Research map / Learning theory and algorithms / Submodular and game algorithms
The Equivalence of Dynamic and Strategic Stability under Regularized Learning in Games
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 |
|---|---|---|---|
| Use regularized learning with a steep regularizer | Finite N-player games · Finite N-player games | stochastic asymptotic stability | Mixed |
| Use regularized learning with a steep regularizer | Finite N-player games · Finite N-player games | irreducible stability | Mixed |
| Use projection-based updates with a quadratic regularizer | Regularized learning · Closed sets | iterations to convergence: finite | Helped |
| Use entropic regularization and logit choice | Regularized learning · Closed sets | convergence rate: exp(-const sum_{runalt=1}^{run} iter[step]) | Helped |
| Use fractional power regularization | Regularized learning · Closed sets | convergence rate: 1/(const + sum_{runalt=start}^{run} iter[step])^{2} | Helped |
| Run regularized learning with step-size/gain parameters satisfying the stated conditions | Regularized learning · Any finite game | resilience to strategic deviations: with probability 1 | Helped |
| Rely on no-regret play alone | Players' long-run behavior · The 4x4 symmetric 2-player example | rationalizability: -1/6 | Hurt |
Closest papers by meaning
- The impact of uncertainty on regularized learning in games (ICML 2025 · similarity 0.93)
- No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests (NeurIPS 2024 · similarity 0.92)
- Convergence of No-Swap-Regret Dynamics in Self-Play (NeurIPS 2024 · similarity 0.92)
- Robust Equilibria in Continuous Games: From Strategic to Dynamic Robustness (NeurIPS 2025 · similarity 0.92)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 2025 · similarity 0.91)
- Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration (NeurIPS 2025 · similarity 0.91)
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.