In this paper, the authors outline a formal system for reasoning about agents＇ knowledge in knowledge games-a special type of multi-agent system. Knowledge games are card games where the agents＇ actions involve an e...In this paper, the authors outline a formal system for reasoning about agents＇ knowledge in knowledge games-a special type of multi-agent system. Knowledge games are card games where the agents＇ actions involve an exchange of information with other agents in the game. The authors＇ system is modeled using Coq-a formal proof management system. To the best of the authors＂ knowledge, there are no papers in which knowledge games are considered using a Coq proof assistant. The authors use the dynamic logic of common knowledge, where they particularly focus on the epistemic consequences of epistemic actions carried out by agents. The authors observe the changes in the system that result from such actions. Those changes that can occur in such a system that are of interest to the authors take the form of agents＇ knowledge about the state of the system, knowledge about other agents＇ knowledge, higher-order agents＇ knowledge and so on, up to common knowledge. Besides an axiomatic ofepistemic logic, the authors use a known axiomatization of card games that is extended with some new axioms that are required for the authors＇ approach. Due to a deficit in implementations grounded in theory that enable players to compute their knowledge in any state of the game, the authors show how the authors＇ approach can be used for these purposes.展开更多
This paper studies the continuous prisoner's dilemma games (CPDG) on Barabasi-Albert (BA) networks.In the model,each agent on a vertex of the networks makes an investment and interacts with all of his neighboring ...This paper studies the continuous prisoner's dilemma games (CPDG) on Barabasi-Albert (BA) networks.In the model,each agent on a vertex of the networks makes an investment and interacts with all of his neighboring agents.Making an investment is costly,but which benefits its neighboring agents,where benefit and cost depend on the level of investment made.The payoff of each agent is given by the sum of payoffs it receives in its interactions with all its neighbors.Not only payoff,individual's guilty emotion in the games has also been considered.The negative guilty emotion produced in comparing with its neighbors can reduce the utility of individuals directly.We assume that the reduction amount depends on the individual's degree and a baseline level parameter.The group's cooperative level is characterized by the average investment of the population.Each player makes his investment in the next step based on a convex combination of the investment of his best neighbors in the last step,his best history strategies in the latest steps which number is controlled by a memory length parameter,and a uniformly distributed random number.Simulation results show that this degree-dependent guilt mechanism can promote the evolution of cooperation dramatically comparing with degree-independent guilt or no guilt cases.Imitation,memory,uncertainty coefficients and network structure also play determinant roles in the cooperation level of the population.All our results may shed some new light on studying the evolution of cooperation based on network reciprocity mechanisms.展开更多
文摘In this paper, the authors outline a formal system for reasoning about agents＇ knowledge in knowledge games-a special type of multi-agent system. Knowledge games are card games where the agents＇ actions involve an exchange of information with other agents in the game. The authors＇ system is modeled using Coq-a formal proof management system. To the best of the authors＂ knowledge, there are no papers in which knowledge games are considered using a Coq proof assistant. The authors use the dynamic logic of common knowledge, where they particularly focus on the epistemic consequences of epistemic actions carried out by agents. The authors observe the changes in the system that result from such actions. Those changes that can occur in such a system that are of interest to the authors take the form of agents＇ knowledge about the state of the system, knowledge about other agents＇ knowledge, higher-order agents＇ knowledge and so on, up to common knowledge. Besides an axiomatic ofepistemic logic, the authors use a known axiomatization of card games that is extended with some new axioms that are required for the authors＇ approach. Due to a deficit in implementations grounded in theory that enable players to compute their knowledge in any state of the game, the authors show how the authors＇ approach can be used for these purposes.
基金Supported by the National Natural Science Foundation of China under Grant Nos.71071119 and 60574071supported by Hubei Province Key Laboratory of Systems Science in Metallurgical Process (Wuhan University of Science and Technology)
文摘This paper studies the continuous prisoner's dilemma games (CPDG) on Barabasi-Albert (BA) networks.In the model,each agent on a vertex of the networks makes an investment and interacts with all of his neighboring agents.Making an investment is costly,but which benefits its neighboring agents,where benefit and cost depend on the level of investment made.The payoff of each agent is given by the sum of payoffs it receives in its interactions with all its neighbors.Not only payoff,individual's guilty emotion in the games has also been considered.The negative guilty emotion produced in comparing with its neighbors can reduce the utility of individuals directly.We assume that the reduction amount depends on the individual's degree and a baseline level parameter.The group's cooperative level is characterized by the average investment of the population.Each player makes his investment in the next step based on a convex combination of the investment of his best neighbors in the last step,his best history strategies in the latest steps which number is controlled by a memory length parameter,and a uniformly distributed random number.Simulation results show that this degree-dependent guilt mechanism can promote the evolution of cooperation dramatically comparing with degree-independent guilt or no guilt cases.Imitation,memory,uncertainty coefficients and network structure also play determinant roles in the cooperation level of the population.All our results may shed some new light on studying the evolution of cooperation based on network reciprocity mechanisms.
