Sequential Cooperative Bayesian Inference
This work provides foundational insights for improving cooperation in human-human and human-machine interactions, though it appears incremental as it builds on existing models of cooperation.
The paper tackled the problem of establishing theoretical foundations for cooperative inference among Bayesian agents using sequential data, and demonstrated that cooperation is not only possible but also theoretically well-founded in general, with results on consistency, convergence rates, and stability.
Cooperation is often implicitly assumed when learning from other agents. Cooperation implies that the agent selecting the data, and the agent learning from the data, have the same goal, that the learner infer the intended hypothesis. Recent models in human and machine learning have demonstrated the possibility of cooperation. We seek foundational theoretical results for cooperative inference by Bayesian agents through sequential data. We develop novel approaches analyzing consistency, rate of convergence and stability of Sequential Cooperative Bayesian Inference (SCBI). Our analysis of the effectiveness, sample efficiency and robustness show that cooperation is not only possible in specific instances but theoretically well-founded in general. We discuss implications for human-human and human-machine cooperation.