Research map / Bandits and online learning / Online convex optimization and games
Online Convex Optimization for Sequential Decision Processes and 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 LRM with online gradient descent to compute QREs instead of using CFR$^+$ as the Nash-equilibrium reference | LRM · Goofspiel 4 | saddle-point gap convergence | Helped |
| Use LRM with online gradient descent to compute QREs instead of using CFR$^+$ as the Nash-equilibrium reference | LRM · Leduc 5 | saddle-point gap convergence | Mixed |
| Solve an ℓ₂-regularized game rather than compute a Nash equilibrium | LRM · Leduc 5 | saddle-point gap convergence | Helped |
| Increase the penalty for distance from a precomputed Nash equilibrium | LRM opponent exploiter · Static-opponent exploitation | utility increase from exploitation | Hurt |
| Increase the penalty for distance from a precomputed Nash equilibrium | LRM opponent exploiter · Static-opponent exploitation | exploiter's own exploitability | Helped |
| Apply alternation when updating the two players' losses | Regret minimization for bilinear games · Toy game with X = Y = [0,1] | saddle-point convergence | Hurt |
Closest papers by meaning
- Efficient Regret Minimization Algorithm for Extensive-Form Correlated Equilibrium (NeurIPS 2019 · similarity 0.94)
- Regret Minimization in Behaviorally-Constrained Zero-Sum Games (ICML 2017 · similarity 0.93)
- Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions (NeurIPS 2019 · similarity 0.93)
- Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games (AAAI 2021 · similarity 0.93)
- Regret Circuits: Composability of Regret Minimizers (ICML 2019 · similarity 0.93)
- Stable-Predictive Optimistic Counterfactual Regret Minimization (ICML 2019 · similarity 0.92)
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.