# End-to-End Learning and Intervention in Games

arXiv: https://arxiv.org/abs/2010.13834 · HTML: https://mlsanity.com/paper/2010.13834/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2020.

## Built on by (most cited first, 20 of 20)

- [SoK: Machine Learning Governance](https://mlsanity.com/paper/2109.10870/) (2021)
- [Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence](https://mlsanity.com/paper/2110.01212/) (2021)
- [Is Nash Equilibrium Approximator Learnable?](https://mlsanity.com/paper/2108.07472/) (2021)
- [Differentiable Bilevel Programming for Stackelberg Congestion Games](https://mlsanity.com/paper/2209.07618/) (2022)
- [Regret Equals Covariance: A Closed-Form Characterization for Stochastic Optimization](https://mlsanity.com/paper/2605.14019/) (2026)
- [WardropNet: Traffic Flow Predictions via Equilibrium-Augmented Learning](https://mlsanity.com/paper/2410.06656/) (2024)
- [Learning to Steer Markovian Agents under Model Uncertainty](https://mlsanity.com/paper/2407.10207/) (2024)
- [Deep Incentive Design with Differentiable Equilibrium Blocks](https://mlsanity.com/paper/2603.07705/) (2026)
- [Beyond NaN: Resiliency of Optimization Layers in The Face of Infeasibility](https://mlsanity.com/paper/2202.06242/) (2022)
- [Tackling Asymmetric and Circular Sequential Social Dilemmas with Reinforcement Learning and Graph-based Tit-for-Tat](https://mlsanity.com/paper/2206.12909/) (2022)
- [Differentiable Arbitrating in Zero-sum Markov Games](https://mlsanity.com/paper/2302.10058/) (2023)
- [Learning Optimal Tax Design in Nonatomic Congestion Games](https://mlsanity.com/paper/2402.07437/) (2024)
- [Operator Splitting for Learning to Predict Equilibria in Convex Games](https://mlsanity.com/paper/2106.00906/) (2021)
- [Barriers to Welfare Maximization with No-Regret Learning](https://mlsanity.com/paper/2411.01720/) (2024)
- [SPO-VCS: An End-to-End Smart Predict-then-Optimize Framework with Alternating Differentiation Method for Relocation Problems in Large-Scale Vehicle Crowd Sensing](https://mlsanity.com/paper/2411.18432/) (2024)
- [Hypernetwork-based approach for optimal composition design in partially controlled multi-agent systems](https://mlsanity.com/paper/2502.12605/) (2025)
- [From Sequential to Recursive: Enhancing Decision-Focused Learning with Bidirectional Feedback](https://mlsanity.com/paper/2511.08035/) (2025)
- [Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisition](https://mlsanity.com/paper/2604.23413/) (2026)
- [Semiparametric Efficient Bilevel Gradient Estimation](https://mlsanity.com/paper/2605.21341/) (2026)
- [Large Language Model Assisted Transportation Planning through a Differentiable User Equilibrium Layer](https://mlsanity.com/paper/2610.16140/) (2026)

## Abstract (arXiv)

In a social system, the self-interest of agents can be detrimental to the collective good, sometimes leading to social dilemmas. To resolve such a conflict, a central designer may intervene by either redesigning the system or incentivizing the agents to change their behaviors. To be effective, the designer must anticipate how the agents react to the intervention, which is dictated by their often unknown payoff functions. Therefore, learning about the agents is a prerequisite for intervention. In this paper, we provide a unified framework for learning and intervention in games. We cast the equilibria of games as individual layers and integrate them into an end-to-end optimization framework. To enable the backward propagation through the equilibria of games, we propose two approaches, respectively based on explicit and implicit differentiation. Specifically, we cast the equilibria as the solutions to variational inequalities (VIs). The explicit approach unrolls the projection method for solving VIs, while the implicit approach exploits the sensitivity of the solutions to VIs. At the core of both approaches is the differentiation through a projection operator. Moreover, we establish the correctness of both approaches and identify the conditions under which one approach is more desirable than the other. The analytical results are validated using several real-world problems.