Where Do Human Heuristics Come From?. Binz, M. and Endres, D.
Where Do Human Heuristics Come From? [link]Paper  abstract   bibtex   
Human decision-making deviates from the optimal solution, that maximizes cumulative rewards, in many situations. Here we approach this discrepancy from the perspective of bounded rationality and our goal is to provide a justification for such seemingly sub-optimal strategies. More specifically we investigate the hypothesis, that humans do not know optimal decision-making algorithms in advance, but instead employ a learned, resource-bounded approximation. The idea is formalized through combining a recently proposed meta-learning model based on Recurrent Neural Networks with a resource-bounded objective. The resulting approach is closely connected to variational inference and the Minimum Description Length principle. Empirical evidence is obtained from a two-armed bandit task. Here we observe patterns in our family of models that resemble differences between individual human participants.
@article{binzWhereHumanHeuristics2019,
  archivePrefix = {arXiv},
  eprinttype = {arxiv},
  eprint = {1902.07580},
  primaryClass = {cs, stat},
  title = {Where {{Do Human Heuristics Come From}}?},
  url = {http://arxiv.org/abs/1902.07580},
  abstract = {Human decision-making deviates from the optimal solution, that maximizes cumulative rewards, in many situations. Here we approach this discrepancy from the perspective of bounded rationality and our goal is to provide a justification for such seemingly sub-optimal strategies. More specifically we investigate the hypothesis, that humans do not know optimal decision-making algorithms in advance, but instead employ a learned, resource-bounded approximation. The idea is formalized through combining a recently proposed meta-learning model based on Recurrent Neural Networks with a resource-bounded objective. The resulting approach is closely connected to variational inference and the Minimum Description Length principle. Empirical evidence is obtained from a two-armed bandit task. Here we observe patterns in our family of models that resemble differences between individual human participants.},
  urldate = {2019-02-22},
  date = {2019-02-20},
  keywords = {Statistics - Machine Learning,Computer Science - Machine Learning},
  author = {Binz, Marcel and Endres, Dominik},
  file = {/home/dimitri/Nextcloud/Zotero/storage/JQPX2ZX3/Binz and Endres - 2019 - Where Do Human Heuristics Come From.pdf;/home/dimitri/Nextcloud/Zotero/storage/WFPQMPBN/1902.html}
}
Downloads: 0