Deep Incentive Design with Differentiable Equilibrium Blocks

• URL: http://arxiv.org/abs/2603.07705v2
• Date: Thu, 12 Mar 2026 17:09:10 GMT
• Title: Deep Incentive Design with Differentiable Equilibrium Blocks
• Abstract summary: Game-agnostic differentiable equilibrium blocks (DEBs) are modules in a novel framework to address a wide variety of incentive design problems.<n>We train a single neural network using a unified pipeline and DEB for each task.<n>This architecture solves the full distribution of problem instances, parameterized by a context.
• Score: 31.490756127062507
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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).

Related papers

• Finding Sets of Pareto Sets in Real-World Scenarios -- A Multitask Multiobjective Perspective [35.96111940830105]
  evolutionary multitasking has been employed to generate a set of Pareto sets" (SOS) for machine learning models.<n>We demonstrate the versatility and applicability of the SOS concept across diverse domains, focusing on three real-world problems.<n>We present visualizations of the generated SOS in both decision and objective spaces, complemented by the development of a measurement.
  arXiv  Detail & Related papers  (2026-04-04T03:39:32Z)
• Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation [91.17994756436259]
  Multi-agent systems (MAS) based on large language models (LLMs) have emerged as a powerful solution for dealing with complex problems across diverse domains.<n>Existing approaches are fundamentally constrained by their reliance on a template graph modification paradigm with a predefined set of agents and hard-coded interaction structures.<n>We propose ARG-Designer, a novel autoregressive model that operationalizes this paradigm by constructing the collaboration graph from scratch.
  arXiv  Detail & Related papers  (2025-07-24T09:17:41Z)
• Constrained Stein Variational Gradient Descent for Robot Perception, Planning, and Identification [11.126853736828984]
  We present two novel frameworks for applying principles of constrained optimization to the new variational inference Stein variational descent.<n>We show that we can build distributions of: robot motion plans that exactly avoid collisions, robot arm joint angles on the SE(3) manifold with exact table placement constraints, and object poses from point clouds with table placement constraints.
  arXiv  Detail & Related papers  (2025-05-31T14:52:34Z)
• Synthesis of Reward Machines for Multi-Agent Equilibrium Design (Full Version) [2.2099217573031678]
  We study the problem of equilibrium design using dynamic incentive structures, known as reward machines. We show how reward machines can be used to represent dynamic incentives that allocate rewards in a manner that optimises the designer's goal. We present two variants of the problem: strong and weak. We demonstrate that both can be solved in time using a Turing machine equipped with an NP oracle.
  arXiv  Detail & Related papers  (2024-08-19T15:17:58Z)
• Compositional Generative Inverse Design [69.22782875567547]
  Inverse design, where we seek to design input variables in order to optimize an underlying objective function, is an important problem. We show that by instead optimizing over the learned energy function captured by the diffusion model, we can avoid such adversarial examples. In an N-body interaction task and a challenging 2D multi-airfoil design task, we demonstrate that by composing the learned diffusion model at test time, our method allows us to design initial states and boundary shapes.
  arXiv  Detail & Related papers  (2024-01-24T01:33:39Z)
• Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solvers [22.85979978964773]
  Solution concepts such as Nash Equilibria, Correlated Equilibria, and Coarse Correlated Equilibria are useful components for many multiagent machine learning algorithms. We introduce the Neural Equilibrium solver which utilizes a special equivariant neural network architecture to approximately solve the space of all games of fixed shape, buying speed and determinism.
  arXiv  Detail & Related papers  (2022-10-17T17:00:31Z)
• Controllable Dynamic Multi-Task Architectures [92.74372912009127]
  We propose a controllable multi-task network that dynamically adjusts its architecture and weights to match the desired task preference as well as the resource constraints. We propose a disentangled training of two hypernetworks, by exploiting task affinity and a novel branching regularized loss, to take input preferences and accordingly predict tree-structured models with adapted weights.
  arXiv  Detail & Related papers  (2022-03-28T17:56:40Z)
• Mind Your Solver! On Adversarial Attack and Defense for Combinatorial Optimization [111.78035414744045]
  We take an initiative on developing the mechanisms for adversarial attack and defense towards optimization solvers. We present a simple yet effective defense strategy to modify the graph structure to increase the robustness of solvers.
  arXiv  Detail & Related papers  (2021-12-28T15:10:15Z)
• Inducing Equilibria via Incentives: Simultaneous Design-and-Play Finds Global Optima [114.31577038081026]
  We propose an efficient method that tackles the designer's and agents' problems simultaneously in a single loop. Although the designer does not solve the equilibrium problem repeatedly, it can anticipate the overall influence of the incentives on the agents. We prove that the algorithm converges to the global optima at a sublinear rate for a broad class of games.
  arXiv  Detail & Related papers  (2021-10-04T06:53:59Z)
• Equilibrium Design for Concurrent Games [5.9873770241999]
  In game theory, mechanism design is concerned with the design of incentives so that a desired outcome of the game can be achieved. We study the design of incentives so that a desirable equilibrium is obtained, for instance, an equilibrium satisfying a given temporal logic property. As an application, equilibrium design can be used as an alternative solution to the rational synthesis and verification problems for concurrent games.
  arXiv  Detail & Related papers  (2021-06-18T15:45:45Z)
• Learning to Control PDEs with Differentiable Physics [102.36050646250871]
  We present a novel hierarchical predictor-corrector scheme which enables neural networks to learn to understand and control complex nonlinear physical systems over long time frames. We demonstrate that our method successfully develops an understanding of complex physical systems and learns to control them for tasks involving PDEs.
  arXiv  Detail & Related papers  (2020-01-21T11:58:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.