Research map / Multi-agent systems and games / Games and equilibria
Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence
Boyi Liu, Jiayang Li, Zhuoran Yang, Hoi To Wai, Mingyi Hong, Yu Nie, Zhaoran Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use simultaneous single-loop design-and-play instead of double-loop AD | Emission tax design · Emission tax design | Time per iteration (ms): 137.89 -> 2.57 | Improved |
| Use simultaneous single-loop design-and-play instead of double-loop ID | Emission tax design · Emission tax design | Time per iteration (ms): 18.04 -> 2.57 | Improved |
| Use simultaneous single-loop design-and-play instead of double-loop AD | Emission tax design · Emission tax design | Total CPU time (s): 71.56 -> 2.09 | Improved |
| Use simultaneous single-loop design-and-play instead of double-loop ID | Emission tax design · Emission tax design | Total CPU time (s): 11.29 -> 2.09 | Improved |
| Omit the uniform-strategy mixing step (Setting D) (ablation) | Simultaneous design-and-play · Sioux-Falls congestion pricing | Convergence | Hurt |
| Use the theorem's step-size schedule (Setting A) rather than the other tested schedules (ablation) | Simultaneous design-and-play · Sioux-Falls congestion pricing | Convergence stability | Improved |
Closest papers by meaning
- Scalable Neural Incentive Design with Parameterized Mean-Field Approximation (NeurIPS 2025 · similarity 0.87)
- Contextual Bilevel Reinforcement Learning for Incentive Alignment (NeurIPS 2024 · similarity 0.87)
- Computing Game Symmetries and Equilibria That Respect Them (AAAI 2025 · similarity 0.85)
- Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment (NeurIPS 2025 · similarity 0.85)
- Cost Minimization for Equilibrium Transition (AAAI 2024 · similarity 0.85)
- Aligning Individual and Collective Objectives in Multi-Agent Cooperation (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
