sinica 9(3), 520–532 (2022)
Zhao, B., Liu, D., Luo, C.: Reinforcement learning-based optimal stabilization for unknown nonlinear systems subject to inputs with uncertain constraints. IEEE Trans. Neural Netw. Learn. Syst. 31(10), 4330–4340 (2020)
Zhao, S., Wang, J.: Robust optimal control for constrained uncertain switched systems subjected to input saturation: The adaptive event-triggered case. Nonlinear Dyn. 110(1), 363–380 (2022)
Mishra, A., Ghosh, S.: Variable gain gradient descent-based reinforcement learning for robust optimal tracking control of uncertain nonlinear system with input constraints. Nonlinear Dyn. 107(3), 2195–2214 (2022)
Yang, X., Zhou, Y., Dong, N., Wei, Q.: Adaptive critics for decentralized stabilization of constrained-input nonlinear interconnected systems. IEEE Trans. Syst. Man, Cybern. Syst. 52(7), 4187–4199 (2022)
Mu, C., Wang, K., Sun, C.: Policy-iteration-based learning for nonlinear player game systems with constrained inputs. IEEE Trans. Syst. Man, Cybern. Syst. 51(10), 6488–6502 (2021)
Zhang, S., Zhao, B., Liu, D., Zhang, Y.: Observer-based event-triggered control for zero-sum games of input constrained multi-player nonlinear systems. Neural Netw. 114(8), 101–112 (2021)
Sun, J., Liu, C.: Distributed zero-sum differential game for multi-agent systems in strict-feedback form with input saturation and output constraint. Neural Netw. 106, 8–19 (2018)
Zhu, Y., Zhao, D., Li, X.: Iterative adaptive dynamic programming for solving unknown nonlinear zero-sum game based on online data. IEEE Trans. Neural Netw. Learn. Syst. 28(3), 714–725 (2017)
Bhasin, S., Kamalapurkar, R., Johnson, M., Vamvoudakis, K.G., Lewis, F.L., Dixon, W.E.: A novel actor-critic-identifier architecture for approximate optimal control of uncertain nonlinear systems. Automatica 49, 82–92 (2013)
Yasini, S., Sitani, M.B.N., Kirampor, A.: Reinforcement learning and neural networks for multi-agent nonzero-sum games of nonlinear constrained-input systems. Int. J. Mach. Learn. Cybern. 7, 967–980 (2016)
Funding
This work was supported in part by the National Key Research and Development Program of China under Grant 2021ZD0112302; and in part by the National Natural Science Foundation of China under Grant 62222301, Grant 61890930-5, and Grant 62021003.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
The authors declare that they have no conflict of interest.
Ethical approval
No conflict of interest exits in this submission, and the research work does not involve any human participants and/or animals. The manuscript is approved by all authors for publication.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Huo, Y., Wang, D., Qiao, J. et al. Adaptive critic design for nonlinear multi-player zero-sum games with unknown dynamics and control constraints. Nonlinear Dyn 111, 11671–11683 (2023). https://doi.org/10.1007/s11071-023-08419-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11071-023-08419-5