Multi-player H ∞ Differential Game using On-Policy and Off-Policy Reinforcement Learning
2020 IEEE 16TH INTERNATIONAL CONFERENCE ON CONTROL & AUTOMATION (ICCA)(2020)
摘要
This paper studies a multi-player H ∞ differential game for systems of general linear dynamics. In this game, multiple players design their control inputs to minimize their cost functions in the presence of worst-case disturbances. We first derive the optimal control and disturbance policies using the solutions to Hamilton-Jacobi-Isaacs (HJI) equations. We then prove that the derived optimal policies stabilize the system and constitute a Nash equilibrium solution. Two integral reinforcement learning (IRL) -based algorithms, including the policy iteration IRL and off-policy IRL, are developed to solve the differential game online. We show that the off-policy IRL can solve the multi-player H ∞ differential game online without using any system dynamics information. Simulation studies are conducted to validate the theoretical analysis and demonstrate the effectiveness of the developed learning algorithms.
更多查看译文
关键词
learning algorithms,Nash equilibrium solution,system stability,on-policy reinforcement learning,multiplayer H∞ differential game,cost function minimization,system dynamics information,off-policy IRL,integral reinforcement learning -based algorithms,optimal policies,Hamilton-Jacobi-Isaacs equations,disturbance policies,optimal control,worst-case disturbances,general linear dynamics,off-policy reinforcement learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络