Research map / Bandits and online learning / Online convex optimization and games
Competing Against Nash Equilibria in Adversarially Changing Zero-Sum 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 |
|---|---|---|---|
| Each player independently minimizes its own regret (naive OCO reduction) instead of jointly targeting NE regret | Online Matrix Games with adversarial payoffs · Online Matrix Games (theoretical) | NE regret sublinear | Hurt |
| Use joint saddle-point updates with negative-entropy regularization (log dependence on action count) | Online Matrix Games full information (OMG-RFTL) · Full information Online Matrix Games | NE regret bound | Helped |
| Bandit feedback: one-point unbiased matrix estimate with joint randomization of both players' actions, combined with saddle-point RFTL | Bandit Online Matrix Games (BANDIT-OMG-RFTL) · Bandit Online Matrix Games | NE regret bound | Helped |
Closest papers by meaning
- No-Regret Learning in Time-Varying Zero-Sum Games (ICML 2022 · similarity 0.92)
- The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback (ICML 2025 · similarity 0.90)
- Convergence of No-Swap-Regret Dynamics in Self-Play (NeurIPS 2024 · similarity 0.90)
- Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms (NeurIPS 2024 · similarity 0.90)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · similarity 0.90)
- No Free Lunch Theorem and Black-Box Complexity Analysis for Adversarial Optimisation (NeurIPS 2024 · 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.