Comparing Human Predictions from Expert Advice to On-line Optimization Algorithms

Feng Xia, Jian-Qiao Zhu, Tom Griffiths

Abstract: Author(s): Xia, Feng; Zhu, Jianqiao; Griffiths, Tom | Abstract: On-line decision problems – in which a decision is made based on a sequence of past events without knowledge of the future – have been extensively studied in theoretical computer science. A famous example is the Prediction from Expert Advice problem, in which an agent has to make a decision informed by the predictions of a set of experts. An optimal solution to this problem is the Multiplicative Weights Update Method (MWUM). In this paper, we investigate how humans behave in a Prediction from Expert Advice task. We compare MWUM and several other algorithms proposed in the computer science literature against human behavior. We find that MWUM provides the best fit to people’s choices.