Predicting the behavior of interacting humans by fusing data from multiple sources
This addresses the challenge of efficiently modeling human interactions for researchers and practitioners using online platforms, though it is incremental as it adapts existing multi-fidelity approaches to a new domain.
The paper tackled the problem of poor generalization from low-fidelity online experiments to real-world human interactions by extending multi-fidelity methods to combine sparse high-fidelity data with abundant low-fidelity data, resulting in accurate models of human behavior.
Multi-fidelity methods combine inexpensive low-fidelity simulations with costly but high-fidelity simulations to produce an accurate model of a system of interest at minimal cost. They have proven useful in modeling physical systems and have been applied to engineering problems such as wing-design optimization. During human-in-the-loop experimentation, it has become increasingly common to use online platforms, like Mechanical Turk, to run low-fidelity experiments to gather human performance data in an efficient manner. One concern with these experiments is that the results obtained from the online environment generalize poorly to the actual domain of interest. To address this limitation, we extend traditional multi-fidelity approaches to allow us to combine fewer data points from high-fidelity human-in-the-loop experiments with plentiful but less accurate data from low-fidelity experiments to produce accurate models of how humans interact. We present both model-based and model-free methods, and summarize the predictive performance of each method under different conditions.