Research map / Multi-agent systems and games / Games and equilibria
End-to-End Learning and Intervention in Games
Jiayang Li, Jing Yu, 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 learned cost functions from mode a instead of true cost functions for toll design | Toll intervention in the linear city transportation system · Linear city transportation system | travel time savings: $10.21\%$ -> $11.05\%$ | Improved |
| Use learned cost functions from mode b for toll design | Toll intervention in the linear city transportation system · Linear city transportation system | crowdedness cost increase: 15% -> $54.27\%$ | Hurt |
| Use learned cost functions from mode c for toll design | Toll intervention in the linear city transportation system · Linear city transportation system | travel time savings: $10.21\%$ -> $31.38\%$ | Improved |
| Use learned cost functions from mode c for toll design | Toll intervention in the linear city transportation system · Linear city transportation system | crowdedness cost increase: 15% -> 261.48% | Hurt |
| Change the learning hyperparameter setting to mode a (ablation) | End-to-end payoff learning · Linear city transportation system | fitting loss | Improved |
| Use implicit differentiation instead of explicit differentiation | Differentiable VI layer · Braess's paradox | gradient agreement | No clear effect |
| Use the projection-Newton method instead of the projection method | Wardrop equilibrium solver · Two-loop city network | convergence speed | Improved |
Closest papers by meaning
- Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games (NeurIPS 2023 · similarity 0.88)
- Large Scale Learning of Agent Rationality in Two-Player Zero-Sum Games (AAAI 2019 · similarity 0.87)
- Meta-Learning in Games (ICLR 2023 · similarity 0.87)
- A-PSRO: A Unified Strategy Learning Method with Advantage Metric for Normal-form Games (ICML 2025 · similarity 0.87)
- Aligning Individual and Collective Objectives in Multi-Agent Cooperation (NeurIPS 2024 · similarity 0.86)
- Explicit Exploration for High-Welfare Equilibria in Game-Theoretic Multiagent Reinforcement Learning (ICML 2025 · similarity 0.86)
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.
