Imitation | EPFL Graph Search

Imitation (from Latin imitatio, "a copying, imitation") is a behavior whereby an individual observes and replicates another's behavior. Imitation is also a form of that leads to the "development of traditions, and ultimately our culture. It allows for the transfer of information (behaviors, customs, etc.) between individuals and down generations without the need for genetic inheritance." The word imitation can be applied in many contexts, ranging from animal training to politics. The term generally refers to conscious behavior; subconscious imitation is termed mirroring. In anthropology, some theories hold that all cultures imitate ideas from one of a few original cultures or several cultures whose influence overlaps geographically. Evolutionary diffusion theory holds that cultures influence one another, but that similar ideas can be developed in isolation. Scholars as well as popular authors have argued that the role of imitation in humans is unique among animals. However, this claim has been recently challenged by scientific research which observed social learning and imitative abilities in animals. Psychologist Kenneth Kaye showed that the ability of infants to match the sounds or gestures of an adult depends on an interactive process of turn-taking over many successive trials, in which adults' instinctive behavior plays as great a role as that of the infant. These writers assume that evolution would have selected imitative abilities as fit because those who were good at it had a wider arsenal of learned behavior at their disposal, including tool-making and language. However, research also suggests that imitative behaviors and other social learning processes are only selected for when outnumbered or accompanied by asocial learning processes: an over-saturation of imitation and imitating individuals leads humans to collectively copy inefficient strategies and evolutionarily maladaptive behaviors, thereby reducing flexibility to new environmental contexts that require adaptation.

Follow the Clairvoyant: an Imitation Learning Approach to Optimal Control

Giancarlo Ferrari Trecate, John Lygeros, Luca Furieri, Florian Dörfler, Andrea Martin

We consider control of dynamical systems through the lens of competitive analysis. Most prior work in this area focuses on minimizing regret, that is, the loss relative to an ideal clairvoyant policy that has noncausal access to past, present, and future d ...

Elsevier2023

Many Are The Ways to Learn: Identifying multi-modal behavioral profiles of collaborative learning in constructivist activities

Pierre Dillenbourg, Barbara Bruno, Jauwairia Nasir, Aditi Kothiyal

Understanding how learners engage with learning technologies, and its relation with their learning, is crucial to the design of effective learning interventions. Assessing the learners’ state however, is non-trivial. Research suggests that performance is n ...

2021