Research map / Reinforcement learning / Imitation learning
Virtual-Taobao: Virtualizing Real-World Online Retail Environment for 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 |
|---|---|---|---|
| Train the search policy with RL in Virtual Taobao instead of supervised learning on historical data | Taobao search policy · Taobao online | R2P: 0.096 -> 0.101 | Helped |
| Train the search policy with RL in Virtual Taobao instead of SL2 on historical data | Taobao search policy · Taobao online | R2P: 0.098 -> 0.101 | Helped |
| Add Action Norm Constraint (ANC) to TRPO (ablation) | TRPO · Taobao online | Total Turnover (TT) | Helped |
| Add Action Norm Constraint (ANC) to TRPO (ablation) | TRPO · Taobao online | Total Volume (TV) | Helped |
| Use MAIL rather than behavior cloning to build the virtual environment | TRPO-ANC policy trained in Virtual Taobao · Later virtual environments (one day, one week, and one month later) | R2P | Helped |
Closest papers by meaning
- Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning (ICLR 2026 · similarity 0.86)
- Reinforcement Mechanism Design for Fraudulent Behaviour in e-Commerce (AAAI 2018 · similarity 0.83)
- ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based Agents (AAAI 2026 · similarity 0.83)
- Online Matching with Stochastic Rewards: Provable Better Bound via Adversarial Reinforcement Learning (ICML 2024 · similarity 0.81)
- XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning (ICLR 2025 · similarity 0.81)
- Improving Reward Model Generalization from Adversarial Process Enhanced Preferences (ICML 2025 · similarity 0.81)
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.