Research map / Bandits and online learning / Multi-armed bandits
Choice Bandits
Arpit Agarwal, Nicholas Johnson, Shivani Agarwal
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 |
|---|---|---|---|
| WBA with k=2 compared against dueling bandit baselines RMED1, RUCB, BTM, DTS | WBA · synthetic and real choice-model datasets (k=2) | regret | Mixed |
| WBA instead of MaxMinUCB for k=2 and k=5 | WBA · all datasets including MNL models | regret | Improved |
| increase pulled set size from k=2 to k>2 | WBA · GCC-One, GCC-Two, Sushi, Irish-Dublin | regret | Improved |
Closest papers by meaning
- On Weak Regret Analysis for Dueling Bandits (NeurIPS 2024 · similarity 0.90)
- Bandits with Ranking Feedback (NeurIPS 2024 · similarity 0.89)
- Neural Dueling Bandits: Preference-Based Optimization with Human Feedback (ICLR 2025 · similarity 0.89)
- Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits (ICLR 2024 · similarity 0.89)
- Fusing Reward and Dueling Feedback in Stochastic Bandits (ICML 2025 · similarity 0.89)
- Balancing Performance and Costs in Best Arm Identification (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.
