用可微分博弈块实现多智能体激励设计，自动找到稳定均衡。
Deep Incentive Design with Differentiable Equilibrium Blocks
- 引入可微分博弈块，将激励设计问题转化为端到端训练任务。
- 在合约设计、任务调度等3类问题上统一求解，支持每方2至16种动作。
- 适合需要自动化设计博弈规则的经济与计算机系统研究者。
由于计算困难、均衡不唯一且不稳定，自动化设计具有理想均衡结果的多智能体交互极具挑战。本文提出使用与博弈无关的可微分均衡块（DEBs）作为模块，构建全新的可微分框架——深度激励设计（DID），以解决经济学与计算机科学中的多种激励设计问题。通过三个不同且复杂的任务验证：合约设计、机器调度和逆均衡问题。仅用单一神经网络与统一流程及DEB，即可求解参数化上下文下的全分布问题实例，覆盖每方2至16种动作的广泛规模场景。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。