Research map / Bandits and online learning / Multi-armed bandits
Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewards
Anmol Kagrecha, Jayakrishnan Nair, Krishna Jagannathan
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 distribution-oblivious successive-rejects algorithm instead of the non-oblivious counterpart | Successive rejects · 10-arm Pareto/exponential instance, mean minimization and CVaR minimization | probability of incorrect arm identification | No clear effect |
| set mean-estimator truncation growth to q_m = 0.4 (ablation) | Distribution-oblivious successive rejects · 2-arm Pareto/exponential instance, mean minimization | probability of incorrect arm identification | Hurt |
| set mean-estimator truncation growth to q_m = 0.5 (ablation) | Distribution-oblivious successive rejects · 2-arm Pareto/exponential instance, mean minimization | probability of incorrect arm identification | Hurt |
| set mean-estimator truncation growth to q_m = 0.7 (ablation) | Distribution-oblivious successive rejects · 2-arm Pareto/exponential instance, mean minimization | probability of incorrect arm identification | No clear effect |
Closest papers by meaning
- Optimal Best-Arm Identification Methods for Tail-Risk Measures (NeurIPS 2021 · similarity 0.91)
- Adaptive Algorithms for Infinitely Many-Armed Bandits: A Unified Framework (JMLR 2026 · similarity 0.90)
- On the Complexity of Best-Arm Identification in Multi-Armed Bandit Models (JMLR 2016 · similarity 0.90)
- Fixed-Budget Differentially Private Best Arm Identification (ICLR 2024 · similarity 0.88)
- New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problem (AAAI 2024 · similarity 0.88)
- Balancing Performance and Costs in Best Arm Identification (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.
