Coalition Free Energy and Adaptive Precision in Multi-Agent Cooperation
For multi-agent systems, this work provides a principled method for adaptive precision control that improves robustness under uncertainty, though the gains are incremental over fixed-precision baselines.
The paper introduces a Game-Theoretic Free Energy Principle (GT-FEP) for credit assignment in multi-agent systems, and proposes Adaptive Precision Control (APC) that dynamically adjusts observation precision. APC achieves performance comparable to the best fixed precision without prior tuning on real-world trajectory datasets.
Cooperative multi-agent systems require robust mechanisms for credit assignment under uncertainty. Here we introduce a variational framework, termed the Game-Theoretic Free Energy Principle (GT-FEP), that models coalition formation through a Gibbs distribution over interacting agents. Within this framework, we derive a precision-dependent formulation of cooperative credit assignment and show that an agent's Shapley value exhibits a non-monotonic relationship with sensory precision beta, reflecting a trade-off between noisy inference and overconfident local estimation. Motivated by this observation, we propose Adaptive Precision Control (APC), an online adaptation algorithm that dynamically adjusts observation precision using local estimates of cooperative contribution. We evaluate APC on real-world Swiss roundabout trajectory datasets and on a multi-agent control task derived from the same trajectories. Across both settings, APC adapts to changing noise conditions online and achieves performance comparable to the best fixed precision without prior tuning. Our results connect variational inference, cooperative game theory, and adaptive multi-agent coordination, and suggest that precision adaptation can improve robust cooperation under uncertainty.