Observational learning | EPFL Graph Search

Observational learning is learning that occurs through observing the behavior of others. It is a form of social learning which takes various forms, based on various processes. In humans, this form of learning seems to not need reinforcement to occur, but instead, requires a social model such as a parent, sibling, friend, or teacher with surroundings. Particularly in childhood, a model is someone of authority or higher status in an environment. In animals, observational learning is often based on classical conditioning, in which an instinctive behavior is elicited by observing the behavior of another (e.g. mobbing in birds), but other processes may be involved as well. Many behaviors that a learner observes, remembers, and imitates are actions that models display and display modeling, even though the model may not intentionally try to instill a particular behavior. A child may learn to swear, smack, smoke, and deem other inappropriate behavior acceptable through poor modeling. Albert Bandura claims that children continually learn desirable and undesirable behavior through observational learning. Observational learning suggests that an individual's environment, cognition, and behavior all incorporate and ultimately determine how the individual functions and models. Through observational learning, individual behaviors can spread across a culture through a process called diffusion chain. This basically occurs when an individual first learns a behavior by observing another individual and that individual serves as a model through whom other individuals learn the behavior, and so on. Culture plays a role in whether observational learning is the dominant learning style in a person or community. Some cultures expect children to actively participate in their communities and are therefore exposed to different trades and roles on a daily basis. This exposure allows children to observe and learn the different skills and practices that are valued in their communities. Albert Bandura, who is known for the classic Bobo doll experiment, identified this basic form of learning in 1961.

Non-invasive stimulation of the human striatum disrupts reinforcement learning of motor skills

Friedhelm Christoph Hummel, Takuya Morishita, Pierre Theopistos Vassiliadis, Elena Beanato, Esra Neufeld, Fabienne Windel, Maximilian Jonas Wessel, Traian Popa, Julie Duqué

Reinforcement feedback can improve motor learning, but the underlying brain mechanisms remain underexplored. In particular, the causal contribution of specific patterns of oscillatory activity within the human striatum is unknown. To address this question, ...

Nature Portfolio2024

Imitation Learning in Discounted Linear MDPs without exploration assumptions

Volkan Cevher, Efstratios Panteleimon Skoulakis, Luca Viano

We present a new algorithm for imitation learning in infinite horizon linear MDPs dubbed ILARL which greatly improves the bound on the number of trajectories that the learner needs to sample from the environment. In particular, we re- move exploration assu ...

2024