@article {3442, title = {Cost-Benefit Arbitration Between Multiple Reinforcement-Learning Systems.}, journal = {Psychol Sci}, volume = {28}, year = {2017}, month = {2017 Sep}, pages = {1321-1333}, abstract = {

Human behavior is sometimes determined by habit and other times by goal-directed planning. Modern reinforcement-learning theories formalize this distinction as a competition between a computationally cheap but inaccurate model-free system that gives rise to habits and a computationally expensive but accurate model-based system that implements planning. It is unclear, however, how people choose to allocate control between these systems. Here, we propose that arbitration occurs by comparing each system{\textquoteright}s task-specific costs and benefits. To investigate this proposal, we conducted two experiments showing that people increase model-based control when it achieves greater accuracy than model-free control, and especially when the rewards of accurate performance are amplified. In contrast, they are insensitive to reward amplification when model-based and model-free control yield equivalent accuracy. This suggests that humans adaptively balance habitual and planned action through on-line cost-benefit analysis.

}, issn = {1467-9280}, doi = {10.1177/0956797617708288}, author = {Kool, Wouter and Samuel J Gershman and Fiery A Cushman} }