Research map / Learning theory and algorithms / Submodular and game algorithms
Reduced Space and Faster Convergence in Imperfect-Information Games via Pruning
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 |
|---|---|---|---|
| Add Total RBP to CFR | CFR · Leduc-5 | space reduction factor: factor of 7 | Helped |
| Add Total RBP to CFR+ | CFR+ · Leduc-5 | space reduction factor: factor of 10 | Helped |
| Use Total RBP instead of Interval RBP | CFR · Leduc-5 | convergence rate: by a factor of 2 | Helped |
| Add Total RBP instead of Interval RBP | CFR · Leduc | convergence | No clear effect |
| Use Interval RBP instead of Total RBP | CFR+ · Leduc | convergence | Helped |
| Add Total RBP rather than Interval RBP | CFR+ · Leduc-5 | convergence | Mixed |
| Set the average-strategy pruning threshold to 0.1 (ablation) | CFR+ with Total RBP · Leduc-5 | space reduction factor: factor of 10 | Helped |
| Set the average-strategy pruning threshold to 0.1 (ablation) | CFR with Total RBP · Leduc-5 | space reduction factor: factor of 7 | Helped |
| Use thresholds below 0.01 instead of 0.01 (ablation) | CFR and CFR+ with Total RBP · Leduc and Leduc-5 | convergence speed | No clear effect |
| Use higher average-strategy thresholds rather than lower thresholds (ablation) | CFR and CFR+ with Total RBP · Leduc and Leduc-5 | space reduction | Helped |
| Use lower average-strategy thresholds rather than higher thresholds (ablation) | CFR and CFR+ with Total RBP · Leduc and Leduc-5 | convergence speed | Helped |
Closest papers by meaning
- Solving Imperfect-Information Games via Discounted Regret Minimization (AAAI 2019 · similarity 0.92)
- Efficient Online Pruning and Abstraction for Imperfect Information Extensive-Form Games (ICLR 2025 · similarity 0.91)
- Dynamic Thresholding and Pruning for Regret Minimization (AAAI 2017 · similarity 0.90)
- Lazy-CFR: fast and near-optimal regret minimization for extensive games with imperfect information (ICLR 2020 · similarity 0.90)
- Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games (ICLR 2025 · similarity 0.88)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · similarity 0.88)
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.