Research map / Bandits and online learning / Contextual bandits and Thompson sampling
A Direct Approach for Handling Contextual Bandits with Latent State Dynamics
Zhen LI, Gilles Stoltz
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 |
|---|---|---|---|
| update reward-model parameters only at stage boundaries (staged LinUCB) | LinUCB on estimated beliefs · state-dependent reward model | regret rate: T^{3/4} (simplified) vs T^{7/8} (state-dependent) bound | Improved |
| use staged LinUCB on estimated beliefs instead of plain LinUCB | LinUCB · simulated banking marketing (UCI credit card), 2 latent states | pseudo-regret | Improved |
| run without stages (stage length 1) versus stage length 37 (ablation) | LinUCB on estimated beliefs · simulated banking marketing | pseudo-regret | No clear effect |
Closest papers by meaning
- Model Selection for Contextual Bandits (NeurIPS 2019 · similarity 0.91)
- Stochastic Bandits with Context Distributions (NeurIPS 2019 · similarity 0.91)
- Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates (ICML 2026 · similarity 0.90)
- Semiparametric Contextual Bandits (ICML 2018 · similarity 0.89)
- Stochastic Contextual Bandits with Long Horizon Rewards (AAAI 2023 · similarity 0.89)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · 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.
