In the evolutionary game of the same task for groups,the changes in game rules,personal interests,the crowd size,and external supervision cause uncertain effects on individual decision-making and game results.In the M...In the evolutionary game of the same task for groups,the changes in game rules,personal interests,the crowd size,and external supervision cause uncertain effects on individual decision-making and game results.In the Markov decision framework,a single-task multi-decision evolutionary game model based on multi-agent reinforcement learning is proposed to explore the evolutionary rules in the process of a game.The model can improve the result of a evolutionary game and facilitate the completion of the task.First,based on the multi-agent theory,to solve the existing problems in the original model,a negative feedback tax penalty mechanism is proposed to guide the strategy selection of individuals in the group.In addition,in order to evaluate the evolutionary game results of the group in the model,a calculation method of the group intelligence level is defined.Secondly,the Q-learning algorithm is used to improve the guiding effect of the negative feedback tax penalty mechanism.In the model,the selection strategy of the Q-learning algorithm is improved and a bounded rationality evolutionary game strategy is proposed based on the rule of evolutionary games and the consideration of the bounded rationality of individuals.Finally,simulation results show that the proposed model can effectively guide individuals to choose cooperation strategies which are beneficial to task completion and stability under different negative feedback factor values and different group sizes,so as to improve the group intelligence level.展开更多
Autonomous cooperation of unmanned swarms is the research focus on“new combat forces”and“disruptive technologies”in military fields.The mechanism design is the fundamental way to realize autonomous cooperation.Fac...Autonomous cooperation of unmanned swarms is the research focus on“new combat forces”and“disruptive technologies”in military fields.The mechanism design is the fundamental way to realize autonomous cooperation.Facing the realistic requirements of a swarm network dynamic adjustment under the background of high dynamics and strong confrontation and aiming at the optimization of the coordination level,an adaptive dynamic reconfiguration mechanism of unmanned swarm topology based on an evolutionary game is designed.This paper analyzes military requirements and proposes the basic framework of autonomous cooperation of unmanned swarms,including the emergence of swarm intelligence,information network construction and collaborative mechanism design.Then,based on the framework,the adaptive dynamic reconfiguration mechanism is discussed in detail from two aspects:topology dynamics and strategy dynamics.Next,the unmanned swarms’community network is designed,and the network characteristics are analyzed.Moreover,the mechanism characteristics are analyzed by numerical simulation,focusing on the impact of key parameters,such as cost,benefit coefficient and adjustment rate on the level of swarm cooperation.Finally,the conclusion is made,which is expected to provide a theoretical reference and decision support for cooperative mode design and combat effectiveness generation of unmanned swarm operations.展开更多
This paper analyzes a problem processing mechanism in a new collaboration system between the main manufacturer and the supplier in the"main manufacturer-supplier"mode,which has been widely applied in the col...This paper analyzes a problem processing mechanism in a new collaboration system between the main manufacturer and the supplier in the"main manufacturer-supplier"mode,which has been widely applied in the collaborative development management of the complex product.This paper adopts the collaboration theory,the evolutionary game theory and numerical simulation to analyze the decision-making mechanism where one upstream supplier and one downstream manufacturer must process an unpredicted problem without any advance contract in common.Results show that both players'decision-makings are in some correlation with the initial state,income impact coefficients,and dealing cost.It is worth noting that only the initial state influences the final decision,while income impact coefficients and dealing cost just influence the decision process.This paper shows reasonable and practical suggestions for the manufacturer and supplier in a new collaboration system for the first time and is dedicated to the managerial implications on reducing risks of processing problems.展开更多
The research of cluster supply chains is a new direction and a hotspot of the industrial cluster theory. On the condition of the coordination game, the enterprises may be stuck on the non-efficient equilibrium status,...The research of cluster supply chains is a new direction and a hotspot of the industrial cluster theory. On the condition of the coordination game, the enterprises may be stuck on the non-efficient equilibrium status, which becomes an important problem that must be considered on cluster supply chains. A symmetrical coordination game model is constituted to describe the competition and cooperation relationship of the same-quality manufacturers on cluster supply chains. The methods of the non-cooperation game theory and the evolutionary game theory are respectively used to analyze the model, whose parameters＇ influences under each method are then compared. It can be concluded that the analysis of the evolutionary game theory is more realistic and practical. Finally, three approaches are considered to break away from being path-dependence locked-in non-efficient status during this coordination game evolutionary process, which provide the development of cluster supply chains with an effective forecasting and Pareto optimizing method.展开更多
In this paper the nature of predatory pricing is analyzed with genetic algorithms. It is found that, even under the same payoff structure, the results of the coevolution of weak monopolists and entrants are sensitive ...In this paper the nature of predatory pricing is analyzed with genetic algorithms. It is found that, even under the same payoff structure, the results of the coevolution of weak monopolists and entrants are sensitive to the representationof the decisionmaking process. Two representations are studied in this paper. One is the actionbased representation and the other the strategybased representation. The former is to represent a naive mind and the latter is to capture a sophisticated mind. For the actionbased representation, the convergence results are easily obtained and predatory pricing is only temporary in all simulations. However, for the strategybased representation, predatory pricing is not a rare phenomenon and its appearance is cyclical but not regular. Therefore, the snowball effect of a little craziness observed in the experimental game theory wins its support from this representation. Furthermore, the nature of predatory pricing has something to do with the evolution of the sophisticated rather than the naive minds.展开更多
基金supported by the National Key R&D Program of China(2017YFB1400105).
文摘In the evolutionary game of the same task for groups,the changes in game rules,personal interests,the crowd size,and external supervision cause uncertain effects on individual decision-making and game results.In the Markov decision framework,a single-task multi-decision evolutionary game model based on multi-agent reinforcement learning is proposed to explore the evolutionary rules in the process of a game.The model can improve the result of a evolutionary game and facilitate the completion of the task.First,based on the multi-agent theory,to solve the existing problems in the original model,a negative feedback tax penalty mechanism is proposed to guide the strategy selection of individuals in the group.In addition,in order to evaluate the evolutionary game results of the group in the model,a calculation method of the group intelligence level is defined.Secondly,the Q-learning algorithm is used to improve the guiding effect of the negative feedback tax penalty mechanism.In the model,the selection strategy of the Q-learning algorithm is improved and a bounded rationality evolutionary game strategy is proposed based on the rule of evolutionary games and the consideration of the bounded rationality of individuals.Finally,simulation results show that the proposed model can effectively guide individuals to choose cooperation strategies which are beneficial to task completion and stability under different negative feedback factor values and different group sizes,so as to improve the group intelligence level.
基金supported by the National Natural Science Foundation of China(71901217)the Key Primary Research Project of Primary Strengthening Program(2020-JCJQ-ZD-007).
文摘Autonomous cooperation of unmanned swarms is the research focus on“new combat forces”and“disruptive technologies”in military fields.The mechanism design is the fundamental way to realize autonomous cooperation.Facing the realistic requirements of a swarm network dynamic adjustment under the background of high dynamics and strong confrontation and aiming at the optimization of the coordination level,an adaptive dynamic reconfiguration mechanism of unmanned swarm topology based on an evolutionary game is designed.This paper analyzes military requirements and proposes the basic framework of autonomous cooperation of unmanned swarms,including the emergence of swarm intelligence,information network construction and collaborative mechanism design.Then,based on the framework,the adaptive dynamic reconfiguration mechanism is discussed in detail from two aspects:topology dynamics and strategy dynamics.Next,the unmanned swarms’community network is designed,and the network characteristics are analyzed.Moreover,the mechanism characteristics are analyzed by numerical simulation,focusing on the impact of key parameters,such as cost,benefit coefficient and adjustment rate on the level of swarm cooperation.Finally,the conclusion is made,which is expected to provide a theoretical reference and decision support for cooperative mode design and combat effectiveness generation of unmanned swarm operations.
基金supported by the National Natural Science Foundation of China(7117111271502073)。
文摘This paper analyzes a problem processing mechanism in a new collaboration system between the main manufacturer and the supplier in the"main manufacturer-supplier"mode,which has been widely applied in the collaborative development management of the complex product.This paper adopts the collaboration theory,the evolutionary game theory and numerical simulation to analyze the decision-making mechanism where one upstream supplier and one downstream manufacturer must process an unpredicted problem without any advance contract in common.Results show that both players'decision-makings are in some correlation with the initial state,income impact coefficients,and dealing cost.It is worth noting that only the initial state influences the final decision,while income impact coefficients and dealing cost just influence the decision process.This paper shows reasonable and practical suggestions for the manufacturer and supplier in a new collaboration system for the first time and is dedicated to the managerial implications on reducing risks of processing problems.
基金the National Natural Science Foundation of China (60374023)the Natural ScienceFoundation of Guangdong Province (011629).
文摘The research of cluster supply chains is a new direction and a hotspot of the industrial cluster theory. On the condition of the coordination game, the enterprises may be stuck on the non-efficient equilibrium status, which becomes an important problem that must be considered on cluster supply chains. A symmetrical coordination game model is constituted to describe the competition and cooperation relationship of the same-quality manufacturers on cluster supply chains. The methods of the non-cooperation game theory and the evolutionary game theory are respectively used to analyze the model, whose parameters＇ influences under each method are then compared. It can be concluded that the analysis of the evolutionary game theory is more realistic and practical. Finally, three approaches are considered to break away from being path-dependence locked-in non-efficient status during this coordination game evolutionary process, which provide the development of cluster supply chains with an effective forecasting and Pareto optimizing method.
文摘In this paper the nature of predatory pricing is analyzed with genetic algorithms. It is found that, even under the same payoff structure, the results of the coevolution of weak monopolists and entrants are sensitive to the representationof the decisionmaking process. Two representations are studied in this paper. One is the actionbased representation and the other the strategybased representation. The former is to represent a naive mind and the latter is to capture a sophisticated mind. For the actionbased representation, the convergence results are easily obtained and predatory pricing is only temporary in all simulations. However, for the strategybased representation, predatory pricing is not a rare phenomenon and its appearance is cyclical but not regular. Therefore, the snowball effect of a little craziness observed in the experimental game theory wins its support from this representation. Furthermore, the nature of predatory pricing has something to do with the evolution of the sophisticated rather than the naive minds.
