In this paper we address the cooperation problem in structured populations by considering the prisoner's dilemma game as metaphor of the social interactions between individuals with imitation capacity. We present a new strategy update rule called democratic weighted update where the individuals behavior is socially influenced by each one of their neighbors. In particular, the capacity of an individual to socially influence other ones is proportional to its wisdom which is defined by its successful in the game. When in a neighborhood there are cooperators and defectors, the focal player is contradictorily influenced by them and, therefore, the effective social influence is given by the difference of the total wisdom of each strategy in its neighborhood. First, by considering the growing process of the network and neglecting mutations we show the evolution of highly cooperative systems. Then, we broadly shown that the social influence allows to overcome the emergence of mutants into highly cooperative systems. In this way, we are able to conclude that considering the growing process of the system, individuals with imitation capacity and the social influence the cooperation evolves. Therefore, here we present a theoretical solution of the cooperation problem among unrelated individuals with imitiation capacity.
In the future, artificial learning agents are likely to become increasingly widespread in our society. They will interact with both other learning agents and humans in a variety of complex settings including social dilemmas. We consider the problem of how an external agent can promote cooperation between artificial learners by distributing additional rewards and punishments based on observing the learners' actions. We propose a rule for automatically learning how to create right incentives by considering the players' anticipated parameter updates. Using this learning rule leads to cooperation …
Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmas
Northwestern Polytechnical University（西北工业大学）；Tsinghua University（清华大学）；University of Auckland（奥克兰大学）；Kyushu University（九州大学）；The Hong Kong Polytechnic University（香港理工大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Bounded Normative Equivalence in Human-AI Cooperation: Group Behaviour, Not Partner Labels, Predicts Cooperation under Anonymous Aggregate Feedback
Department of Sociology, University of Zurich（苏黎世大学社会学系）；Centre for Sociology of Humans and Machines (SOHAM), Trinity College Dublin & Technological University Dublin（人类与机器社会学中心（SOHAM））
Trinity College Dublin（都柏林圣三一学院）；Ludwig Maximilian University of Munich（慕尼黑大学）；Technological University Dublin（都柏林理工大学）；University College Dublin（都柏林大学学院）
Using simulations between pairs of $ε$-greedy q-learners with one-period memory, this article demonstrates that the potential function of the stochastic replicator dynamics (Foster and Young, 1990) allows it to predict the emergence of error-proof cooperative strategies from the underlying parameters of the repeated prisoner's dilemma. The observed cooperation rates between q-learners are related to the ratio between the kinetic energy exerted by the polar attractors of the replicator dynamics under the grim trigger strategy. The frontier separating the parameter space conducive to cooperation…
Collective action demands that individuals efficiently coordinate how much, where, and when to cooperate. Laboratory experiments have extensively explored the first part of this process, demonstrating that a variety of social-cognitive mechanisms influence how much individuals choose to invest in group efforts. However, experimental research has been unable to shed light on how social cognitive mechanisms contribute to the where and when of collective action. We build and test a computational model of human behavior in Clean Up, a social dilemma task popular in multi-agent reinforcement learni…
Predicting how cooperative behavior arises in the thermodynamic limit is one of the outstanding problems in evolutionary game theory. For two player games, cooperation is seldom the Nash equilibrium. However, in the thermodynamic limit cooperation is the natural recourse regardless of whether we are dealing with humans or animals. In this work, we use the analogy with the Ising model to predict how cooperation arises in the thermodynamic limit.
Groups of humans are often able to find ways to cooperate with one another in complex, temporally extended social dilemmas. Models based on behavioral economics are only able to explain this phenomenon for unrealistic stateless matrix games. Recently, multi-agent reinforcement learning has been applied to generalize social dilemma problems to temporally and spatially extended Markov games. However, this has not yet generated an agent that learns to cooperate in social dilemmas as humans do. A key insight is that many, but not all, human individuals have inequity averse social preferences. This…
