Research map / Bandits and online learning / Online convex optimization and games
Bandit Linear Optimization for Sequential Decision Making 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 the proposed bandit regret minimizer instead of AHR | Bandit linear optimization for TFSDM · 2×3 matrix game, Kuhn poker, 3-rank Goofspiel, and Leduc poker | cumulative regret | Helped |
| Use the proposed bandit regret minimizer instead of online MCCFR | Bandit linear optimization for TFSDM · 2×3 matrix game and Kuhn poker | cumulative regret | Helped |
| Use the proposed bandit regret minimizer instead of online MCCFR | Bandit linear optimization for TFSDM · 3-rank Goofspiel and Leduc poker | cumulative regret | Hurt |
| Use linear-time tree traversals and the dilated entropy regularizer rather than AHR's log-barrier procedure | Bandit regret minimization for TFSDM · 3-rank Goofspiel and Leduc poker | runtime per iteration | Helped |
| Use AHR on larger TFSDM problems | AHR · 3-rank Goofspiel and Leduc poker | numerical stability | Hurt |
Closest papers by meaning
- Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games (AAAI 2021 · similarity 0.90)
- Safe Learning in Tree-Form Sequential Decision Making: Handling Hard and Soft Constraints (ICML 2022 · similarity 0.89)
- Oracle-Efficient Algorithms for Online Linear Optimization with Bandit Feedback (NeurIPS 2019 · similarity 0.89)
- Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions (NeurIPS 2026 · similarity 0.89)
- Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games (ICLR 2024 · similarity 0.88)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 2025 · similarity 0.87)
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.