Various approaches used in Agent-based Computational Economics (ACE) to model endogenously determined interactions between agents are discussed. This concerns models in which agents not only (learn how to) play some (market or other) game, but also (learn to) decide with whom to do that (or not).

We provide a model of dynamic duopoly in which firms face financial constraints and disappear when they are unable to fulfill them. We show that, in some cases, Cournot outputs are no longer supported in equilibrium, because if these outputs were set, a firm may have incentives to ruin the...

Endogenous timing can help to derive the time structure of decision making instead of assuming it as exogenously given. In our study we consider a homogeneous market where, like in the model of Kreps and Scheinkman (1983), sellers determine sales capacities before prices. Sellers must serve...

We develop a method to estimate a game’s primitives in complex dynamic environments. Because of the environment’s complexity, agents may not know or understand some key features of their interaction. Instead of equilibrium assumptions, we impose an asymptotic ε-regret (ε-AR) condition on...

We develop a nonparametric and ordinal approach for testing pure strategy Nash equilibrium play in games with monotone best responses, such as those with strategic complements/substitutes. The approach makes minimal assumptions on unobserved heterogeneity, requires no parametric assumptions on...