Goals and habits in the brain

Abstract

An enduring and richly elaborated dichotomy in cognitive neuroscience is that of reflective versus reflexive decision making and choice. Other literatures refer to the two ends of what is likely to be a spectrum with terms such as goal-directed versus habitual, model-based versus model-free or prospective versus retrospective. One of the most rigorous traditions of experimental work in the field started with studies in rodents and graduated via human versions and enrichments of those experiments to a current state in which new paradigms are probing and challenging the very heart of the distinction. We review four generations of work in this tradition and provide pointers to the forefront of the field's fifth generation.

Figure 1

Schematic of the Tolman Detour Task Model-based and model-free decision making in a cartoon of a maze invented by Tolman and Honzik (1930). Left column: the maze has three paths (long, medium, and short), but a boulder can block just the short path (middle; after the subject has found the boulder and comes back to the start) or both short and medium (bottom). Middle column: the model-based system uses a model (thought bubble) of the maze to plan; after discovering the boulder, it knows whether the medium path is open (middle; cyan is best) or blocked (bottom; red is best). Right column: the model-free system learns path lengths based on extensive experience; if no path is blocked, this leads to the optimal choice (top; green is best); when it discovers the boulder by going along the short, green, path, it only knows that this path is blocked and thus tries the medium path (cyan) whether it is viable (middle) or not (bottom) (figure design by Alyssa Dayan).