基于半自治agent的profit-sharing增强学习方法研究

在基于半自治agent的系统中应用profit-sharing增强学习方法,并与基于动态规划的Q-learning增强学习方法进行比较,在不确定因素较多的动态环境中,当系统状态变化不是一个马尔科夫过程时profit-sharing方法具有很大优势。根据半自治agent中半自治的特性——受制性,提出了一种面向基于半自治agent的增强学习模型,以战场仿真中安全隐蔽的寻找模型为实例对基于半自治agent的profit-sharing增强学习模型进行了试验分析。

Integrating Macro and Micro Perspectives on Profit-Sharing in China

Despite considerable interest in the adoption of profit-sharing plans in small firms in China, there lacks a comprehensive theoretical framework to explore why these plans are adopted. Much of the literature on profit-sharing originates from a pure economic perspective based upon agency theory. However, when profit-sharing is adopted in small firms at the discretion of the CEO, often psychological mechanisms become an important factor. This paper provides an integrated theoretical framework combining the economic perspective with the psychological perspective to investigate the reason why CEOs in Chinese private firms choose to adopt profit sharing schemes. Specifically, we develop a model examining both internal and external factors specific to the individual and the firm. We then theorize whether the reasons for using the profit-sharing plans will ultimately lead to improved firm performance.

Contract stability and default risk control of pig farming in the company and farmer mode

To investigate contract stability in the company and farmer mode and to explore control measures of market price risk and production risk,a multiperiod game model was established in this study.Considering multiple periods and losses caused by deaths simultaneously,a stable contract price interval depending on the breaching penalty,transaction cost,spot market price,and quantity of pigs was observed.Results indicate that the higher the penalty and transaction cost savings,the better the stability of the contract;the contract price should be negotiated around the weighted average of the spot market price.When the production risk is higher,hog insurance can significantly improve the contract stability;when the market price is lower,hog price index insurance improves the contract stability by guaranteeing the company income;when the market price is higher,the profit-returning mechanism improves the stability by protecting farmers incomes.Applying three measures simultaneously results in the best stability.Examples based on data from 2014 to 2018 in Henan Province,China,were given.

A Policy-Improving System for Adaptability to Dynamic Environments Using Mixture Probability and Clustering Distribution

Along with the increasing need for rescue robots in disasters such as earthquakes and tsunami, there is an urgent need to develop robotics software for learning and adapting to any environment. A reinforcement learning (RL) system that improves agents’ policies for dynamic environments by using a mixture model of Bayesian networks has been proposed, and is effective in quickly adapting to a changing environment. However, the increase in computational complexity requires the use of a high-performance computer for simulated experiments and in the case of limited calculation resources, it becomes necessary to control the computational complexity. In this study, we used an RL profit-sharing method for the agent to learn its policy, and introduced a mixture probability into the RL system to recognize changes in the environment and appropriately improve the agent’s policy to adjust to a changing environment. We also introduced a clustering distribution that enables a smaller, suitable selection, while maintaining a variety of mixture probability elements in order to reduce the computational complexity and simultaneously maintain the system’s performance. Using our proposed system, the agent successfully learned the policy and efficiently adjusted to the changing environment. Finally, control of the computational complexity was effective, and the decline in effectiveness of the policy improvement was controlled by using our proposed system.

A Reinforcement Learning System to Dynamic Movement and Multi-Layer Environments

There are many proposed policy-improving systems of Reinforcement Learning (RL) agents which are effective in quickly adapting to environmental change by using many statistical methods, such as mixture model of Bayesian Networks, Mixture Probability and Clustering Distribution, etc. However such methods give rise to the increase of the computational complexity. For another method, the adaptation performance to more complex environments such as multi-layer environments is required. In this study, we used profit-sharing method for the agent to learn its policy, and added a mixture probability into the RL system to recognize changes in the environment and appropriately improve the agent’s policy to adjust to the changing environment. We also introduced a clustering that enables a smaller, suitable selection in order to reduce the computational complexity and simultaneously maintain the system’s performance. The results of experiments presented that the agent successfully learned the policy and efficiently adjusted to the changing in multi-layer environment. Finally, the computational complexity and the decline in effectiveness of the policy improvement were controlled by using our proposed system.