Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Dynamic Learning of Sequential Choice Bandit Problem under Marketing Fatigue
Junyu Cao, Wei Sun
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 proposed UCB algorithm instead of Benchmark-1 (explore-then-exploit) | SC-Bandit without contexts · Non-contextual SC-Bandit | average regret | Improved |
| Use the proposed UCB algorithm instead of Benchmark-2 | SC-Bandit without contexts · Non-contextual SC-Bandit | average regret | Improved |
| Use Benchmark-2 instead of Benchmark-1, incorporating learning during exploration | SC-Bandit without contexts · Non-contextual SC-Bandit | average regret | Improved |
| Use the proposed UCB algorithm instead of Benchmark-1 (explore-then-exploit) | Contextual SC-Bandit · Contextual SC-Bandit | average regret | Improved |
| Use the proposed UCB algorithm instead of Benchmark-2 | Contextual SC-Bandit · Contextual SC-Bandit | average regret | Improved |
| Incorporate learning during exploration, as in Benchmark-2 rather than Benchmark-1 | SC-Bandit · Contextual and non-contextual SC-Bandit | average regret | Improved |
| Increase the range of uniformly generated valuations across the reported scenarios | SC-Bandit UCB · SC-Bandit robustness experiment | average regret: 141.13, 121.91, 59.69, and 44.64 | Mixed |
| Use higher valuations that can produce longer optimal sequences | SC-Bandit UCB · SC-Bandit robustness experiment | time to learn the optimal sequence | Hurt |
Closest papers by meaning
- Fatigue-Aware Bandits for Dependent Click Models (AAAI 2020 · similarity 0.88)
- Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit Problem (ICML 2019 · similarity 0.87)
- Improved Analysis for Bandit Learning in Matching Markets (NeurIPS 2024 · similarity 0.86)
- Online Learning of Delayed Choices (NeurIPS 2024 · similarity 0.85)
- Regret Analysis of Repeated Delegated Choice (AAAI 2024 · similarity 0.85)
- Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards (NeurIPS 2025 · similarity 0.85)
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.
