@article {4815, title = {Origin of perseveration in the trade-off between reward and complexity}, journal = {Cognition}, volume = {204}, year = {2020}, month = {11/2020}, pages = {104394}, abstract = {

When humans and other animals make repeated choices, they tend to repeat previously chosen actions independently of their reward history. This paper locates the origin of perseveration in a trade-off between two computational goals: maximizing rewards and minimizing the complexity of the action policy. We develop an information-theoretic formalization of policy complexity and show how optimizing the trade-off leads to perseveration. Analysis of two data sets reveals that people attain close to optimal trade-offs. Parameter estimation and model comparison supports the claim that perseveration quantitatively agrees with the theoretically predicted functional form (a softmax function with a frequency-dependent action bias).

}, keywords = {Decision making, Information theory, reinforcement learning}, issn = {00100277}, doi = {10.1016/j.cognition.2020.104394}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0010027720302134}, author = {Samuel J Gershman} }