.png){kind=icon}
返回
Safe reinforcement learning for dynamical games
.png){kind=icon}
PRE
AI
DOI：10.1002/rnc.4962.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This article presents a novel actor-critic-barrier structure for the multiplayer safety-critical systems. Non-zero-sum (NZS) games with full-state constraints are first transformed into unconstrained NZS games using a barrier function. The barrier function is capable of dealing with both symmetric and asymmetric constraints on the state. It is shown that the Nash equilibrium of the unconstrained NZS guarantees to stabilize the original multiplayer system. The barrier function is combined with an actor-critic structure to learn the Nash equilibrium solution in an online fashion. It is shown that integrating the barrier function with the actor-critic structure guarantees that the constraints will not be violated during learning. Boundedness and stability of the closed-loop signals are analyzed. The efficacy of the presented approach is finally demonstrated by using a simulation example.
Keyword:
adaptive optimal learning
barrier-actor-critic structure
Nash equilibrium
safety-aware games
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.2
论文数:
7.0K
被引数:
1.4W
机构
引用论文
分享收藏分享收藏Control Barrier Function Based Quadratic Programs for Safety Critical Systems用于安全关键系统的基于控制障碍函数的二次程序
OAAI
OAAI分享收藏Online barrier-actor-critic learning for H∞ control with full-state constraints and input saturation
PREAI
分享收藏Data-Based Reinforcement Learning for Nonzero-Sum Games With Unknown Drift Dynamics基于数据的具有未知漂移动态的非零和游戏的强化学习
PREAI
分享收藏Adaptive tracking control of uncertain MIMO nonlinear systems with input constraints具有输入约束的不确定MIMO非线性系统的自适应跟踪控制.png)
AUTOMATICA
AUTOMATICAIF5.9
PREAI
分享收藏Adaptive Neural Network Control of an Uncertain Robot With Full-State Constraints具有全状态约束的不确定机器人自适应神经网络控制
PREAI
分享收藏
查看更多内容