The evolution of forecasting for decision making in dynamic environments
Global change is reshaping ecosystems and societies. Strategic choices that were best yesterday may be sub-optimal tomorrow; and environmental conditions that were once taken for granted may soon cease to exist. In this setting, how people choose behavioral strategies has important consequences for environmental dynamics. Economic and evolutionary theories make similar predictions for strategic behavior in a static environment, even though one approach assumes perfect rationality and the other assumes no cognition whatsoever; but predictions differ in a dynamic environment. Here we explore a middle ground between economic rationality and evolutionary myopia. Starting from a population of myopic agents, we study the emergence of a new type that forms environmental forecasts when making strategic decisions. We show that forecasting types can have an advantage in changing environments, even when the act of forecasting is costly. Forecasting types can invade but not overtake the population, producing a stable coexistence with myopic types. Moreover, forecasters provide a public good by reducing the amplitude of environmental oscillations and increasing mean payoff to forecasting and myopic types alike. We interpret our results for understanding the evolution of different modes of decision-making. And we discuss implications for the management of environmental systems of great societal importance.
Code (1)
Tasks
Decision MakingManagementSimilar Papers 제목 키워드 기반
Computational evolution of decision-making strategies
Most research on adaptive decision-making takes a strategy-first approach, proposing a method of solving a problem and then examining whether it can be implemented in the brain and in what environments it succeeds. We pr…
Decision MakingQuantum-Evolutionary Neural Networks for Multi-Agent Federated Learning
As artificial intelligence continues to drive innovation in complex, decentralized environments, the need for scalable, adaptive, and privacy-preserving decision-making systems has become critical. This paper introduces …
Decision MakingEvolutionary AlgorithmsFederated LearningPrivacy PreservingAdaptive Decision-Objective Loss for Forecast-then-Optimize in Power Systems
Forecast-then-optimize is a widely-used framework for decision-making problems in power systems. Traditionally, statistical losses have been employed to train forecasting models, but recent research demonstrated that imp…
Decision MakingQxEAI: Quantum-like evolutionary algorithm for automated probabilistic forecasting
Forecasting, to estimate future events, is crucial for business and decision-making. This paper proposes QxEAI, a methodology that produces a probabilistic forecast that utilizes a quantum-like evolutionary algorithm bas…
Decision MakingTime SeriesLeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling
Time series forecasting serves as an essential tool for many real-world applications, supporting tasks such as resource optimization and decision-making. Despite significant architectural advancements, most modern models…
Time Series Forecasting