A comparison of stable and fluctuating resources with respect to evolutionary adaptation and life-history traits using individual-based modeling and machine learning

Synergistic Integration Between Machine Learning and Agent-Based Modeling: A Multidisciplinary Review

Agent-based modeling (ABM) involves developing models in which agents make adaptive decisions in a changing environment. Machine-learning (ML) based inference models can improve sequential decision-making by learning agents' behavioral patterns. With the aid of ML, this emerging area can extend traditional agent-based schemes that hardcode agents' behavioral rules into an adaptive model. Even though there are plenty of studies that apply ML in ABMs, the generalized applicable scenarios, frameworks, and procedures for implementations are not well addressed. In this article, we provide a comprehensive review of applying ML in ABM based on four major scenarios, i.e., microagent-level situational awareness learning, microagent-level behavior intervention, macro-ABM-level emulator, and sequential decision-making. For these four scenarios, the related algorithms, frameworks, procedures of implementations, and multidisciplinary applications are thoroughly investigated. We also discuss how ML can improve prediction in ABMs by trading off the variance and bias and how ML can improve the sequential decision-making of microagent and macrolevel policymakers via a mechanism of reinforced behavioral intervention. At the end of this article, future perspectives of applying ML in ABMs are discussed with respect to data acquisition and quality issues, the possible solution of solving the convergence problem of reinforcement learning, interpretable ML applications, and bounded rationality of ABM.

Prey life-history influences the evolution of egg mass and indirectly reproductive investment in a group of free-living insect predators

The balance between risk and benefit of exploiting resources drives life-history evolution in organisms. Predators are naturally recognized as major drivers of the life-history evolution of their prey. Although prey may also influence the life-history evolution of their predators in the context of an evolutionary arms race, there is far more evidence of the role of predators than of prey.The goal of this study was to investigate the role of prey in life-history evolution of predators using ladybird beetle predators of aphids and coccids. These particular ladybirds and their prey were chosen because literature shows that the pace of life of aphids is faster than that of coccids and this difference is reflected in the life histories of the ladybirds that specialize on feeding on aphids or coccids.Thirty-four species of ladybird predators of aphids and eight of coccids belonging to five different tribes were collected and reared in the laboratory. The females were weighed as well as their eggs, and their reproductive investment estimated as the number of ovarioles. Phylogenetic relatedness was controlled for in the statistical analyses.Controlling for female mass revealed that ladybird predators of aphids lay bigger eggs than ladybird predators of coccids. This difference is not influenced by phylogenetic relatedness but only by the type of prey eaten. We suggest that ladybird predators of coccids lay smaller eggs because neonate larvae do not have to search, catch, and subdue prey. Both types of ladybirds have a similar reproductive investment relative to their body mass when phylogeny is controlled for.Recognizing the influence of prey on the life-history evolution of predators is important for understanding food web dynamics. From an applied perspective, this fine evolutionary tuning of prey-predator relationships should be used to guide and increase the efficiency of biological control programs.