Research map / Learning theory and algorithms / Submodular and game algorithms
Multiagent Evaluation under Incomplete Information
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 relaxed Clopper-Pearson confidence bounds instead of the other tested bounds (ablation) | ResponseGraphUCB · Bernoulli games | number of interactions: roughly an order of magnitude fewer samples | Helped |
| Use Clopper-Pearson bounds instead of Hoeffding bounds (ablation) | ResponseGraphUCB · Bernoulli games | number of interactions | Helped |
| Increase the error tolerance δ (ablation) | ResponseGraphUCB with uniform-exhaustive sampling and UCB, R-UCB, or CP-UCB · Soccer meta-game | response graph edge errors | Mixed |
| Collect more samples to reduce payoff-table error | Elo and infinite-α α-Rank · Soccer meta-game | Kendall partial ranking error | Helped |
| Collect more samples | Infinite-α α-Rank · Kuhn poker meta-game | ranking error | Helped |
| Use the error tolerance δ as a tuning parameter (ablation) | ResponseGraphUCB · Soccer meta-game | ranking error | No clear effect |
| Use the error tolerance δ as a tuning parameter (ablation) | ResponseGraphUCB · Kuhn poker meta-game | ranking error | Helped |
| Apply adaptive sampling to games with payoff gaps concentrated near zero | ResponseGraphUCB · Kuhn poker meta-game | ranking variance | Hurt |
Closest papers by meaning
- Estimating $α$-Rank from A Few Entries with Low Rank Matrix Completion (ICML 2021 · similarity 0.91)
- Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration (NeurIPS 2025 · similarity 0.87)
- No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests (NeurIPS 2024 · similarity 0.86)
- Is Knowledge Power? On the (Im)possibility of Learning from Strategic Interactions (NeurIPS 2024 · similarity 0.86)
- Eliciting Kemeny Rankings (AAAI 2024 · similarity 0.86)
- The impact of uncertainty on regularized learning in games (ICML 2025 · similarity 0.85)
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.