Competition and cooperation between multiple learning systems

Competition and cooperation between multiple learning systems
Competition and cooperation between multiple learning systems

Modern theories of reinforcement learning posit two systems competing for control of behavior: a "model-free" or "habitual" system that learns cached state-action values, and a "model-based" or "goal-directed" system that learns a world model which is then used to plan actions. Many behavioral and neural studies have indicated that these two systems can be dissociated, but recent data cast doubt on a strict separation of the two systems. This project explores, both theoretically and experimentally, a cooperative architecture in which the model-based system transfers knowledge to the model-free system via simulation of surrogate experience.

Associated Research Thrust(s): 

Principal Investigators: 

Postdoctoral Associates and Fellows: