Research map / Bandits and online learning / Multi-armed bandits
Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed Bandits
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 |
|---|---|---|---|
| Bias the likelihood toward parameters with higher possible reward | RBMLE · Exponential-family and sub-Gaussian bandits | regret: O(log(T)) | Helped |
| Choose the bias growth rate as α(t)=Cα log t with a sufficiently large Cα | RBMLE · Gaussian and sub-Gaussian bandits | regret: O(log(T)) | Helped |
| Estimate the minimum gap adaptively when selecting the bias growth rate | RBMLE · Gaussian and sub-Gaussian bandits | regret: O(log(T)) | Helped |
| Use RBMLE rather than integral-estimating IDS or VIDS | Bandit algorithms · Bernoulli, Gaussian, and Exponential bandits | computation time per decision: orders of magnitude less computation time | Helped |
| Use knowledge-gradient methods on discrete Bernoulli rewards | KG, KGMin, and KGMN · Bernoulli bandits | cumulative regret | Hurt |
Closest papers by meaning
- Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits (AAAI 2021 · similarity 0.94)
- Reward-Biased Maximum Likelihood Estimation for Neural Contextual Bandits: A Distributional Learning Perspective (AAAI 2023 · similarity 0.92)
- Structure Adaptive Algorithms for Stochastic Bandits (ICML 2020 · similarity 0.90)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.89)
- Forced Exploration in Bandit Problems (AAAI 2024 · similarity 0.88)
- Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates (NeurIPS 2024 · 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.