Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Fighting Boredom in Recommender Systems with Linear Reinforcement Learning
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 |
|---|---|---|---|
| plan a long-term cycle of actions (LINUCRL) instead of a greedy contextual policy | LINUCRL · A/B testing simulator | relative improvement over only A: 61.3% -> 66.7% | Helped |
| exploit linear reward structure (LINUCRL) instead of tabular UCRL | LINUCRL · MovieLens-100k simulator | average reward: 3.327 -> 3.54 | Helped |
| model recency effect and optimize long-term reward (LINUCRL) instead of LINUCB | LINUCRL · MovieLens-100k simulator | average reward: 3.43 -> 3.54 | Helped |
| increase polynomial degree of recency reward model (ablation) | recency reward model · MovieLens-100k reward fit | R2: 0.55 -> 0.81 (action, d=1 to d=5) | Helped |
| optimal long-term policy instead of greedy policy when boredom effect is strong | toy two-action MDP · toy experiment | average reward | Helped |
| UCRL on A/B simulator versus only B baseline | UCRL · A/B testing simulator | relative improvement over only A: 46.0% -> 46.5% | No clear effect |
Closest papers by meaning
- On the Unexpected Effectiveness of Reinforcement Learning for Sequential Recommendation (ICML 2024 · similarity 0.89)
- Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation (ICLR 2024 · similarity 0.88)
- Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders (NeurIPS 2026 · similarity 0.88)
- Strategic Linear Contextual Bandits (NeurIPS 2024 · similarity 0.88)
- UNEX-RL: Reinforcing Long-Term Rewards in Multi-Stage Recommender Systems with UNidirectional EXecution (AAAI 2024 · similarity 0.87)
- Learning to Recommend in Unknown Games (NeurIPS 2026 · similarity 0.87)
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.