AIOct 31, 2024

Responsibility-aware Strategic Reasoning in Probabilistic Multi-Agent Systems

arXiv:2411.00146v22 citationsh-index: 11AAAI
Originality Incremental advance
AI Analysis

This work addresses the need for responsibility-aware reasoning in autonomous systems, offering a framework for balanced decision-making among agents, though it is incremental as it builds on existing logics and solution concepts.

The paper tackles the problem of strategic reasoning in probabilistic multi-agent systems by introducing PATL+R, a logic that incorporates causal responsibility modalities, and presents an approach to synthesize joint strategies that optimize responsibility and reward distribution, using Nash equilibrium and parametric model checking.

Responsibility plays a key role in the development and deployment of trustworthy autonomous systems. In this paper, we focus on the problem of strategic reasoning in probabilistic multi-agent systems with responsibility-aware agents. We introduce the logic PATL+R, a variant of Probabilistic Alternating-time Temporal Logic. The novelty of PATL+R lies in its incorporation of modalities for causal responsibility, providing a framework for responsibility-aware multi-agent strategic reasoning. We present an approach to synthesise joint strategies that satisfy an outcome specified in PATL+R, while optimising the share of expected causal responsibility and reward. This provides a notion of balanced distribution of responsibility and reward gain among agents. To this end, we utilise the Nash equilibrium as the solution concept for our strategic reasoning problem and demonstrate how to compute responsibility-aware Nash equilibrium strategies via a reduction to parametric model checking of concurrent stochastic multi-player games.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes