The ability to perform joint (multi-person) actions such as ensemble music performance confers numerous benefits, from generating unique aesthetic experiences to enhancing affiliation with one’s co-actors. Co-actors must be able to accurately predict when one another’s actions will occur so that they can time their own actions accordingly. One question facing the field of social neuroscience is how co-actors learn to make accurate predictions about one another’s actions. The current project, JAL, launches one of the first systematic investigations of joint action learning to address this question on the levels of both brain and behaviour. The project will implement a series of empirical studies in which partners learn novel joint turn-taking tasks while electroencephalography (EEG) is simultaneously measured from both partners: Turn-taking tasks are optimal for measuring prediction processes because partners must be able to accurately predict when one another’s turns will end so that they can seamlessly alternate actions. Learning conditions will be manipulated across studies to address three primary questions: 1) Is there an identifiable neural marker of how well partners learn to predict one another’s actions? 2) Do partners learn to generate stronger predictions about actions that serve as relevant cues for interpersonal coordination relative to actions that do not? 3) Can partners acquire the ability to predict one another's actions in a task-general manner? Outcomes from these studies will provide novel insights into how humans learn to coordinate actions with one another and will pioneer methods of simultaneously measuring behavioural and neural activity from multiple individuals during action learning. The knowledge gained from this project will be critical not only for improving methods of teaching joint action but also for developing interventions for individuals with deficits in social motor coordination.