In this work, we ask for and answer what makes classical temporal-difference reinforcement
learning with ϵ-greedy strategies cooperative. Cooperating in social dilemma situations is …

Many recent studies have used reinforcement learning methods to investigate the behavior
of agents in evolutionary games. Q-learning, in particular, has become a mainstream …

Dynamical interaction represents a fundamental coevolutionary rule that addresses the
intricacies of cooperation in social dilemmas. It provides a normative account for the …

Traffic congestion is a major source of discomfort and economic losses in urban
environments. Recently, the proliferation of traffic detectors and the advances in algorithms …

Interaction is an important step in cooperation evolution, and non-deterministic interactions
are common in complex and changeable environments. Therefore, the number of interactive …

Imitation and replication have emerged as a paradigm in numerous studies that explore the
evolution of cooperative behavior. Since they embrace the essence of natural selection, it is …

In evolutionary game theory, the emergence and maintenance of group cooperative
behavior is usually challenged by the lure of high-payoff defection behavior. Recently …

In the public goods game on the network, individuals might believe that their neighbors'
neighbors have more similar situations to their own than their direct neighbors since they …

The emergence of cooperation between competing agents has been commonly studied
through evolutionary games, but such cooperation often requires a mechanism or a third …

In the framework of the coevolution dynamics of the weak prisoner's dilemma, inspired by
prior empirical research, we present a coevolutionary model with local network dynamics in …