Summary of Modrl-ta:a Multi-objective Deep Reinforcement Learning Framework For Traffic Allocation in E-commerce Search, by Peng Cheng et al.
MODRL-TA:A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search
by Peng Cheng, Huimu Wang, Jinyuan Zhao, Yihao Wang, Enqiang Xu, Yu Zhao, Zhuojian Xiao, Songlin Wang, Guoyu Tang, Lin Liu, Sulong Xu
First submitted to arxiv on: 22 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Information Retrieval (cs.IR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed multi-objective deep reinforcement learning framework addresses the limitations of existing methods in traffic allocation for e-commerce platforms. The framework consists of multi-objective Q-learning (MOQ), a decision fusion algorithm (DFM) based on the cross-entropy method (CEM), and a progressive data augmentation system (PDA). MOQ constructs ensemble RL models, each dedicated to an objective such as click-through rate or conversion rate, aiming to estimate the long-term value of multiple objectives. DFM dynamically adjusts weights among objectives to maximize long-term value, addressing temporal dynamics in e-commerce scenarios. The PDA trained MOQ with simulated data from offline logs and strategically integrated real user interaction data, alleviating distributional shifts and cold start problems. Experimental results demonstrate significant improvements on real-world online e-commerce systems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Traffic allocation is a way to make products more visible in an online store. This helps merchants grow their business, meets customers’ needs, and makes everyone happy. Old methods didn’t consider the long-term effects of this process, while new approaches had trouble balancing different goals and starting from scratch with real data. A team proposed a new framework that combines multiple ideas to solve these problems. It uses a special kind of machine learning called reinforcement learning, which adjusts its decisions based on feedback. The framework is tested on real online stores and shows big improvements. |
Keywords
* Artificial intelligence * Cross entropy * Data augmentation * Machine learning * Reinforcement learning
