Diversifying Agent's Behaviors in Interactive Decision Models
This research addresses the challenge of unknown unknowns in open AI systems, particularly for competitive or privacy-concerned agents, though it appears incremental as it builds on prior knowledge and existing techniques.
The paper tackles the problem of modeling other agents' behaviors in multi-agent decision-making under uncertainty by proposing a method to diversify the subject agent's behavioral models prior to interactions, using linear reduction and feature expansion with diversity measurements, and demonstrates performance in two problem domains.
Modelling other agents' behaviors plays an important role in decision models for interactions among multiple agents. To optimise its own decisions, a subject agent needs to model what other agents act simultaneously in an uncertain environment. However, modelling insufficiency occurs when the agents are competitive and the subject agent can not get full knowledge about other agents. Even when the agents are collaborative, they may not share their true behaviors due to their privacy concerns. In this article, we investigate into diversifying behaviors of other agents in the subject agent's decision model prior to their interactions. Starting with prior knowledge about other agents' behaviors, we use a linear reduction technique to extract representative behavioral features from the known behaviors. We subsequently generate their new behaviors by expanding the features and propose two diversity measurements to select top-K behaviors. We demonstrate the performance of the new techniques in two well-studied problem domains. This research will contribute to intelligent systems dealing with unknown unknowns in an open artificial intelligence world.