Research map / Bandits and online learning / Multi-armed bandits
General Robustness Evaluation of Incentive Mechanism against Bounded Rationality Using Continuum-Armed Bandits
Zehong Hu, Jie Zhang, Zhao Li
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 |
|---|---|---|---|
| raise C0 from 0.5 to 0.7 (delta=0.99) | CABS · Hypothetical testbed | empirical error rate: 0.02 -> 0.075 | Hurt |
| raise C0 from 0.5 to 0.7 (delta=0.9) | CABS · Hypothetical testbed | empirical error rate: 0.005 -> 0.0 | Mixed |
| lower delta from 0.99 to 0.9 (C0=0.5) | CABS · Hypothetical testbed | empirical error rate: 0.02 -> 0.005 | Improved |
| increase number of workers n from 300 to 550 (Be(0.5,0.5)) | BFM · BFM vs BP-UCB | robustness: 0.89 -> 0.43 | Hurt |
| increase number of workers n from 300 to 550 (Be(1.0,1.0)) | BFM · BFM vs BP-UCB | robustness: 1.00 -> 0.70 | Hurt |
| increase number of workers n from 300 to 550 (Be(2.0,2.0)) | BFM · BFM vs BP-UCB | robustness: 1.00 -> 0.97 | Hurt |
| change worker wage distribution from Be(0.5,0.5) to Be(2.0,2.0) (n=550) | BFM · BFM vs BP-UCB | robustness: 0.43 -> 0.97 | Improved |
| replace UCB-1, ATB and Monte Carlo with CABS | CABS · Hypothetical testbed | average regret | Improved |
| use ATB instead of CABS | ATB · Hypothetical testbed | average regret | Hurt |
| evaluate DGMS by shared-task strategy instead of shared-task actions | DGMS · peer prediction, bad-mouthing agents | robustness | Improved |
| use MRZ instead of OA when Pr(h=0) is large | peer prediction mechanisms · peer prediction, bad-mouthing agents | robustness | Improved |
| use MRZ instead of OA when Pr(h=0) is small | peer prediction mechanisms · peer prediction, bad-mouthing agents | robustness | Hurt |
Closest papers by meaning
- Is O(log N) practical? Near-Equivalence Between Delay Robustness and Bounded Regret in Bandits and RL (NeurIPS 2024 · similarity 0.87)
- Greedy Algorithms for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure (NeurIPS 2025 · similarity 0.87)
- Robust Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agents (AAAI 2025 · similarity 0.87)
- Intrinsic Robustness of Prophet Inequality to Strategic Reward Signaling (NeurIPS 2024 · similarity 0.86)
- Plant-and-Steal: Truthful Fair Allocations via Predictions (NeurIPS 2024 · similarity 0.86)
- Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting (NeurIPS 2024 · similarity 0.86)
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.
