Self-Explaining Deviations for Coordination
This addresses coordination challenges in multi-agent systems, particularly for scenarios requiring theory of mind, though it appears incremental as it builds on existing concepts like SEDs.
The paper tackles the problem of enabling agents to discover self-explaining deviations (SEDs) for coordination in partially observable multi-agent settings, and introduces the IMPROVISED algorithm, which successfully produces finesse plays in Hanabi, a benchmark for human theory of mind.
Fully cooperative, partially observable multi-agent problems are ubiquitous in the real world. In this paper, we focus on a specific subclass of coordination problems in which humans are able to discover self-explaining deviations (SEDs). SEDs are actions that deviate from the common understanding of what reasonable behavior would be in normal circumstances. They are taken with the intention of causing another agent or other agents to realize, using theory of mind, that the circumstance must be abnormal. We first motivate SED with a real world example and formalize its definition. Next, we introduce a novel algorithm, improvement maximizing self-explaining deviations (IMPROVISED), to perform SEDs. Lastly, we evaluate IMPROVISED both in an illustrative toy setting and the popular benchmark setting Hanabi, where it is the first method to produce so called finesse plays, which are regarded as one of the more iconic examples of human theory of mind.