Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration
This work addresses the challenge of collecting vast human data for realistic models in human-AI collaboration, offering a data-efficient solution that is incremental but impactful for improving collaborative AI systems.
The paper tackles the problem of data-efficient human behavior modeling for AI collaboration by proposing an optimal behavior prior, which significantly improves data efficiency and enables generalization to new environments, leading to better human-AI collaboration performance compared to models using only real human data.
AI agents designed to collaborate with people benefit from models that enable them to anticipate human behavior. However, realistic models tend to require vast amounts of human data, which is often hard to collect. A good prior or initialization could make for more data-efficient training, but what makes for a good prior on human behavior? Our work leverages a very simple assumption: people generally act closer to optimal than to random chance. We show that using optimal behavior as a prior for human models makes these models vastly more data-efficient and able to generalize to new environments. Our intuition is that such a prior enables the training to focus one's precious real-world data on capturing the subtle nuances of human suboptimality, instead of on the basics of how to do the task in the first place. We also show that using these improved human models often leads to better human-AI collaboration performance compared to using models based on real human data alone.