Research map / Learning theory and algorithms / Submodular and game algorithms
Online Learning in Periodic Zero-Sum Games
Tanner Fiez, Ryann Sim, EFSTRATIOS PANTELEIMON SKOULAKIS, Georgios Piliouras, Lillian J Ratliff
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 |
|---|---|---|---|
| periodic rescaling of Matching Pennies payoffs (time-invariant equilibrium) instead of a static game | continuous-time GDA · Matching Pennies, period 2pi | trajectory boundedness / Poincare recurrence | No clear effect |
| periodic rescaling instead of static game | replicator dynamics (FTRL) · Matching Pennies with periodic rescaling | payoff-space boundedness | No clear effect |
| 64-player polymatrix extension with random periodic rescaling per game | replicator dynamics · 64-player Matching Pennies polymatrix | weighted sum of KL divergences | No clear effect |
| run 8x8 polymatrix game for long time | replicator dynamics · 8x8 zero-sum polymatrix pixel grid | Poincare recurrence: T=6226 | Improved |
| remove time-invariant equilibrium: first quarter Matching Pennies, remaining three quarters a second matrix with equilibrium [0.9091, 0.0909] (ablation) | replicator dynamics (FTRL) · periodic game without common equilibrium | Poincare recurrence | Hurt |
| move from static to periodic zero-sum games | time-average GDA and FTRL strategies · periodic zero-sum games | time-average convergence to equilibrium | Hurt |
| move from static to periodic bimatrix zero-sum games | FTRL time-average utilities · periodic bimatrix games | time-average utility convergence | Improved |
Closest papers by meaning
- Synchronization in Learning in Periodic Zero-Sum Games Triggers Divergence from Nash Equilibrium (AAAI 2025 · similarity 0.92)
- No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests (NeurIPS 2024 · similarity 0.91)
- Convergence of No-Swap-Regret Dynamics in Self-Play (NeurIPS 2024 · similarity 0.90)
- Memory Asymmetry Creates Heteroclinic Orbits to Nash Equilibrium in Learning in Zero-Sum Games (AAAI 2024 · similarity 0.89)
- Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration (NeurIPS 2025 · similarity 0.89)
- The impact of uncertainty on regularized learning in games (ICML 2025 · similarity 0.89)
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.
