Despite substantial progress in applying neural networks (NN) to multi-agent reinforcement learning (MARL) areas, they still largely suffer from a lack of transparency and interoperability. However, its implicit cooperative mechanism is not yet fully understood due to black-box networks. In this work, we study an interpretable value decomposition framework via concept bottleneck models, which promote trustworthiness by conditioning credit assignment on an intermediate level of human-like cooperation concepts. To address this problem, we propose a novel value-based method, named Concepts learning for Multi-agent Q-learning (CMQ), that goes beyond the current performance-vs-interpretability trade-off by learning interpretable cooperation concepts. CMQ represents each cooperation concept as a supervised vector, as opposed to existing models where the information flowing through their end-to-end mechanism is concept-agnostic. Intuitively, using individual action value conditioning on global state embeddings to represent each concept allows for extra cooperation representation capacity. Empirical evaluations on the StarCraft II micromanagement challenge and level-based foraging (LBF) show that CMQ achieves superior performance compared with the state-of-the-art counterparts. The results also demonstrate that CMQ provides more cooperation concept representation capturing meaningful cooperation modes, and supports test-time concept interventions for detecting potential biases of cooperation mode and identifying spurious artifacts that impact cooperation.
Cooperation has long been a fundamental topic in both human society and AI systems. However, recent studies indicate that the collapse of cooperation may emerge in multi-agent systems (MASs) driven by large language models (LLMs). To address this challenge, we explore reputation systems as a remedy. We propose RepuNet, a dynamic, dual-level reputation framework that models both agent-level reputation dynamics and system-level network evolution. Specifically, driven by direct interactions and indirect gossip, agents form reputations for both themselves and their peers, and decide whether to connect or disconnect other agents for future interactions. Through three distinct scenarios, we show that RepuNet effectively avoids cooperation collapse, promoting and sustaining cooperation in LLM-based MASs. Moreover, we find that reputation systems can give rise to rich emergent behaviors in LLM-based MASs, such as the formation of cooperative clusters, the social isolation of exploitative agents, and the preference for sharing positive gossip rather than negative ones. The GitHub repository for our project can be accessed via the following link: https://github.com/RGB-0000FF/RepuNet.
Inspired by the principle of self-regulating cooperation in collective institutions, we propose the Group Relative Policy Optimization with Global Cooperation Constraint (GRPO-GCC) framework. This work is the first to introduce GRPO into spatial public goods games, establishing a new deep reinforcement learning baseline for structured populations. GRPO-GCC integrates group relative policy optimization with a global cooperation constraint that strengthens incentives at intermediate cooperation levels while weakening them at extremes. This mechanism aligns local decision making with sustainable collective outcomes and prevents collapse into either universal defection or unconditional cooperation. The framework advances beyond existing approaches by combining group-normalized advantage estimation, a reference-anchored KL penalty, and a global incentive term that dynamically adjusts cooperative payoffs. As a result, it achieves accelerated cooperation onset, stabilized policy adaptation, and long-term sustainability. GRPO-GCC demonstrates how a simple yet global signal can reshape incentives toward resilient cooperation, and provides a new paradigm for multi-agent reinforcement learning in socio-technical systems.
Ignacio Castellanos Anaya, David A. Echeverry Botero
This article analyzes social capital in Colombia and how to create it in distrustful societies using game theory. Networking generation and trustful environments are intimately related to development, lowering transactional costs and helping societies to create better interchange processes under regulated institutions. However, there are societies, such as the Colombian one, where building trust is difficult due to the country’s history, conflict, and dubious contract bargains. In Colombia and some Latin American countries, most negotiations rely on the assumption that the counterparty wants a tremendous advantage or has an obscure desire when doing business. Still, it is possible to generate confidence through non-cooperative games, in which prior cooperation or trust between market players is unnecessary. The proposed model in this article shows how two agents who do not cooperate and do not have confidence in a competitive environment get higher earnings in the medium and long term in private contractual relationships if they consider their goodwill as a critical variable in their profits calculation and choose the agreement performance strategy.
Law in general. Comparative and uniform law. Jurisprudence, Political science (General)
Parental involvement of super-diverse families in the educational process is an integral part of the integration of emergent bilingual students, which, however, entails obstacles to its implementation in Greek schools and worldwide. Τhe present study investigates, through a qualitative case study, the perceptions of eight primary school teachers who had worked in zones of educational priority (ZEPs) in Greek public education, which are also called reception classes, towards the involvement of immigrant and refugee parents in the educational process as well as the barriers that influence it. The methodological tool of semi-structured interviews was used, while the sample was selected with both the convenience and snowball sampling techniques. Some important results reveal the usefulness of parental involvement for all involved persons in the school–family partnership as well as the multiple obstacles to its implementation. The main difficulties encountered by the participants were the parents’ lack of competence in Greek or in an intermediate language as well as their unfamiliarity with a culturally different education system. In response to this reality, the establishment of translation services at school with language and cultural interpreters that could bridge theses distances while recognizing families’ differences as an asset rather as an obstacle emerges as a necessity.
Cooperation plays a crucial role in both nature and human society, and the conundrum of cooperation attracts the attention from interdisciplinary research. In this study, we investigated the evolution of cooperation in optional prisoner's dilemma games by introducing simple bots. We focused on one-shot and anonymous games, where the bots could be programmed to always cooperate, always defect, never participate, or choose each action with equal probability. Our results show that cooperative bots facilitate the emergence of cooperation among ordinary players in both well-mixed populations and a regular lattice under weak imitation scenarios. Introducing loner bots has no impact on the emergence of cooperation in well-mixed populations, but it facilitates the dominance of cooperation in regular lattices under strong imitation scenarios. However, too many loner bots on a regular lattice inhibit the spread of cooperation and can eventually result in a breakdown of cooperation. Our findings emphasize the significance of bot design in promoting cooperation and offer useful insights for encouraging cooperation in real-world scenarios.
Abstract Why do many societies moralize apparently harmless pleasures, such as lust, gluttony, alcohol, drugs, and even music and dance? Why do they erect temperance, asceticism, sobriety, modesty, and piety as cardinal moral virtues? According to existing theories, this puritanical morality cannot be reduced to concerns for harm and fairness: It must emerge from cognitive systems that did not evolve for cooperation (e.g., disgust-based “purity” concerns). Here, we argue that, despite appearances, puritanical morality is no exception to the cooperative function of moral cognition. It emerges in response to a key feature of cooperation, namely that cooperation is (ultimately) a long-term strategy, requiring (proximately) the self-control of appetites for immediate gratification. Puritanical moralizations condemn behaviors which, although inherently harmless, are perceived as indirectly facilitating uncooperative behaviors, by impairing the self-control required to refrain from cheating. Drinking, drugs, immodest clothing, and unruly music and dance are condemned as stimulating short-term impulses, thus facilitating uncooperative behaviors (e.g., violence, adultery, free-riding). Overindulgence in harmless bodily pleasures (e.g., masturbation, gluttony) is perceived as making people slave to their urges, thus altering abilities to resist future antisocial temptations. Daily self-discipline, ascetic temperance, and pious ritual observance are perceived as cultivating the self-control required to honor prosocial obligations. We review psychological, historical, and ethnographic evidence supporting this account. We use this theory to explain the fall of puritanism in western, educated, industrialized, rich, and democratic (WEIRD) societies, and discuss the cultural evolution of puritanical norms. Explaining puritanical norms does not require adding mechanisms unrelated to cooperation in our models of the moral mind.
Caspar Oesterheld, Johannes Treutlein, Roger Grosse
et al.
As machine learning agents act more autonomously in the world, they will increasingly interact with each other. Unfortunately, in many social dilemmas like the one-shot Prisoner's Dilemma, standard game theory predicts that ML agents will fail to cooperate with each other. Prior work has shown that one way to enable cooperative outcomes in the one-shot Prisoner's Dilemma is to make the agents mutually transparent to each other, i.e., to allow them to access one another's source code (Rubinstein 1998, Tennenholtz 2004) -- or weights in the case of ML agents. However, full transparency is often unrealistic, whereas partial transparency is commonplace. Moreover, it is challenging for agents to learn their way to cooperation in the full transparency setting. In this paper, we introduce a more realistic setting in which agents only observe a single number indicating how similar they are to each other. We prove that this allows for the same set of cooperative outcomes as the full transparency setting. We also demonstrate experimentally that cooperation can be learned using simple ML methods.
Hugo Perez-Martinez, Carlos Gracia-Lazaro, Fabio Dercole
et al.
Understanding cooperative behavior in biological and social systems constitutes a scientific challenge, being the object of intense research over the past decades. Many mechanisms have been proposed to explain the presence and persistence of cooperation in those systems, showing that there is no unique explanation, as different scenarios have different possible driving forces. In this paper, we propose a model to study situations in which voluntary participation involves an access cost to the cooperative interaction, besides the cost associated with cooperation. The proposed Costly-Access Prisoner's Dilemma, a symmetric donation game with voluntary and costly participation, breaks the symmetry between abstainers and participants of the Voluntary Prisoner's Dilemma. A mean-field approach shows that, in well-mixed populations, the dynamic always leads the system to abstention. However, depending on the return parameter, numerical simulations in structured populations display an alternating behavior between mono-strategic, multi-stable, and coexistence phases. This behavior is fully explained through a theoretical analysis of the strategic motifs, the transitions being determined by the change in stability of those motifs.
Erika Chiba, Diane Carmeliza N. Cuaresma, Jomar F. Rabajante
et al.
The development of cooperation in human societies is a major unsolved problem in biological and social sciences. Extensive studies in game theory have shown that cooperative behaviour can evolve only under very limited conditions or with additional complexities, such as spatial structure. Non-trivial two-person games are categorized into three types of games, namely, the prisoner's dilemma game, the chicken game and the stag hunt game. Recently, the weight-lifting game has been shown to cover all five games depending on the success probability of weight lifting, which include the above three games and two trivial cases (all cooperation and all defection; conventionally not distinguished as separate classes). Here, we introduce the concept of the environmental value of a society. Cultural development and deterioration are represented by changes in this probability. We discuss cultural evolution in human societies and the biological communities of living systems.
Henry Schulten, Gregor Dumphart, Antonios Koskinas
et al.
Wireless localization is a key requirement for many applications. It concerns position estimation of mobile nodes (agents) relative to fixed nodes (anchors) from wireless channel measurements. Cooperative localization is an advanced concept that considers the joint estimation of multiple agent positions based on channel measurements of all agent-anchor links together with all agent-agent links. In this paper we present the first study of cooperative localization for magneto-inductive wireless sensor networks, which are of technological interest due to good material penetration and channel predictability. We demonstrate significant accuracy improvements (a factor of 3 for 10 cooperating agents) over the non-cooperative scheme. The evaluation uses the Cramér-Rao lower bound on the cooperative position estimation error, which is derived herein. To realize this accuracy, the maximum-likelihood estimate (MLE) must be computed by solving a high-dimensional least-squares problem, whereby convergence to local minima proves to be problematic. A proposed cooperative localization algorithm addresses this issue: first, preliminary estimates of the agent positions and orientations are computed, which then serve as initial values for a gradient search. In all our test cases, this method yields the MLE and the associated high accuracy (comprising the cooperation gain) from a single solver run. The preliminary estimates use novel closed-form MLE formulas of the distance, direction and orientation for single links between three-axis coils, which are given in detail.
Revision game is a very new model formulating the real-time situation where players dynamically prepare and revise their actions in advance before a deadline when payoffs are realized. It is at the cutting edge of dynamic game theory and can be applied in many real-world scenarios, such as eBay auction, stock market, election, online games, crowdsourcing, etc. In this work, we novelly identify a class of strategies for revision games which are called Limited Retaliation strategies. An limited retaliation strategy stipulates that, (1) players first follow a recommended cooperative plan; (2) if anyone deviates from the plan, the limited retaliation player retaliates by using the defection action for a limited duration; (3) after the retaliation, the limited retaliation player returns to the cooperative plan. A limited retaliation strategy has three key features. It is cooperative, sustaining a high level of social welfare. It is vengeful, deterring the opponent from betrayal by threatening with a future retaliation. It is yet forgiving, since it resumes cooperation after a proper retaliation. The cooperativeness and vengefulness make it constitute cooperative subgame perfect equilibrium, while the forgiveness makes it tolerate occasional mistakes. limited retaliation strategies show significant advantages over Grim Trigger, which is currently the only known strategy for revision games. Besides its contribution as a new robust and welfare-optimizing equilibrium strategy, our results about limited retaliation strategy can also be used to explain how easy cooperation can happen, and why forgiveness emerges in real-world multi-agent interactions. In addition, limited retaliation strategies are simple to derive and computationally efficient, making it easy for algorithm design and implementation in many multi-agent systems.
Cooperation declines in repeated public good games because individuals behave as conditional cooperators. This is because individuals imitate the social behaviour of successful individuals when their payoff information is available. However, in human societies, individuals cooperate in many situations involving social dilemmas. We hypothesize that humans are sensitive to both success (payoffs) and how that success was obtained, by cheating (not socially sanctioned) or good behaviour (socially sanctioned and adds to prestige or reputation), when information is available about payoffs and prestige. We propose and model a repeated public good game with heterogeneous conditional cooperators where an agent's donation in a public goods game depends on comparing the number of donations in the population in the previous round and with the agent's arbitrary chosen conditional cooperative criterion. Such individuals imitate the social behaviour of role models based on their payoffs and prestige. The dependence is modelled by two population-level parameters: affinity towards payoff and affinity towards prestige. These affinities influence the degree to which agents value the payoff and prestige of role models. Agents update their conditional strategies by considering both parameters. The simulations in this study show that high levels of cooperation are established in a population consisting of heterogeneous conditional cooperators for a certain range of affinity parameters in repeated public good games. The results show that social value (prestige) is important in establishing cooperation.
We study environments in which agents are randomly matched to play a Prisoner's Dilemma, and each player observes a few of the partner's past actions against previous opponents. We depart from the existing related literature by allowing a small fraction of the population to be commitment types. The presence of committed agents destabilizes previously proposed mechanisms for sustaining cooperation. We present a novel intuitive combination of strategies that sustains cooperation in various environments. Moreover, we show that under an additional assumption of stationarity, this combination of strategies is essentially the unique mechanism to support full cooperation, and it is robust to various perturbations. Finally, we extend the results to a setup in which agents also observe actions played by past opponents against the current partner, and we characterize which observation structure is optimal for sustaining cooperation.
The purpose of this study was affecting factors on student’s membership of Agricultural Faculty Razi University in Student’s Cooperative of way comparison of persons property of membership and non-membership. This quantity study wasdone by survey method and by use of questionnaire tool by Cronbach's alpha coefficient 0.74.The statistical population of this study are included students of Agricultural Faculty Razi University on total of degrees. Totally 108 persons are chosen as sample with use of Cochran formula to way sampling random. Finds of Logistic Regression are shown that variables of entered in four steps of model includingfield of study,agricultural experience, age and self-efficacy are determined between 55.4 to 74.2 percent of variance of membership in student’s cooperative. In this wayjust two variables of),agricultural experience and age are predicted membership in student’s cooperative significantly. Is that by increase of student’s agricultural experience, their membership in cooperative are less and younger students less membership has in student’s production cooperative. In this model, agricultural experience andstudent’s age have predicted totally 90.1 percent of students’ membership and non-membership properly. Accordingly,is recommended given existing opportunities like (professors presenting as management and advice team, existing farm and new watering systems) in agricultural faculty, politicians and relevant authorities take action to student’s activity in format of student’s cooperative.
neda tahmasbi roshan, Ali Morovati Sharif Abadi, Seyed Habibollah mirghafoori
et al.
Agricultural cooperatives need to consider sustainability factors in their supply chain operations to achieve sustainable performance in order to achieve long-term viability. Accordingly, the purpose of this study was to investigate the effect of Ssustainable Supply Chain Management Dimensions including sustainable procurement, sustainable design, sustainable distribution and investment improvement on sustainability performance of cooperative agricultural companies. The statistical population of the research were agricultural cooperatives in the cities of Mazandaran province, whose information was most actively registered and active in the site. The number of these cooperatives is 132 cooperatives and the sample was selected by stratified random sampling and based on the Morgan Table, there were 100 cooperatives. A questionnaire was distributed among the heads of these cooperatives to collect the data. In order to analyze the data, Structural Equation Model and SMART- PLS software were used. Results showed that the confirmation of the impact of sustainable design, stable distribution and improve investment on economic performance, social performance and environmental performance as well as results of tests on Sustainable Procurement indicated the relationship between the Sustainable Procurement and social performance and environmental, but Its relationship with economic performance has not been verified.
Bahman KHosravipour, Abbas Abdeshahi, Maryam Barzegar
et al.
The purpose of this study, descriptive-correlation study, the factors affecting the participation of farmers in the rural outskirts of the eastern Ramhormoz township in irrigation projects. The data collection instrument was a questionnaire survey of a panel of experts including Astatyd validity of agricultural extension and education, studied and accordingly was approved. It also uses SPSS software reliability and reliability with Cronbach Alpha (0.83) was approved. The population of rural farmers study the outskirts of the eastern city Ramhrmztshkyl (N = 300) that of these, 170 sample using stratified random sampling method were selected as samples and finally 170 Completed questionnaires were received and analyzed. Pearson correlation test results show that trust between the social and the social status varies with the participation of farmers in irrigation projects and there is a significant positive relationship. In multiple linear regression with the variables of social trust and the ability to explain people's willingness to do community work 0.31 percent of variations in farmers' participation in irrigation projects have.
The purpose of this study was comparison power of theories of planned behaviorand norm-activation modelin predicting palm owners’ behavior in Dashtestan Township and determination of factors affecting on water conservation. In this research, data have been collected with questionnaire and through survey research. Validity was gained by a panel of expert approved and its reliability was confirmed through coefficient (Cronbach’s) alpha (0.70-0.86). Population consisted of palm owners’ who were Dashtestan Township by using multistage random sampling technique, 300 individuals palm owners’ were selected Dashtestan Township. The findings showed that the variables norm-activation theory with predicting 24 percent of palm owners’ behavior in relation to water conservation than the variables planned behavior theory with predicting 45 percent of palm owners’ behavior in relation to water conservation was less powerful.