Xue Shan, Luo Biao, Liu Derong, Gao Ying
School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China; Peng Cheng Laboratory, Shenzhen 518000, China.
School of Automation, Central South University, Changsha 410083, China; Peng Cheng Laboratory, Shenzhen 518000, China.
Neural Netw. 2022 Aug;152:212-223. doi: 10.1016/j.neunet.2022.04.013. Epub 2022 Apr 21.
In this paper, an event-triggered integral reinforcement learning (IRL) algorithm is developed for the nonzero-sum game problem with asymmetric input saturation. First, for each player, a novel non-quadratic value function with a discount factor is designed, and the coupled Hamilton-Jacobi equation that does not require a complete knowledge of the game is derived by using the idea of IRL. Second, the execution of each player is based on the event-triggered mechanism. In the implementation, an adaptive dynamic programming based learning scheme using a single critic neural network (NN) is developed. Experience replay technique is introduced into the classical gradient descent method to tune the weights of the critic NN. The stability of the system and the elimination of Zeno behavior are proved. Finally, simulation experiments verify the effectiveness of the event-triggered IRL algorithm.
本文针对具有非对称输入饱和的非零和博弈问题，提出了一种事件触发积分强化学习（IRL）算法。首先，为每个参与者设计了一个带有折扣因子的新型非二次价值函数，并利用IRL思想推导出了无需完全了解博弈的耦合哈密顿 - 雅可比方程。其次，每个参与者的执行基于事件触发机制。在实现过程中，开发了一种基于自适应动态规划的单评判神经网络（NN）学习方案。将经验回放技术引入经典梯度下降方法来调整评判NN的权重。证明了系统的稳定性和芝诺行为的消除。最后，仿真实验验证了事件触发IRL算法的有效性。
