Research map / Bandits and online learning / Online convex optimization and games
Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence
Yun Kuen Cheung, Georgios Piliouras
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 a finitely passive learning dynamic | Continuous-time learning dynamics · Arbitrary payoff sequences | regret | Improved |
| Use an FTRL learning dynamic | Continuous-time learning dynamics · Arbitrary payoff sequences | regret | Improved |
| Take a convex combination of finitely lossless learning dynamics | Learning dynamics · Arbitrary payoff sequences | regret | Improved |
| Use a convex combination of FTRL dynamics | Agents in a graphical constant-sum game · Graphical constant-sum game with a fully-mixed Nash equilibrium | Poincaré recurrence | Improved |
| Use Replicator Dynamics, Online Gradient Descent, or their convex combination | Learning dynamics · Cyclic Matching Pennies | Poincaré recurrence | Improved |
| Use Replicator Dynamics, Online Gradient Descent, or their convex combination | Learning dynamics · Rock-Paper-Scissors | distance to initial strategy: 10^{-3} | Improved |
Closest papers by meaning
- No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests (NeurIPS 2024 · similarity 0.90)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · similarity 0.89)
- Learning from Delayed Feedback in Games via Extra Prediction (NeurIPS 2025 · similarity 0.89)
- Convergence of No-Swap-Regret Dynamics in Self-Play (NeurIPS 2024 · similarity 0.89)
- No Coin Left Behind: Maximizing Strategic Surplus Against No-Regret Dynamics (NeurIPS 2026 · similarity 0.88)
- The impact of uncertainty on regularized learning in games (ICML 2025 · 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.
