Automated design of multi-agent interactions with desirable equilibrium outcomes is inherently difficult due to the computational hardness, non-uniqueness, and instability of the resulting equilibria. In this work, we propose the use of game-agnostic differentiable equilibrium blocks (DEBs) as modules in a novel, differentiable framework to address a wide variety of incentive design problems from economics and computer science. We call this framework deep incentive design (DID). To validate our approach, we examine three diverse, challenging incentive design tasks: contract design, machine scheduling, and inverse equilibrium problems. For each task, we train a single neural network using a unified pipeline and DEB. This architecture solves the full distribution of problem instances, parameterized by a context, handling all games across a wide range of scales (from two to sixteen actions per player).

翻译：由于计算复杂性、均衡解的非唯一性及不稳定性，自动化设计具有理想均衡结果的多智能体交互本质上具有挑战性。本研究提出采用博弈无关的可微分均衡模块作为核心组件，构建一种新颖的可微分框架，以解决经济学与计算机科学领域中的各类激励设计问题。我们将该框架称为深度激励设计。为验证方法的有效性，我们考察了三类具有挑战性的激励设计任务：契约设计、机器调度与逆均衡问题。针对每项任务，我们采用统一流程与可微分均衡模块训练单一神经网络。该架构能够求解由上下文参数化的问题实例全分布，处理从每智能体两个到十六个动作的广泛规模博弈。