Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Contextual Bandits and Imitation Learning with Preference-Based Active Queries
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 active preference queries, skipping queries when the version space agrees on the optimal action | AURORA · Contextual dueling bandits | queries: from querying every round to \widetilde{O}\left(\min\left\{T,\; \frac{A^3\beta^3\dim^2_E(\+F,\Delta)}{\Delta^2}\right\}\ | Helped |
| Use preference comparisons to learn the policy without expert action labels or reward signals | AURORAE · Imitation learning | regret | Helped |
| Stack one AURORA instance per time step and use preference-based feedback | AURORAE · Imitation learning | queries: AURORA query bound multiplied by H | Helped |
Closest papers by meaning
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · similarity 0.92)
- Selective Sampling and Imitation Learning via Online Regression (NeurIPS 2023 · similarity 0.91)
- Efficient Algorithms for Adversarial Contextual Learning (ICML 2016 · similarity 0.90)
- Neural Dueling Bandits: Preference-Based Optimization with Human Feedback (ICLR 2025 · similarity 0.90)
- Multi-Agent Imitation Learning: Value is Easy, Regret is Hard (NeurIPS 2024 · similarity 0.89)
- Diffusion Models Meet Contextual Bandits (NeurIPS 2025 · similarity 0.89)
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.