An evolutionary game theory-based machine learning framework for predicting mandatory lane change decision

Mandatory lane change(MLC)is likely to cause traffic oscillations,which have a negative impact on traffic efficiency and safety.There is a rapid increase in research on mandatory lane change decision(MLCD)prediction,which can be categorized into physics-based models and machine-learning models.Both types of models have their advantages and disadvantages.To obtain a more advanced MLCD prediction method,this study proposes a hybrid architecture,which combines the Evolutionary Game Theory(EGT)based model(considering data efficient and interpretable)and the Machine Learning(ML)based model(considering high prediction accuracy)to model the mandatory lane change decision of multi-style drivers(i.e.EGTML framework).Therefore,EGT is utilized to introduce physical information,which can describe the progressive cooperative interactions between drivers and predict the decision-making of multi-style drivers.The generalization of the EGTML method is further validated using four machine learning models:ANN,RF,LightGBM,and XGBoost.The superiority of EGTML is demonstrated using real-world data(i.e.,Next Generation SIMulation,NGSIM).The results of sensitivity analysis show that the EGTML model outperforms the general ML model,especially when the data is sparse.

Evolutionary dynamics of tax-based strong altruistic reward andpunishment in a public goods game

In public goods games, punishments and rewards have been shown to be effective mechanisms for maintaining individualcooperation. However, punishments and rewards are costly to incentivize cooperation. Therefore, the generation ofcostly penalties and rewards has been a complex problem in promoting the development of cooperation. In real society,specialized institutions exist to punish evil people or reward good people by collecting taxes. We propose a strong altruisticpunishment or reward strategy in the public goods game through this phenomenon. Through theoretical analysis and numericalcalculation, we can get that tax-based strong altruistic punishment (reward) has more evolutionary advantages thantraditional strong altruistic punishment (reward) in maintaining cooperation and tax-based strong altruistic reward leads toa higher level of cooperation than tax-based strong altruistic punishment.

Environmental options of local governments for regional air pollution joint control:application of evolutionary game theory

Apanage management is currently the main method used to control air pollution in China,but it has proved to be inefficient for controlling transboundary air pollution.As a result,China’s central government is demanding joint control of regional air pollution.From the perspective of cooperation benefits,we adopt the evolutionary game theory(EGT)to analyse evolutionary trends of regional authorities’behaviours and their stable strategy in the campaign for joint control of regional air pollution.A case study,the intergovernmental cooperation management for‘APEC Blue’,is taken to illustrate the intergovernmental game.The result shows that an evolutionarily stable strategy(ESS)of‘joint control’for local governments depends on individual region’s benefits and collaboration revenues.Local governments should be encouraged in collaborating with their neighbouring governments,because a certain amount of transaction costs will not undermine their cooperation.With regards to the case study,joint control through executive orders is unpractical in the Beijing–Tianjin–Hebei region.‘APEC Blue’can only be temporary and the failure of such collaboration for long-term regional air pollution control is inevitable because of its high control costs,economic loss,transaction costs and low common profits.

Evolutionary game analysis of problem processing mechanism in new collaboration

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.

Analysis of the Choice of Return Mechanism of PPP Model in Rural Human Settlement Improvement under the Rural Revitalization Strat­egy:Research Based on the Perspective of Evolutionary Game

The improvement of rural human settlement environment is a significant direction of the rural revitalization strategy.Based on the finite rational evolutionary game theory,a cooperative behavior evolutionary game model of rural human settlement environment improvement PPP model with local government,social capital and rural residents as the main game players with the reward mechanism of Government Payment and one with the reward mechanism of Viability Gap Funding are constructed.Comparing the total project revenue of two reward mechanisms,the thesis will obtain the effects of choosing the reward mechanism of rural human settlement improvement PPP.Finally,available suggestions are made to the decision of the reward mechanism of PPP project about rural human settlement environment,thus promoting the application and development of PPP in rural environmental management and to promote sustainable improvement of rural habitat improvement.

Non-monotonic behavior of jam probability and stretchedexponential distribution in pedestrian counterflow

We adopt a floor field cellular automata model to study the statistical properties of bidirectional pedestrian flow movingin a straight corridor. We introduce a game-theoretic framework to deal with the conflict of multiple pedestrians tryingto move to the same target location. By means of computer simulations, we show that the complementary cumulative distributionof the time interval between two consecutive pedestrians leaving the corridor can be fitted by a stretched exponentialdistribution, and surprisingly, the statistical properties of the two types of pedestrian flows are affected differently by theflow ratio, i.e., the ratio of the pedestrians walking toward different directions. We also find that the jam probability exhibitsa non-monotonic behavior with the flow ratio, where the worst performance arises at an intermediate flow ratio of around0.2. Our simulation results are consistent with some empirical observations, which suggest that the peculiar characteristicsof the pedestrians may attributed to the anticipation mechanism of collision avoidance.

Coordination game model of co-opetition relationship on cluster supply chains

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.

RTRC:A Reputation-Based Incentive Game Model for Trustworthy Crowdsourcing Service

The ubiquity of mobile devices have promoted the prosperity of mobile crowd systems, which recruit crowds to contribute their resources for performing tasks. Yet, due to the various resource consumption, the crowds may be reluctant to join and contribute information. Thus, the low participation level of crowds will be a hurdle that prevents the adoption of crowdsourcing. A critical challenge for these systems is how to design a proper mechanism such that the crowds spontaneously act as suppliers to contribute accurate information. Most of existing mechanisms ignore either the honesty of crowds or requesters respectively. In this paper, considering the honesty of both, we propose a game-based incentive mechanism, namely RTRC, to stimulate the crowds to contribute accurate information and to motivate the requesters to return accurate feedbacks. In addition, an evolutionary game is designed to model the dynamic of user-strategy selection. Specially, the replicator dynamic is applied to model the adaptation of strategy interactions taking into account the dynamic nature in time dependence and we also derive the evolutionarily stable strategies(ESSs) for users. Finally, empirical results over the simulations show that all the requesters and suppliers will select honest strategy to maximize their profit.

A 2-stage strategy updating rule promotes cooperation in the prisoner's dilemma game

In this study,we propose a spatial prisoner＇s dilemma game model with a 2-stage strategy updating rule,and focus on the cooperation behavior of the system.In the first stage,i.e.,the pre-learning stage,a focal player decides whether to update his strategy according to the pre-learning factor β and the payoff difference between himself and the average of his neighbors.If the player makes up his mind to update,he enters into the second stage,i.e.,the learning stage,and adopts a strategy of a randomly selected neighbor according to the standard Fermi updating rule.The simulation results show that the cooperation level has a non-trivial dependence on the pre-learning factor.Generally,the cooperation frequency decreases as the pre-learning factor increases;but a high cooperation level can be obtained in the intermediate region of- 3〈 β 〈-1.We then give some explanations via studying the co-action of pre-learning and learning.Our results may sharpen the understanding of the influence of the strategy updating rule on evolutionary games.

A tripartite evolutionary game analysis of providing subsidies for pick-up/drop-off strategy in carpooling problem

Although the pick-up/drop-off(PUDO)strategy in carpooling offers the convenience of short-distance walking for passengers during boarding and disembarking,there is a noticeable hesitancy among commuters to adopt this travel method,despite its numerous benefits.Here,this paper establishes a tripartite evolutionary game theory(EGT)model to verify the evolutionary stability of choosing the PUDO strategy of drivers and passengers and offering subsidies strategy of carpooling platforms in carpooling system.The model presented in this paper serves as a valuable tool for assessing the dissemination and implementation of PUDO strategy and offering subsidies strategy in carpooling applications.Subsequently,an empirical analysis is conducted to examine and compare the sensitivity of the parameters across various scenarios.The findings suggest that:firstly,providing subsidies to passengers and drivers,along with deductions for drivers through carpooling platforms,is an effective way to promote wider adoption of the PUDO strategy.Then,the decision-making process is divided into three stages:initial stage,middle stage,and mature stage.PUDO strategy progresses from initial rejection to widespread acceptance among drivers in the middle stage and,in the mature stage,both passengers and drivers tend to adopt it under carpooling platform subsidies;the factors influencing the costs of waiting and walking times,as well as the subsidies granted to passengers,are essential determinants that require careful consideration by passengers,drivers,and carpooling platforms when choosing the PUDO strategy.Our work provides valuable insight into the PUDO strategy’s applicability and the declared results provide implications for traffic managers and carpooling platforms to offer a suitable incentive.

A Stochastic Evolutionary Game Perspective on the Stability of Strategic Alliances Against External Opportunism

This paper applies stochastic evolutionary game theory to analyzing the stability of cooperation among members against external opportunism in a multi-firm alliance.The authors first review the pros and cons of pertinent traditional models,and then a stochastic game model on decisions is proposed,where a coordination parameter,a time variable,a punishment effect and bounded rationality are considered.The Gauss white noise is introduced to reflect the random disturbance in the process.Several sufficient criteria on stability are developed,which enable us to investigate"if-then"type scenarios and project the impact of different strategies.

Voter model on adaptive networks

Voter model is an important basic model in statistical physics.In recent years,it has been more and more used to describe the process of opinion formation in sociophysics.In real complex systems,the interactive network of individuals is dynamically adjusted,and the evolving network topology and individual behaviors affect each other.Therefore,we propose a linking dynamics to describe the coevolution of network topology and individual behaviors in this paper,and study the voter model on the adaptive network.We theoretically analyze the properties of the voter model,including consensus probability and time.The evolution of opinions on dynamic networks is further analyzed from the perspective of evolutionary game.Finally,a case study of real data is shown to verify the effectiveness of the theory.

Optimal production strategy for auto manufacturers with government subsidies in competitive environments

Using the Hotelling model and evolutionary game theory,this paper studies the optimal production strategy of duopoly auto manufacturers and explores the impacts of two government policies(manufacturer and consumer subsidies)on strategies related to the production of electric vehicles(EVs)or fuel vehicles(FVs).The study finds that consumers’environmental preferences have direct effects on manufacturers’market shares and profits,which in turn,affect the manufacturers’production strategy selection.Specifically,when consumer environmental preference is sufficiently high,both auto manufacturers will eventually choose to produce EVs;when it is moderate,only one with a cost advantage will choose to produce EVs.Finally,when it is low,neither auto manufacturer will produce EVs.The findings further reveal that the more significant the difference in EV production costs is,the more inclined auto manufacturers are to choose a different final stable strategy.Regardless of whether the government subsidizes manufacturers or consumers,the policy only works if subsidies reach a certain threshold.The study also identifies the conditions under which government subsidies are considered more cost-effective.

MARKETING OBJECTIVES OF RETAILERS WITH DIFFERENTIATED GOODS:AN EVOLUTIONARY PERSPECTIVE

In the real world, revenue maximization behavior may prevail in various markets. To understand this phenomenon, we develop a two-population model with two-vertically integrated channels. Every channel consists of one manufacturer and many （a sufficiently large number of） retailers that sell products in different markets by adopting pure marketing objective strategies： profit maximization and revenue maximization. We study the marketing objective behaviors in the quantity-setting duopoly and the price-setting duopoly situations respectively from an indirect evolutionary point of view. In the quantity-setting duopoly situation, we find that whether the equilibrium is an evolutionarily stable strategy depends on the type of strategic iateraction （substitutes or complements）, relative unit cost, market scale, etc. We extend it to the case with continuous preferences. We argue that revenue maximization may be an evolutionarily stable strategy and profit maximization strategy may be unstable. Under proper conditions, revenue maximization behavior can coexist with profit maximization behavior. In the price-setting duopoly situation with linear demand functions, we find that profit maximization is always an evolutionarily stable strategy and revenue maximization behavior will gradually become extinct. The extended model has a similar result but the retailers may compromise the two pure strategies.

Natural selection bet ween two games with environmentai feedback

Evolutionary game theory has extensively investigated situations in which several gamesare competing against each other at the same time,but the model only assumes sym-metric interactions in homogeneous environments.Now,the population is consideredin heterogeneous environments,individuals in the population occupy a different qualityof patches,and individual fitness depends not only on the interaction between individ-uals,but also on the quality of the environment.Here,by establishing a mathemati-cal framework,we analyze the natural selection between two strategies and two gamesin heterogeneous environments.Furthermore,we analyze the natural selection of Pris-oner's Dilemma and Hawk-Dove games theoretically to demonstrate the dynamics ofcooperators and defectors in their choice of environment and their respective games.Asexpected,the distribution of games and strategies changes with time.Based on differentinitial population compositions,we also discuss the invasion problem of games from dif-ferent perspectives.To one's surprise,we can find that good quality patches attract allindividuals;the long-term dynamics in invariant rich environments is the same as thedynamics of symmetric interactions in homogeneous environments.

Evolutionary stable strategies for business innovation and knowledge transfer

Evolutionary game theory expands into a number of areas that go beyond the biological concept of evolution to include sociology,economics,and business management.Social networks determine definite interactions between individuals in social settings.The common nature of these two broad areas of research generates interest in applying the approaches of evolutionary game theory to social network-based problems.Knowledge transfer that occurs in the process of social interaction improves a company's innovation capability.This paper attempts to explore ways in which networks relate to knowledge transfer on the basis of evolutionary game theory.We offer a simple mathematical model to examine the interaction of knowledge transfer and actor behavior in games of coordination.

Hybrid model of inter-stage spectrum trading in multistage game-theoretic framework

Dynamic spectrum access（DSA）,consisting of spectrum sharing and spectrum trading stage,becomes a promising approach to increase the efficiency of spectrum usage and system performance.In this paper,from the perspective of individual interest optimization,we focus on strategy adaptation of network users and their interaction in spectrum trading process.Considering adverse effects on decision-making accuracy and the fairness among network users via local information acquirement,a hybrid game model based on global information of relevant spectrum is proposed to formulate intelligent behaviors of both primary and secondary users.Specifically,by using the evolutionary game theory,a spectrum-selection approach for the evolution process of secondary users is designed to converge to the evolutionary equilibrium gradually.Moreover,competition among primary users is modeled as a non-cooperative game and an iterative algorithm is employed to achieve the Nash equilibrium.The simulation results show that the proposed hybrid game model investigates network dynamics under different network parameter settings.

Complex dynamics and bifurcation analysis for a Beverton-Holt population model with Allee effect

In this paper,we have derived a discrete evolutionary Beverton-Holt population model.The model is built using evolutionary game theory methodology and takes into consideration the strong Allee effect related to predation saturation.We have discussed the existence of the positive fixed point and examined its asymptotic stability.Analytically,we demonstrated that the derived model exhibits Neimark-Sacker bifurcation when the maximal predator intensity is at lower values.All chaotic behaviors are justified numerically.Finally,to avoid these chaotic features and achieve asymptotic stability,we implement two chaos control methods.

Research on System Dynamic of Buying Work Safety Services in Small and Medium-Sized Enterprises

Buying work safety services from intermediaries is a new and important approach to improve the work safety in small and medium-sized enterprises(SMEs).The existing literature addresses the significance and effectiveness of the service model but it ignores the dynamic game relationship between relevant stakeholders when SMEs choose to purchase the services under bounded rationality.Therefore,this study aims to analyse this dynamic game relationship based on evolutionary game theory.Furthermore,dynamic simulations of the evolutionary game model are applied to determine the impact of major factors for three stakeholders(SMEs,governments,and safety service agents),examine stability strategies,and identify modes of equilibrium under different subsidy strategies.The results of simulation are as follows.First,the results explain that how the major factors(service price,the quality of service,government subsidy,etc.)affect the system dynamic force of buying work safety services.Second,when the subsidy strategy is static payment,the selection of the stakeholders fluctuates and is not optimal.Third,when the subsidy strategy is a dynamic payment,the evolutionary game process converges to a stable state,which indicates that an evolutionarily stable strategy exists under the dynamic subsidy strategy.Moreover,the stable state and equilibrium values are not affected by the different initial values.The results of this study offer a certain reference for the government to guide the implementation of the purchase of work safety or other services in SMEs.