Nonlinear Approximate Optimal Control Based on Integral Reinforcement Learning

This paper focuses on the optimal containment control problem for the nonlinear multiagent systems with partially unknown dynamics via an integral reinforcement learning algorithm. By employing integral reinforcement learning, the requirement of the drift dynamics is relaxed. The integral reinforcement learning method is proved to be equivalent to the model-based policy iteration, which guarantees the convergence of the proposed control algorithm. For each follower, the Hamilton-Jacobi-Bellman equation is solved by a single critic neural network with a modified updating law which guarantees the weight error dynamic to be asymptotically stable. Through using input-output data, the approximate optimal containment control protocol of each follower is obtained by applying the critic neural network. The closed-loop containment error system is guaranteed to be stable under the proposed optimal containment control scheme. Simulation results demonstrate the effectiveness of the presented control scheme.

This paper develops an integral reinforcement learning (IRL) controller for a class of high-order multivariable nonlinear systems with unknown control coefficients (UCCs). A new long-term performance index is first presented, and then the critic neural network (NN) and the action NN are presented to estimate the unobtainable long-term performance index and the unknown drift of systems, respectively. By combining the critic and action NNs with Nussbaum-type functions, the IRL controllers for high-order, nonsquare multivariable systems are proposed to cope with the problem of UCCs. The analysis are given to illustrate that the stability of the closed-loop system can be obtained, and the signals of the closed-loop systems are semiglobally uniformly ultimately bounded (UUB). Finally, one simulation example is provided to show the effectiveness of the proposed IRL controllers.

Optimal Tracking Control Based on Integral Reinforcement Learning for An Underactuated Drone

Benefitting from the technology of integral reinforcement learning, the nonzero sum (NZS) game for distributed parameter systems is effectively solved in this paper when the information of system dynamics are unavailable. The Karhunen-Loève decomposition (KLD) is employed to convert the partial differential equation (PDE) systems into high-order ordinary differential equation (ODE) systems. Moreover, the off-policy IRL technology is introduced to design the optimal strategies for the NZS game. To confirm that the presented algorithm will converge to the optimal value functions, the traditional adaptive dynamic programming (ADP) method is first discussed. Then, the equivalence between the traditional ADP method and the presented off-policy method is proved. For implementing the presented off-policy IRL method, actor and critic neural networks are utilized to approach the value functions and control strategies in the iteration process, individually. Finally, a numerical simulation is shown to illustrate the effectiveness of the proposal off-policy algorithm.

Dynamic compensator-based near-optimal control for unknown nonaffine systems via integral reinforcement learning

The goethite iron-removal process is an important procedure to remove the iron ions from the zinc hydrometallurgy. However, as a coherent system with complex reaction mechanism, associated uncertainties, and interconnected adjacent reactors, it is difficult for the process to accurately control the ion concentration. Because a large amount of historical data can be obtained during the process, an optimal control algorithm based on off-policy reinforcement learning is proposed in this paper to overcome these difficulties. According to the historical data, the weights of neural network are learned offline, and the optimal control strategy is solved online. Firstly, a bounded function is introduced to define the maximum effect of the coherent system on the subsystem cost function and to extend the cost function of the nominal system, so that the decentralized guaranteed cost control problem can be expressed as the optimal control problem of the nominal system. Then, an approximate iterative control algorithm based on actor-critic structure is proposed. The actor and critic neural networks are used to approximate control strategies and cost functions respectively. To achieve complete off-line, a new neural network is added to the actor-critic structure to approximate a part of the unknown system structure, and the three neural network parameters are optimized by the state transition algorithm. Finally, the strategy update and strategy iteration operations are performed alternately to learn optimal control strategies. The effectiveness and flexibility of the proposed off-policy optimal control method is validated by data from a real industrial goethite iron-removal process.

In order to obviate the requirement of drift dynamics in adaptive dynamic programming, integral reinforcement learning (IRL) has been proposed as an alternate formulation of Bellman equation. However control coupling dynamics is still needed to obtain closed-form expression of optimal control effort. In addition to this, initial stabilizing controller and two sets of neural networks (NN) (known as Actor-Critic) are required to implement IRL scheme. In order to remedy these, this paper presents a critic-only IRL controller coupled with an experience replay (ER)-based identifier to solve optimal tracking control problem for an unknown continuous-time systems under actuator constraints. The presented control architecture is shown to yield tighter residual sets for state tracking error and error in NN weights. The simulation results establish the efficacy of the presented control scheme on continuous-time systems.

An online adaptive optimal control is proposed for continuous-time nonlinear systems with completely unknown dynamics, which is achieved by developing a novel identifier-critic-based approximate dynamic programming algorithm with a dual neural network (NN) approximation structure. First, an adaptive NN identifier is designed to obviate the requirement of complete knowledge of system dynamics, and a critic NN is employed to approximate the optimal value function. Then, the optimal control law is computed based on the information from the identifier NN and the critic NN, so that the actor NN is not needed. In particular, a novel adaptive law design method with the parameter estimation error is proposed to online update the weights of both identifier NN and critic NN simultaneously, which converge to small neighbourhoods around their ideal values. The closed-loop system stability and the convergence to small vicinity around the optimal solution are all proved by means of the Lyapunov theory. The proposed adaptation algorithm is also improved to achieve finite-time convergence of the NN weights. Finally, simulation results are provided to exemplify the efficacy of the proposed methods.

This paper presents a model-free optimal tracking control algorithm for an aircraft skin inspection robot with constrained-input and input time-delay. To tackle the input time-delay problem, the original system is transformed into a delay-free system with constrained-input and unknown input coupling term. In order to overcome the optimal control problem subject to constrained-input, a discounted value function is employed. In general, it is known that the HJB equation does not admit a classical smooth solution. Moreover, since the input coupling term of the delay-free system is unknown, a model-free integral reinforcement learning(IRL) algorithm which only requires the system sampling data generated by arbitrary different control inputs and external disturbances is proposed. The model-free IRL method is implemented on an actor-critic neural network (NN) structure. A system sampling data set is utilized to learn the value function and control policy. Finally, the simulation verifies the effectiveness of the proposed algorithm.

This paper is concentrated on aperiodic sampling and adaptive learning in continuous-time nonlinear systems. The objective is to find the optimal control policy by minimizing an infinite-quadratic cost function in an online fashion. An algorithm based on integral reinforcement learning is proposed for problems with unknown model information, and a novel dynamic triggering method is combined for saving communication as much as possible. The identifying neural network is utilized to free the input dynamics and critic neural network is constructed to approximate the cost function. The weight convergence and asymptotic stability are theoretically elaborated, and afterwards, a numerical example is presented for illustrating the effectiveness and superiority of the algorithm by comparison.

In this study, a finite‐time online optimal controller was designed for a nonlinear wheeled mobile robotic system (WMRS) with inequality constraints, based on reinforcement learning (RL) neural networks. In addition, an extended cost function, obtained by introducing a penalty function to the original long‐time cost function, was proposed to deal with the optimal control problem of the system with inequality constraints. A novel Hamilton‐Jacobi‐Bellman (HJB) equation containing the constraint conditions was defined to determine the optimal control input. Furthermore, two neural networks (NNs), a critic and an actor NN, were established to approximate the extended cost function and the optimal control input, respectively. The adaptation laws of the critic and actor NN were obtained with the gradient descent method. The semi‐global practical finite‐time stability (SGPFS) was proved using Lyapunov's stability theory. The tracking error converges to a small region near zero within the constraints in a finite period. Finally, the effectiveness of the proposed optimal controller was verified by a simulation based on a practical wheeled mobile robot model.

Integral reinforcement learning and experience replay for adaptive optimal control of partially-unknown constrained-input continuous-time systems

In this paper, we develop an integral reinforcement learning algorithm based on policy iteration to learn online the Nash equilibrium solution for a two-player zero-sum differential game with completely unknown linear continuous-time dynamics. This algorithm is a fully model-free method solving the game algebraic Riccati equation forward in time. The developed algorithm updates value function, control and disturbance policies simultaneously. The convergence of the algorithm is demonstrated to be equivalent to Newton's method. To implement this algorithm, one critic network and two action networks are used to approximate the game value function, control and disturbance policies, respectively, and the least squares method is used to estimate the unknown parameters. The effectiveness of the developed scheme is demonstrated in the simulation by designing an H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</sub> state feedback controller for a power system.

In this paper, a comparison is addressed between two methods, that is, the optimal tracking control methods of unknown nonlinear systems with and without constrained input. Firstly, the optimal tracking problem for a class of affine nonlinear system is formulated. The tracking cost functions are also defined, both for the two methods. The two methods are proved to be equivalent as the actuator bound is large enough. Integral reinforcement learning (IRL) algorithm is employed to solve the optimal tracking problem by using only system data. To facilitate the implementation of the IRL algorithm, the actor-critic neural network technique and the least squares method are employed in approximating the unknown weights iteratively. In the simulation, a detailed comparison is given to demonstrate the relationship between the two methods in the aspects of control input and tracking cost value.

In this brief, a <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula> -learning algorithm is designed to solve the optimal tracking control problem (OTCP) for stochastic system with Markovian jump. The problem is formulated by stochastic augmented system composed of the dynamic system and the reference trajectory system and then using ideas from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula> -learning to provide a solution. Namely, a critic neural network (NN) is used to estimate the optimal cost function while an actor NN is used to approximate the optimal controller. Moreover, both the requirements of transition probability and system matrix are avoided via the designed <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula> -learning algorithm. Finally, we apply the designed algorithm in a single-area power system to track continuous sinusoidal waveforms, and the simulation result is provided to show the effectiveness and applicability of the algorithm.