1
|
Song R, Yang G, Lewis FL. Nearly Optimal Control for Mixed Zero-Sum Game Based on Off-Policy Integral Reinforcement Learning. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:2793-2804. [PMID: 35877793 DOI: 10.1109/tnnls.2022.3191847] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
In this article, we solve a class of mixed zero-sum game with unknown dynamic information of nonlinear system. A policy iterative algorithm that adopts integral reinforcement learning (IRL), which does not depend on system information, is proposed to obtain the optimal control of competitor and collaborators. An adaptive update law that combines critic-actor structure with experience replay is proposed. The actor function not only approximates optimal control of every player but also estimates auxiliary control, which does not participate in the actual control process and only exists in theory. The parameters of the actor-critic structure are simultaneously updated. Then, it is proven that the parameter errors of the polynomial approximation are uniformly ultimately bounded. Finally, the effectiveness of the proposed algorithm is verified by two given simulations.
Collapse
|
2
|
Liu G, Sun Q, Wang R, Hu X. Nonzero-Sum Game-Based Voltage Recovery Consensus Optimal Control for Nonlinear Microgrids System. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023; 34:8617-8629. [PMID: 35275823 DOI: 10.1109/tnnls.2022.3151650] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Since most of the existing models based on the microgrids (MGs) are nonlinear, which could cause the controller oscillate, resulting in the excessive line loss, and the nonlinear could also lead to the controller design difficulty of MGs system. Therefore, this article researches the distributed voltage recovery consensus optimal control problem for the nonlinear MGs system with N -distributed generations (DGs), in the case of providing stringent real power sharing. First, based on the distributed cooperative control concept of multiagent systems and the critic neural networks (NNs), a novel distributed secondary voltage recovery consensus optimal control protocol is constructed via applying the backstepping technique and nonzero-sum (NZS) differential game strategy to realize the voltage recovery of island MGs. Meanwhile, the model identifier is established to reconstruct the unknown NZS games systems based on a three-layer NN. Then, a critic NN weight adaptive adjustment tuning law is proposed to ensure the convergence of the cost functions and the stability of the closed-loop system. Furthermore, according to Lyapunov stability theory, it is proven that all signals are uniform ultimate boundedness in the closed loop system and the voltage recovery synchronization error converges to an arbitrarily small neighborhood of the origin near. Finally, some simulation results in MATLAB illustrate the validity of the proposed control strategy.
Collapse
|
3
|
Wang K, Mu C. Asynchronous learning for actor-critic neural networks and synchronous triggering for multiplayer system. ISA TRANSACTIONS 2022; 129:295-308. [PMID: 35216805 DOI: 10.1016/j.isatra.2022.02.007] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/10/2021] [Revised: 01/19/2022] [Accepted: 02/05/2022] [Indexed: 06/14/2023]
Abstract
In this paper, based on actor-critic neural network structure and reinforcement learning scheme, a novel asynchronous learning algorithm with event communication is developed, so as to solve Nash equilibrium of multiplayer nonzero-sum differential game in an adaptive fashion. From the point of optimal control view, each player or local controller wants to minimize the individual infinite-time cost function by finding an optimal policy. In this novel learning framework, each player consists of one critic and one actor, and implements distributed asynchronous policy iteration to optimize decision-making process. In addition, communication burden between the system and players is effectively reduced by setting up a central event generator. Critic network executes fast updates by gradient-descent adaption while actor network gives event-induced updates using the gradient projection. The closed-loop asymptotic stability is ensured along with uniform ultimate convergence. Then, the effectiveness of the proposed algorithm is substantiated on a four-player nonlinear system, revealing that it can significantly reduce sampling numbers without impairing learning accuracy. Finally, by leveraging nonzero-sum game idea, the proposed learning scheme is also applied to solve the lateral-directional stability of a linear aircraft system, and is further extended to a nonlinear vehicle system for achieving adaptive cruise control.
Collapse
Affiliation(s)
- Ke Wang
- School of Electrical and Information Engineering, Tianjin University, Tianjin, China.
| | - Chaoxu Mu
- School of Electrical and Information Engineering, Tianjin University, Tianjin, China.
| |
Collapse
|
4
|
Mu C, Wang K, Ni Z. Adaptive Learning and Sampled-Control for Nonlinear Game Systems Using Dynamic Event-Triggering Strategy. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022; 33:4437-4450. [PMID: 33621182 DOI: 10.1109/tnnls.2021.3057438] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
Static event-triggering-based control problems have been investigated when implementing adaptive dynamic programming algorithms. The related triggering rules are only current state-dependent without considering previous values. This motivates our improvements. This article aims to provide an explicit formulation for dynamic event-triggering that guarantees asymptotic stability of the event-sampled nonzero-sum differential game system and desirable approximation of critic neural networks. This article first deduces the static triggering rule by processing the coupling terms of Hamilton-Jacobi equations, and then, Zeno-free behavior is realized by devising an exponential term. Subsequently, a novel dynamic-triggering rule is devised into the adaptive learning stage by defining a dynamic variable, which is mathematically characterized by a first-order filter. Moreover, mathematical proofs illustrate the system stability and the weight convergence. Theoretical analysis reveals the characteristics of dynamic rule and its relations with the static rules. Finally, a numerical example is presented to substantiate the established claims. The comparative simulation results confirm that both static and dynamic strategies can reduce the communication that arises in the control loops, while the latter undertakes less communication burden due to fewer triggered events.
Collapse
|
5
|
Liu P, Zhang H, Sun J, Tan Z. Event-triggered adaptive integral reinforcement learning method for zero-sum differential games of nonlinear systems with incomplete known dynamics. Neural Comput Appl 2022. [DOI: 10.1007/s00521-022-07010-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
6
|
Zhao Q, Sun J, Wang G, Chen J. Event-Triggered ADP for Nonzero-Sum Games of Unknown Nonlinear Systems. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022; 33:1905-1913. [PMID: 33882002 DOI: 10.1109/tnnls.2021.3071545] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
For nonzero-sum (NZS) games of nonlinear systems, reinforcement learning (RL) or adaptive dynamic programming (ADP) has shown its capability of approximating the desired index performance and the optimal input policy iteratively. In this article, an event-triggered ADP is proposed for NZS games of continuous-time nonlinear systems with completely unknown system dynamics. To achieve the Nash equilibrium solution approximately, the critic neural networks and actor neural networks are utilized to estimate the value functions and the control policies, respectively. Compared with the traditional time-triggered mechanism, the proposed algorithm updates the neural network weights as well as the inputs of players only when a state-based event-triggered condition is violated. It is shown that the system stability and the weights' convergence are still guaranteed under mild assumptions, while occupation of communication and computation resources is considerably reduced. Meanwhile, the infamous Zeno behavior is excluded by proving the existence of a minimum inter-event time (MIET) to ensure the feasibility of the closed-loop event-triggered continuous-time system. Finally, a numerical example is simulated to illustrate the effectiveness of the proposed approach.
Collapse
|
7
|
Yang Y, Fan X, Xu C, Wu J, Sun B. State consensus cooperative control for a class of nonlinear multi-agent systems with output constraints via ADP approach. Neurocomputing 2021. [DOI: 10.1016/j.neucom.2021.05.046] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
|
8
|
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 2021; 144:101-112. [PMID: 34478940 DOI: 10.1016/j.neunet.2021.08.012] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2021] [Revised: 07/18/2021] [Accepted: 08/09/2021] [Indexed: 11/18/2022]
Abstract
In this paper, an event-triggered control (ETC) method is investigated to solve zero-sum game (ZSG) problems of unknown multi-player continuous-time nonlinear systems with input constraints by using adaptive dynamic programming (ADP). To relax the requirement of system dynamics, a neural network (NN) observer is constructed to identify the dynamics of multi-player system via the input and output data. Then, the event-triggered Hamilton-Jacobi-Isaacs (HJI) equation of the ZSG can be solved by constructing a critic NN, and the approximated optimal control law and the worst disturbance law can be obtained directly. A triggering scheme which determines the updating time instants of the control law and the disturbance law is developed. Thus, the proposed ADP-based ETC method cannot only reduce the computational burden, but also save communication resource and bandwidths. Furthermore, we prove that the signals of the closed-loop system and the approximate errors of the critic NN weights are uniformly ultimately bounded by using Lyapunov's direct method, and the Zeno behavior is excluded. Finally, two simulation examples are provided to demonstrate the effectiveness of the proposed ETC scheme.
Collapse
Affiliation(s)
- Shunchao Zhang
- School of Automation, Guangdong University of Technology, Guangzhou 510006, China.
| | - Bo Zhao
- School of Systems Science, Beijing Normal University, Beijing 100875, China.
| | - Derong Liu
- School of Automation, Guangdong University of Technology, Guangzhou 510006, China.
| | - Yongwei Zhang
- School of Automation, Guangdong University of Technology, Guangzhou 510006, China.
| |
Collapse
|
9
|
Xu Y, Jiang B, Yang H. Two-Level Game-Based Distributed Optimal Fault-Tolerant Control for Nonlinear Interconnected Systems. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2020; 31:4892-4906. [PMID: 31940562 DOI: 10.1109/tnnls.2019.2958948] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
This article addresses the distributed optimal fault-tolerant control (FTC) issue by using the two-level game approach for a class of nonlinear interconnected systems, in which each subsystem couples with its neighbors through not only the states but also the inputs. At the first level, the FTC problem for each subsystem is formulated as a zero-sum differential game, in which the controller and the fault are regarded as two players with opposite interests. At the second level, the whole interconnected system is formulated as a graphical game, in which each subsystem is a player to achieve the global Nash equilibrium for the overall system. The rigorous proof of the stability of the interconnected system is given by means of the cyclic-small-gain theorem, and the relationship between the local optimality and the global optimality is analyzed. Moreover, based on the adaptive dynamic programming (ADP) technology, a distributed optimal FTC learning scheme is proposed, in which a group of critic neural networks (NNs) are established to approximate the cost functions. Finally, an example is taken to illustrate the efficiency and applicability of the obtained theoretical results.
Collapse
|
10
|
Paul S, Ni Z, Mu C. A Learning-Based Solution for an Adversarial Repeated Game in Cyber-Physical Power Systems. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2020; 31:4512-4523. [PMID: 31899439 DOI: 10.1109/tnnls.2019.2955857] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
Due to the rapidly expanding complexity of the cyber-physical power systems, the probability of a system malfunctioning and failing is increasing. Most of the existing works combining smart grid (SG) security and game theory fail to replicate the adversarial events in the simulated environment close to the real-life events. In this article, a repeated game is formulated to mimic the real-life interactions between the adversaries of the modern electric power system. The optimal action strategies for different environment settings are analyzed. The advantage of the repeated game is that the players can generate actions independent of the previous actions' history. The solution of the game is designed based on the reinforcement learning algorithm, which ensures the desired outcome in favor of the players. The outcome in favor of a player means achieving higher mixed strategy payoff compared to the other player. Different from the existing game-theoretic approaches, both the attacker and the defender participate actively in the game and learn the sequence of actions applying to the power transmission lines. In this game, we consider several factors (e.g., attack and defense costs, allocated budgets, and the players' strengths) that could affect the outcome of the game. These considerations make the game close to real-life events. To evaluate the game outcome, both players' utilities are compared, and they reflect how much power is lost due to the attacks and how much power is saved due to the defenses. The players' favorable outcome is achieved for different attack and defense strengths (probabilities). The IEEE 39 bus system is used here as the test benchmark. Learned attack and defense strategies are applied in a simulated power system environment (PowerWorld) to illustrate the postattack effects on the system.
Collapse
|
11
|
Neural networks-based optimal tracking control for nonzero-sum games of multi-player continuous-time nonlinear systems via reinforcement learning. Neurocomputing 2020. [DOI: 10.1016/j.neucom.2020.06.083] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
|
12
|
Li J, Ding J, Chai T, Lewis FL. Nonzero-Sum Game Reinforcement Learning for Performance Optimization in Large-Scale Industrial Processes. IEEE TRANSACTIONS ON CYBERNETICS 2020; 50:4132-4145. [PMID: 31751258 DOI: 10.1109/tcyb.2019.2950262] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
This article presents a novel technique to achieve plant-wide performance optimization for large-scale unknown industrial processes by integrating the reinforcement learning method with the multiagent game theory. A main advantage of this technique is that plant-wide optimal performance is achieved by a distributed approach where multiple agents solve simplified local nonzero-sum optimization problems so that a global Nash equilibrium is reached. To this end, first, the plant-wide performance optimization problem is reformulated by decomposition into local optimization subproblems for each production index in a multiagent framework. Then, the nonzero-sum graphical game theory is utilized to compute the operational indices for each unit process with the purpose of reaching the global Nash equilibrium, resulting in production indices following their prescribed target values. The stability and the global Nash equilibrium of this multiagent graphical game solution are rigorously proved. The reinforcement learning methods are then developed for each agent to solve the nonzero-sum graphical game problem using data measurements available in the system in real time. The plant dynamics do not have to be known. Finally, the emulation results are given to show the effectiveness of the proposed automated decision algorithm by using measured data from a large mineral processing plant in Gansu Province, China.
Collapse
|
13
|
Mu C, Wang K, Zhang Q, Zhao D. Hierarchical optimal control for input-affine nonlinear systems through the formulation of Stackelberg game. Inf Sci (N Y) 2020. [DOI: 10.1016/j.ins.2019.12.078] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
14
|
Su H, Zhang H, Sun S, Cai Y. Integral reinforcement learning-based online adaptive event-triggered control for non-zero-sum games of partially unknown nonlinear systems. Neurocomputing 2020. [DOI: 10.1016/j.neucom.2019.09.088] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
15
|
Sahoo A, Narayanan V. Differential-game for resource aware approximate optimal control of large-scale nonlinear systems with multiple players. Neural Netw 2020; 124:95-108. [PMID: 31986447 DOI: 10.1016/j.neunet.2019.12.031] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2019] [Revised: 12/08/2019] [Accepted: 12/30/2019] [Indexed: 11/29/2022]
Abstract
In this paper, we propose a novel differential-game based neural network (NN) control architecture to solve an optimal control problem for a class of large-scale nonlinear systems involving N-players. We focus on optimizing the usage of the computational resources along with the system performance simultaneously. In particular, the N-players' control policies are desired to be designed such that they cooperatively optimize the large-scale system performance, and the sampling intervals for each player are desired to reduce the frequency of feedback execution. To develop a unified design framework that achieves both these objectives, we propose an optimal control problem by integrating both the design requirements, which leads to a multi-player differential-game. A solution to this problem is numerically obtained by solving the associated Hamilton-Jacobi (HJ) equation using event-driven approximate dynamic programming (E-ADP) and artificial NNs online and forward-in-time. We employ the critic neural networks to approximate the solution to the HJ equation, i.e., the optimal value function, with aperiodically available feedback information. Using the NN approximated value function, we design the control policies and the sampling schemes. Finally, the event-driven N-player system is remodeled as a hybrid dynamical system with impulsive weight update rules for analyzing its stability and convergence properties. The closed-loop practical stability of the system and Zeno free behavior of the sampling scheme are demonstrated using the Lyapunov method. Simulation results using a numerical example are also included to substantiate the analytical results.
Collapse
Affiliation(s)
- Avimanyu Sahoo
- 555 Engineering North, Division of Engineering Technology, Oklahoma State University, Stillwater, OK 74078, United States of America.
| | | |
Collapse
|
16
|
Online event-triggered adaptive critic design for non-zero-sum games of partially unknown networked systems. Neurocomputing 2019. [DOI: 10.1016/j.neucom.2019.07.029] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
|
17
|
Mu C, Wang K. Aperiodic adaptive control for neural-network-based nonzero-sum differential games: A novel event-triggering strategy. ISA TRANSACTIONS 2019; 92:1-13. [PMID: 30732994 DOI: 10.1016/j.isatra.2019.01.025] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/03/2018] [Revised: 12/29/2018] [Accepted: 01/18/2019] [Indexed: 06/09/2023]
Abstract
Owing to the adoption of aperiodic sampling pattern, the event-triggering control mode has been widely investigated in networked systems to save communication and reduce computation. Recently, there has been some preliminary findings to explore applications of this novel mode and to implement it in neural-network-based nonlinear systems by including an event generator. This motivates our investigation. For the first time, this paper designs triggering rules for neural-network-based nonzero-sum differential games characterized by nonlinear dynamics and quadratic cost functions. The main intention of the event-triggering strategy is to reduce communication between controllers and neural networks, thereby mitigating computational loads of controllers. An adaptive critic algorithm is subsequently applied to learn the required Nash equilibrium on line and meantime an alarm sampling period is proposed to ameliorate the learning accuracy. Furthermore, three simulation cases validate the approximate-optimal control performance and appraise virtues of the proposed event-triggering mode.
Collapse
Affiliation(s)
- Chaoxu Mu
- School of Electrical and Information Engineering, Tianjin University, Tianjin, China.
| | - Ke Wang
- School of Electrical and Information Engineering, Tianjin University, Tianjin, China.
| |
Collapse
|
18
|
Ni Z, Paul S. A Multistage Game in Smart Grid Security: A Reinforcement Learning Solution. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2019; 30:2684-2695. [PMID: 30624227 DOI: 10.1109/tnnls.2018.2885530] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
Existing smart grid security research investigates different attack techniques and cascading failures from the attackers' viewpoints, while the defenders' or the operators' protection strategies are somehow neglected. Game theoretic methods are applied for the attacker-defender games in the smart grid security area. Yet, most of the existing works only use the one-shot game and do not consider the dynamic process of the electric power grid. In this paper, we propose a new solution for a multistage game (also called a dynamic game) between the attacker and the defender based on reinforcement learning to identify the optimal attack sequences given certain objectives (e.g., transmission line outages or generation loss). Different from a one-shot game, the attacker here learns a sequence of attack actions applying for the transmission lines and the defender protects a set of selected lines. After each time step, the cascading failure will be measured, and the line outage (and/or generation loss) will be used as the feedback for the attacker to generate the next action. The performance is evaluated on W&W 6-bus and IEEE 39-bus systems. A comparison between a multistage attack and a one-shot attack is conducted to show the significance of the multistage attack. Furthermore, different protection strategies are evaluated in simulation, which shows that the proposed reinforcement learning solution can identify optimal attack sequences under several attack objectives. It also indicates that attacker's learned information helps the defender to enhance the security of the system.
Collapse
|
19
|
Zhang P, Yuan Y, Yang H, Liu H. Near-Nash Equilibrium Control Strategy for Discrete-Time Nonlinear Systems With Round-Robin Protocol. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2019; 30:2478-2492. [PMID: 30602423 DOI: 10.1109/tnnls.2018.2884674] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
In this paper, the near-Nash equilibrium (NE) control strategies are investigated for a class of discrete-time nonlinear systems subjected to the round-robin protocol (RRP). In the studied systems, three types of complexities, namely, the additive nonlinearities, the RRP, and the output feedback form of controllers, are simultaneously taken into consideration. To tackle these complexities, an approximate dynamic programing (ADP) algorithm is first developed for NE control strategies by solving the coupled Bellman's equation. Then, a Luenberger-type observer is designed under the RRP scheduling to estimate the system states. The near-NE control strategies are implemented via the actor-critic neural networks. More importantly, the stability analysis of the closed-loop system is conducted to guarantee that the studied system with the proposed control strategies is bounded stable. Finally, simulation results are provided to demonstrate the validity of the proposed method.
Collapse
|
20
|
Zhang Q, Zhao D. Data-Based Reinforcement Learning for Nonzero-Sum Games With Unknown Drift Dynamics. IEEE TRANSACTIONS ON CYBERNETICS 2019; 49:2874-2885. [PMID: 29994780 DOI: 10.1109/tcyb.2018.2830820] [Citation(s) in RCA: 28] [Impact Index Per Article: 5.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
This paper is concerned about the nonlinear optimization problem of nonzero-sum (NZS) games with unknown drift dynamics. The data-based integral reinforcement learning (IRL) method is proposed to approximate the Nash equilibrium of NZS games iteratively. Furthermore, we prove that the data-based IRL method is equivalent to the model-based policy iteration algorithm, which guarantees the convergence of the proposed method. For the implementation purpose, a single-critic neural network structure for the NZS games is given. To enhance the application capability of the data-based IRL method, we design the updating laws of critic weights based on the offline and online iterative learning methods, respectively. Note that the experience replay technique is introduced in the online iterative learning, which can improve the convergence rate of critic weights during the learning process. The uniform ultimate boundedness of the critic weights are guaranteed using the Lyapunov method. Finally, the numerical results demonstrate the effectiveness of the data-based IRL algorithm for nonlinear NZS games with unknown drift dynamics.
Collapse
|
21
|
Narayanan V, Sahoo A, Jagannathan S, George K. Approximate Optimal Distributed Control of Nonlinear Interconnected Systems Using Event-Triggered Nonzero-Sum Games. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2019; 30:1512-1522. [PMID: 30296241 DOI: 10.1109/tnnls.2018.2869896] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
In this paper, approximate optimal distributed control schemes for a class of nonlinear interconnected systems with strong interconnections are presented using continuous and event-sampled feedback information. The optimal control design is formulated as an N -player nonzero-sum game where the control policies of the subsystems act as players. An approximate Nash equilibrium solution to the game, which is the solution to the coupled Hamilton-Jacobi equation, is obtained using the approximate dynamic programming-based approach. A critic neural network (NN) at each subsystem is utilized to approximate the Nash solution and novel event-sampling conditions, that are decentralized, are designed to asynchronously orchestrate the sampling and transmission of state vector at each subsystem. To ensure the local ultimate boundedness of the closed-loop system state and NN parameter estimation errors, a hybrid-learning scheme is introduced and the stability is guaranteed using Lyapunov-based stability analysis. Finally, implementation of the proposed event-based distributed control scheme for linear interconnected systems is discussed. For completeness, Zeno-free behavior of the event-sampled system is shown analytically and a numerical example is included to support the analytical results.
Collapse
|
22
|
Fan B, Yang Q, Tang X, Sun Y. Robust ADP Design for Continuous-Time Nonlinear Systems With Output Constraints. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2018; 29:2127-2138. [PMID: 29771666 DOI: 10.1109/tnnls.2018.2806347] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
In this paper, a novel robust adaptive dynamic programming (RADP)-based control strategy is presented for the optimal control of a class of output-constrained continuous-time unknown nonlinear systems. Our contribution includes a step forward beyond the usual optimal control result to show that the output of the plant is always within user-defined bounds. To achieve the new results, an error transformation technique is first established to generate an equivalent nonlinear system, whose asymptotic stability guarantees both the asymptotic stability and the satisfaction of the output restriction of the original system. Furthermore, RADP algorithms are developed to solve the transformed nonlinear optimal control problem with completely unknown dynamics as well as a robust design to guarantee the stability of the closed-loop systems in the presence of unavailable internal dynamic state. Via small-gain theorem, asymptotic stability of the original and transformed nonlinear system is theoretically guaranteed. Finally, comparison results demonstrate the merits of the proposed control policy.
Collapse
|
23
|
Kiumarsi B, Vamvoudakis KG, Modares H, Lewis FL. Optimal and Autonomous Control Using Reinforcement Learning: A Survey. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2018; 29:2042-2062. [PMID: 29771662 DOI: 10.1109/tnnls.2017.2773458] [Citation(s) in RCA: 110] [Impact Index Per Article: 18.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
This paper reviews the current state of the art on reinforcement learning (RL)-based feedback control solutions to optimal regulation and tracking of single and multiagent systems. Existing RL solutions to both optimal and control problems, as well as graphical games, will be reviewed. RL methods learn the solution to optimal control and game problems online and using measured data along the system trajectories. We discuss Q-learning and the integral RL algorithm as core algorithms for discrete-time (DT) and continuous-time (CT) systems, respectively. Moreover, we discuss a new direction of off-policy RL for both CT and DT systems. Finally, we review several applications.
Collapse
|
24
|
Jiang H, Zhang H. Iterative ADP learning algorithms for discrete-time multi-player games. Artif Intell Rev 2018. [DOI: 10.1007/s10462-017-9603-1] [Citation(s) in RCA: 23] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
25
|
Wei Q, Liu D, Lin Q. Discrete-Time Local Value Iteration Adaptive Dynamic Programming: Admissibility and Termination Analysis. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2017; 28:2490-2502. [PMID: 27529879 DOI: 10.1109/tnnls.2016.2593743] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/06/2023]
Abstract
In this paper, a novel local value iteration adaptive dynamic programming (ADP) algorithm is developed to solve infinite horizon optimal control problems for discrete-time nonlinear systems. The focuses of this paper are to study admissibility properties and the termination criteria of discrete-time local value iteration ADP algorithms. In the discrete-time local value iteration ADP algorithm, the iterative value functions and the iterative control laws are both updated in a given subset of the state space in each iteration, instead of the whole state space. For the first time, admissibility properties of iterative control laws are analyzed for the local value iteration ADP algorithm. New termination criteria are established, which terminate the iterative local ADP algorithm with an admissible approximate optimal control law. Finally, simulation results are given to illustrate the performance of the developed algorithm.In this paper, a novel local value iteration adaptive dynamic programming (ADP) algorithm is developed to solve infinite horizon optimal control problems for discrete-time nonlinear systems. The focuses of this paper are to study admissibility properties and the termination criteria of discrete-time local value iteration ADP algorithms. In the discrete-time local value iteration ADP algorithm, the iterative value functions and the iterative control laws are both updated in a given subset of the state space in each iteration, instead of the whole state space. For the first time, admissibility properties of iterative control laws are analyzed for the local value iteration ADP algorithm. New termination criteria are established, which terminate the iterative local ADP algorithm with an admissible approximate optimal control law. Finally, simulation results are given to illustrate the performance of the developed algorithm.
Collapse
Affiliation(s)
- Qinglai Wei
- The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
| | - Derong Liu
- School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China
| | - Qiao Lin
- The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
| |
Collapse
|
26
|
Data-driven adaptive dynamic programming for continuous-time fully cooperative games with partially constrained inputs. Neurocomputing 2017. [DOI: 10.1016/j.neucom.2017.01.076] [Citation(s) in RCA: 44] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
|
27
|
Zhao D, Zhang Q, Wang D, Zhu Y. Experience Replay for Optimal Control of Nonzero-Sum Game Systems With Unknown Dynamics. IEEE TRANSACTIONS ON CYBERNETICS 2016; 46:854-865. [PMID: 26529794 DOI: 10.1109/tcyb.2015.2488680] [Citation(s) in RCA: 36] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/05/2023]
Abstract
In this paper, an approximate online equilibrium solution is developed for an N -player nonzero-sum (NZS) game systems with completely unknown dynamics. First, a model identifier based on a three-layer neural network (NN) is established to reconstruct the unknown NZS games systems. Moreover, the identifier weight vector is updated based on experience replay technique which can relax the traditional persistence of excitation condition to a simplified condition on recorded data. Then, the single-network adaptive dynamic programming (ADP) with experience replay algorithm is proposed for each player to solve the coupled nonlinear Hamilton- (HJ) equations, where only the critic NN weight vectors are required to tune for each player. The feedback Nash equilibrium is provided by the solution of the coupled HJ equations. Based on the experience replay technique, a novel critic NN weights tuning law is proposed to guarantee the stability of the closed-loop system and the convergence of the value functions. Furthermore, a Lyapunov-based stability analysis shows that the uniform ultimate boundedness of the closed-loop system is achieved. Finally, two simulation examples are given to verify the effectiveness of the proposed control scheme.
Collapse
|
28
|
Online approximate solution of HJI equation for unknown constrained-input nonlinear continuous-time systems. Inf Sci (N Y) 2016. [DOI: 10.1016/j.ins.2015.09.001] [Citation(s) in RCA: 52] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
|