欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
研究离散时间跳变线性二次（JLQ）模型的直接自适应最优控制问题．将强化学习的理论和方法应用于JLQ模型，设计基于Q函数的策略迭代算法，以优化系统性能．在系统参数以及模态跳变概率未知的情况下，Q函数对应的参数矩阵，可通过观察给定策略下系统行为，应用递归最小二乘算法在线估计．基于此参数矩阵，可构造出新的策略使得系统性能更优．该算法可收敛到最优策略．
英文摘要：
The discrete-time direct adaptive optimal control problem of jump linear quadratic （JLQ） model is investigated. Reinforcement learning theory and approaches are applied to JLQ model and Q function-based policy iteration algorithm is designed to optimize system performance. When the system parameters and jump probabilities of modes are unknown, the parameter matrix with respcet to Q function is online estimated by observing system behavior under a given control law with recursive least square algorithm. Moreover, based on this matrix, a new policy which can improve system performanc is constructed. The algorithm can converge to the optimal policy.
同期刊论文项目
同项目期刊论文
A Location-free Algorithm of Energy-Efficient Connected Coverage for High Density Wireless Sensor Ne
An adaptive sampling algorithm for simulation-based optimization with descriptive complexity prefere
A formal model for analyzing drug combination effects and its application in TNF-?-induced NF?B path
Efficient Simulation Method for General Assembly Systems with Material Handlings Based on Aggregated
Formulation and a Simulation Based Algorithm for Line-side Buffer Assignment Problem in Systems of G
Optimal algorithms for online scheduling on parallel machines to minimize the makespan with a period
Semi-online scheduling on 2 machines under a grade of service provision with bounded processing time
Linear optimization modeling of consistency issues in group decision making based on fuzzy preferenc
Fast Unit Commitment Based on Optimal Linear Approximation to Nonlinear Fuel Cost: Error Analysis an
期刊信息
位置：