Research map / Reinforcement learning / RL from feedback
Text-Based Interactive Recommendation via Constraint-Augmented 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 |
|---|---|---|---|
| add learned discriminator constraint (RCR) | RL recommender · UT-Zappos50K unseen | SR@10: 19% -> 74% | Helped |
| add learned discriminator constraint (RCR) | RL recommender · UT-Zappos50K unseen | NV (violations): 70.02 ± 6.20 -> 11.32 ± 1.98 | Helped |
| add learned discriminator constraint (RCR) | RL recommender · UT-Zappos50K unseen | NI (interactions): 26.75 ± 1.67 -> 10.91 ± 1.06 | Helped |
| replace naive hard attribute constraints with learned discriminator | RL + Naive · UT-Zappos50K unseen | SR@10: 52% -> 74% | Helped |
| replace naive hard attribute constraints with learned discriminator | RL + Naive · UT-Zappos50K unseen | SR@30: 94% -> 94% | No clear effect |
| add naive hard constraints | RL recommender · UT-Zappos50K unseen | SR@30: 63% -> 94% | Helped |
| add learned discriminator constraint (RCR) | RL text generator · Yelp | violation rate: 40.36% -> 10.49% | Helped |
| add learned discriminator constraint (RCR) | RL text generator · Yelp | test-BLEU-2: 0.807 -> 0.840 | Helped |
| add learned discriminator constraint (RCR) | RL text generator · Yelp | self-BLEU-2: 0.658 -> 0.683 | Hurt |
Closest papers by meaning
- On the Unexpected Effectiveness of Reinforcement Learning for Sequential Recommendation (ICML 2024 · similarity 0.87)
- Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders (NeurIPS 2026 · similarity 0.86)
- Contrastive Representation for Interactive Recommendation (AAAI 2025 · similarity 0.85)
- ConvRec-R1: Training LLM-based Conversational Recommender Systems with Reinforcement Learning (ICLR 2026 · similarity 0.85)
- Think before Recommendation: Autonomous Reasoning-enhanced Recommender (NeurIPS 2025 · similarity 0.85)
- MTRec: Learning to Align with User Preferences via Mental Reward Models (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.