Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Efficient Contextual Bandits with Continuous Actions
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 smoothing with tree policies instead of a filter tree without smoothing | CATS versus filter tree baseline · Six regression datasets | progressive validation performance | Helped |
| Use smoothing with tree policies instead of one-versus-all classification | CATS versus one-versus-all baseline · Six regression datasets | progressive validation performance | No clear effect |
| Use tree training rather than flat one-versus-all classification | CATS versus one-versus-all baseline · Training time as discretization K grows | per-example computation: \order{K} versus \order{\log K} | Helped |
| Optimize tree policies and smoothing parameters offline using logged data | CATS policies · Six regression datasets, held-out test sets | test loss | Helped |
| Increase discretization K | CATS · Training time versus discretization | training time | Hurt |
Closest papers by meaning
- Contextual Bandits with Large Action Spaces: Made Practical (ICML 2022 · similarity 0.92)
- Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces (ICML 2022 · similarity 0.91)
- BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits (ICML 2016 · similarity 0.89)
- Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits (ICML 2024 · similarity 0.89)
- An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction (NeurIPS 2025 · similarity 0.88)
- Diffusion Models Meet Contextual Bandits (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.