The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models. (arXiv:2204.10759v1 [cs.AI])

Models of human behavior for prediction and collaboration tend to fall into
two categories: ones that learn from large amounts of data via imitation
learning, and ones that assume human behavior to be noisily-optimal for some
reward function. The former are very useful, but only when it is possible to
gather a lot of human data in the target environment and distribution. The
advantage of the latter type, which includes Boltzmann rationality, is the
ability to make accurate predictions in …

accounting ai arxiv boltzmann distribution human policy