Research map / Reinforcement learning / Offline RL
Text-Based Interactive Recommendation via Offline 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 |
|---|---|---|---|
| Use conservative offline Q-value evaluation and policy improvement instead of direct off-policy learning | Text-based interactive recommendation · UT-Zappos50K simulator | SR@10: 59% -> 72% | Helped |
| Use conservative offline Q-value evaluation and policy improvement instead of imitation learning | Text-based interactive recommendation · UT-Zappos50K simulator | NV: 19.00 ± 3.82 -> 13.08 ± 2.78 | Helped |
| Iteratively refresh the offline dataset using deployed recommender policies | Offline Learning · UT-Zappos50K simulator | SR@10: 72% -> 78% | Helped |
| Iteratively refresh the offline dataset using deployed recommender policies | Offline Learning · UT-Zappos50K simulator | NV: 13.08 ± 2.78 -> 10.53 ± 2.52 | Helped |
| Learn directly from fixed experience collected by multiple unknown policies without correction | Text-based interactive recommendation · UT-Zappos50K simulator | SR@10: 84% -> 59% | Hurt |
Closest papers by meaning
- Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders (NeurIPS 2026 · similarity 0.86)
- ConvRec-R1: Training LLM-based Conversational Recommender Systems with Reinforcement Learning (ICLR 2026 · similarity 0.86)
- On the Unexpected Effectiveness of Reinforcement Learning for Sequential Recommendation (ICML 2024 · similarity 0.86)
- Distributional Off-Policy Evaluation for Slate Recommendations (AAAI 2024 · similarity 0.86)
- MTRec: Learning to Align with User Preferences via Mental Reward Models (NeurIPS 2025 · similarity 0.85)
- MultiScale Contextual Bandits for Long Term Objectives (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.