Research map / Learning theory and algorithms / Submodular and game algorithms
Constrained Phi-Equilibria
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Introduce strategy constraints and restrict deviations to safe deviations | Phi-equilibria in normal-form games · Cost-constrained normal-form games | convexity of the equilibrium set | Hurt |
| Use the general constrained Phi-equilibrium formulation without fixing the number of constraints or actions | ApxCPE · Cost-constrained normal-form games | computational tractability | Hurt |
| Fix the number of cost constraints | Lagrange-multiplier discretization algorithm · ApxCPE(1, ε) | runtime | Helped |
| Fix the number of players' actions | Lagrange-multiplier discretization algorithm · ApxCPE(1, ε), constant ε | runtime | Helped |
| Make each player's deviation costs independent of the modified correlated strategy | Constrained Phi-equilibria · Cost-constrained normal-form games | convexity of the equilibrium set | Helped |
| Make each player's deviation costs independent of the modified correlated strategy | ApxCPE(1, 0) · Cost-constrained normal-form games satisfying the deviation-cost assumption | runtime | Helped |
| Use decentralized no-regret learning when deviation costs are independent of the modified correlated strategy | Constrained Phi-equilibria · Cost-constrained normal-form games satisfying the deviation-cost assumption | equilibrium approximation error: O(\nicefrac{1}{\sqrt{T}) | Helped |
| Use CCE deviations with costs depending only on the player's own action | Marginally-constrained CCE · Cost-constrained normal-form games | runtime | Helped |
Closest papers by meaning
- On Tractable $\Phi$-Equilibria in Non-Concave Games (NeurIPS 2024 · similarity 0.91)
- The Complexity of Correlated Equilibria in Generalized Games (NeurIPS 2025 · similarity 0.91)
- Anytime-Constrained Equilibria in Polynomial Time (ICML 2025 · similarity 0.89)
- Cost Minimization for Equilibrium Transition (AAAI 2024 · similarity 0.89)
- The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games (NeurIPS 2025 · similarity 0.88)
- Polynomial-Time Computation of Exact $\Phi$-Equilibria in Polyhedral Games (NeurIPS 2024 · similarity 0.88)
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.