Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Target Tracking for Contextual Bandits: Application to Demand Side Management
Margaux Brégère, Pierre Gaillard, Yannig Goude, 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 |
|---|---|---|---|
| Use the optimistic target-tracking algorithm with initial covariance estimation | Contextual bandits with tariff-dependent noise (Model 1) · Contextual bandit, Model 1 | regret upper bound: O\Bigl( T^{2/3} \ln^2 \big( \frac{T}{\delta}\big) \sqrt{\ln\frac{1}{\delta}} \Bigr) | Improved |
| Assume targets are attainable and use the simplified optimistic algorithm | Target-tracking algorithm under global noise (Model 2) · Contextual bandit, Model 2 | regret upper bound: O \bigl( \ln^2(T) \bigr) | Improved |
| Use Model 2 rather than Model 1 in the simulator | Target-tracking algorithms on the UK Power Networks-based simulator · January testing period | regret | Improved |
| Use Model 2 rather than Model 1 in the simulator | Target-tracking algorithms on the UK Power Networks-based simulator · January 30 testing day | distance between expected consumption and target | Improved |
Closest papers by meaning
- Linear Contextual Bandits with Knapsacks (NeurIPS 2016 · similarity 0.86)
- Improved learning rates in multi-unit uniform price auctions (NeurIPS 2024 · similarity 0.85)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · similarity 0.85)
- Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand (NeurIPS 2026 · similarity 0.85)
- Contextual Decision-Making with Knapsacks Beyond the Worst Case (NeurIPS 2024 · similarity 0.84)
- Exploration via Feature Perturbation in Contextual Bandits (NeurIPS 2025 · similarity 0.84)
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.
