Research map / Learning theory and algorithms / Submodular and game algorithms
Optimally Deceiving a Learning Leader in Stackelberg Games
Georgios Birmpas, Jiarui Gan, Alexandros Hollender, Francisco Marmolejo, Ninad Rajgopal, Alexandros Voudouris
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 |
|---|---|---|---|
| Allow the follower to report an arbitrary fake payoff matrix | Stackelberg game with a learning leader · General finite Stackelberg games | computability of optimal inducible utility | Improved |
| Require the reported payoff matrix to induce a unique SSE | Follower deception · Non-max-degenerate leader payoff matrices | optimal inducible utility: additive loss of at most ε | Mixed |
| Require a unique SSE rather than any SSE | Follower deception · Max-degenerate leader payoff matrices | strongly inducible utility: 1 to 0 | Hurt |
| Use an arbitrary best-response correspondence instead of one induced by a payoff matrix | Follower deception · General finite Stackelberg games | inducibility criterion | No clear effect |
Closest papers by meaning
- Learning Optimal Strategies to Commit To (AAAI 2019 · similarity 0.89)
- Manipulating a Learning Defender and Ways to Counteract (NeurIPS 2019 · similarity 0.88)
- Learning in Bayesian Stackelberg Games With Unknown Follower's Types (ICML 2026 · similarity 0.88)
- Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis (NeurIPS 2025 · similarity 0.85)
- Regret Minimization in Stackelberg Games with Side Information (NeurIPS 2024 · similarity 0.84)
- Prediction-Intervention Games and Invariant Sets (NeurIPS 2026 · similarity 0.83)
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.
