With the methods of the historical analysis,this paper analyses the present incentive and restrictive mechanism--yearly salary,stock holding and profit sharing system,and establishes a modified incentive and restrictive compensation function.
针对我国上市公司激励约束机制的发展明显滞后于经理层治理的发展问题,利用历史方法,分析了现有激励约束机制——年薪制、持股制和利润分享制的作用,构建了改进的激励约束性报酬函数。
Survey of apprenticeship learning based on reward function approximating;
基于回报函数逼近的学徒学习综述
Survey of apprenticeship learning based on reward function learning
回报函数学习的学徒学习综述
During the learning process,the reward function is controlled automatically to earn the optimal policy.
针对机器人足球比赛的多智能体环境下智能体的训练问题,提出了一种将模糊控制与Q-Learning相结合的学习方法,并在学习过程中自动调节回报函数以获得最优策略,此方法的有效性在中型组的仿真平台上得到了验证,并取得了较好效果,还可将它改进应用于其他多智体环境。