Research map / Bandits and online learning / Multi-armed bandits
Incentivized Exploration for Multi-Armed Bandits under Reward Drift
Zhiyuan Liu, Huazheng Wang, Fan Shen, Kai Liu, Lijun Chen
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 |
|---|---|---|---|
| Increase reward-drift coefficient from l = 0 to l = 1.1 | Incentivized UCB · Synthetic 9-arm bandit | regret: 348.5 -> 854.2 | Hurt |
| Increase reward-drift coefficient from l = 0 to l = 1.1 | Incentivized UCB · Synthetic 9-arm bandit | compensation: 277.2 -> 422.7 | Mixed |
| Increase reward-drift coefficient from l = 0 to l = 1.1 | Incentivized ε-Greedy · Synthetic 9-arm bandit | regret: 160.0 -> 317.0 | Hurt |
| Increase reward-drift coefficient from l = 0 to l = 1.1 | Incentivized ε-Greedy · Synthetic 9-arm bandit | compensation: 185.9 -> 115.2 | Mixed |
| Increase reward-drift coefficient from l = 0 to l = 1.1 | Incentivized Thompson Sampling · Synthetic 9-arm bandit | regret: 25.3 -> 74.5 | Hurt |
| Increase reward-drift coefficient from l = 0 to l = 1.1 | Incentivized Thompson Sampling · Synthetic 9-arm bandit | compensation: 18.9 -> 25.3 | Mixed |
| Use Thompson Sampling instead of UCB or ε-Greedy | Incentivized MAB · Synthetic 9-arm bandit, l = 0 | regret: 348.5 (UCB), 160.0 (ε-Greedy), 25.3 (TS) | Improved |
Closest papers by meaning
- Forced Exploration in Bandit Problems (AAAI 2024 · similarity 0.90)
- Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting (NeurIPS 2024 · similarity 0.89)
- On Multi-Armed Bandit with Impatient Arms (ICML 2024 · similarity 0.88)
- Fusing Reward and Dueling Feedback in Stochastic Bandits (ICML 2025 · similarity 0.88)
- Infrequent Exploration in Linear Bandits (NeurIPS 2025 · similarity 0.88)
- Greedy Algorithms for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure (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.
