Research map / Bandits and online learning / Online convex optimization and games
Near-Optimal $\Phi$-Regret Learning in Extensive-Form 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 log-regularized OFTRL (LRL-OFTRL) local regret minimizers combined via a regret circuit preserving RVU property | trigger-deviation regret minimizer for EFCE · multiplayer imperfect-information EFGs | trigger regret growth in T: O(T^{1/4}) to O(log T) | Helped |
| Refined regret circuit for convex hull that bounds by sum of nonnegative regrets instead of max | convex hull combination of local regret minimizers · theory | RVU property preservation | Helped |
| Use CFR with regret matching and CFR+ with RM+ instead of the proposed dynamics on Kuhn, Goofspiel, Sheriff | baseline regret minimizers · Kuhn poker, Goofspiel, Sheriff | trigger regret growth | Hurt |
Closest papers by meaning
- No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium (NeurIPS 2020 · similarity 0.93)
- Efficient $\Phi$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games (NeurIPS 2024 · similarity 0.90)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · similarity 0.90)
- Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games (ICLR 2024 · similarity 0.89)
- Comparator-Adaptive $\Phi$-Regret: Improved Bounds, Simpler Algorithms, and Applications to Games (NeurIPS 2025 · similarity 0.89)
- No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests (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.