Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Safety-Aware Algorithms for Adversarial Contextual Bandit
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 |
|---|---|---|---|
| Add sequential risk constraint (Lagrangian dual update) to EXP4 | EXP4.R vs EXP4 · Simulated robotics reactive control | average risk constraint satisfaction | Helped |
| Add risk constraint (EXP4.R) vs unconstrained EXP4 | average cost · Simulated robotics reactive control | cost decrease rate | Hurt |
| Lower risk threshold beta | EXP4.R · Simulated robotics reactive control | average cost decrease rate | Hurt |
| Trade-off parameter epsilon in EXP4.P.R (lower epsilon) | EXP4.P.R regret vs risk violation · Theory (high probability bounds) | regret bound and risk violation bound | Mixed |
Closest papers by meaning
- Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays (NeurIPS 2026 · similarity 0.90)
- An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction (NeurIPS 2025 · similarity 0.89)
- An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints (ICML 2025 · similarity 0.89)
- Beyond $\tilde{O}(\sqrt{T})$ Constraint Violation for Online Convex Optimization with Adversarial Constraints (NeurIPS 2025 · similarity 0.89)
- Risk-Aware Continuous Control with Neural Contextual Bandits (AAAI 2024 · similarity 0.89)
- High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions (ICML 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.