Self-Explaining Deviations for Coordination
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Supplementary Feedforward Voltage Control in a Reconfigurable Distribution Network
Network reconfiguration (NR) has attracted much attention due to its ability to convert conventional distribution networks (DNs) into self-healing grids. This paper proposes a new strategy for real-time voltage regulatio…
Coordination for Connected Automated Vehicles at Merging Roadways in Mixed Traffic Environment
In this paper, we present an optimal control framework to address motion coordination of connected automated vehicles (CAVs) in the presence of human-driven vehicles (HDVs) in merging scenarios. Our framework combines an…
Coordination of OLTC and Smart Inverters for Optimal Voltage Regulation of Unbalanced Distribution Networks
Photovoltaic (PV) smart inverters can improve the voltage profile of distribution networks. A multi-objective optimization framework for coordination of reactive power injection of smart inverters and tap operations of o…
Computational EfficiencyNonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search
Monte Carlo Tree Search (MCTS) scales poorly in cooperative multi-agent domains because expansion must consider an exponentially large set of joint actions, severely limiting exploration under realistic search budgets. W…
Towards Explainable TOPSIS: Visual Insights into the Effects of Weights and Aggregations on Rankings
Multi-Criteria Decision Analysis (MCDA) is extensively used across diverse industries to assess and rank alternatives. Among numerous MCDA methods developed to solve real-world ranking problems, TOPSIS remains one of the…