Research map / Bandits and online learning / Multi-armed bandits
Bandits Dueling on Partially Ordered Sets
Julien Audiffren, Liva Ralaivola
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 UnchainedBandits instead of modified RUCB | Dueling bandits on posets · Simulated random posets | regret | Improved |
| Add clearly suboptimal arms to the poset | UnchainedBandits vs modified RUCB · Simulated random posets | regret gap | Improved |
| Use UnchainedBandits or modified RUCB instead of UniformSampling or modified IF2 | Dueling bandits on posets · Simulated random posets | regret | Improved |
| Use UniformSampling instead of modified single-pivot IF2 | Dueling bandits on posets · Simulated random posets | regret | Improved |
| Use larger decoy Delta | Algorithm 4 (decoys) · Theory / real-life | number of comparisons | Mixed |
| Replace average-score top five with Pareto front | Film selection · MovieLens 20M | genre diversity | Improved |
Closest papers by meaning
- Dueling Bandits: Beyond Condorcet Winners to General Tournament Solutions (NeurIPS 2016 · similarity 0.89)
- Batched Dueling Bandits (ICML 2022 · similarity 0.89)
- Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting (NeurIPS 2024 · similarity 0.88)
- On Weak Regret Analysis for Dueling Bandits (NeurIPS 2024 · similarity 0.88)
- Fusing Reward and Dueling Feedback in Stochastic Bandits (ICML 2025 · similarity 0.88)
- The Sampling Complexity of Condorcet Winner Identification in Dueling Bandits (NeurIPS 2026 · 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.
