Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising
Authors: Xiaotian Hao, Zhaoqing Peng, Yi Ma, Guan Wang, Junqi Jin, Jianye Hao, Shan Chen, Rongquan Bai, Mingzhou Xie, Miao Xu, Zhenzhe Zheng, Chuan Yu, Han Li, Jian Xu, Kun Gai
ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive offline and online experiments show the superior performance of our approaches over state-of-theart baselines in terms of cumulative revenue. and 4. Empirical Evaluation: Simulations and 5. Empirical Evaluation: Online A/B Testing |
| Researcher Affiliation | Collaboration | 1College of Intelligence and Computing, Tianjin University, Tianjin, China 2Alimama, Alibaba Group, Beijing, China 3Department of Automation, Tsinghua University, Beijing, China 4Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China. |
| Pseudocode | Yes | Algorithm 1 MSBCB Framework. |
| Open Source Code | No | The paper does not contain an explicit statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | No | The paper describes a simulated environment for empirical evaluation and an online A/B testing conducted on an internal E-commerce platform (Taobao). It does not provide access information or specify a publicly available dataset with a link or citation for its experiments. While Section 4 refers to 'simulation settings of (Ie et al., 2019)', it does not state that their dataset is publicly available. |
| Dataset Splits | No | The paper does not explicitly provide details about training, validation, and test dataset splits with specific percentages, counts, or references to predefined standard splits. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU models, CPU types, memory) used to run the experiments, only mentioning a 'simulated environment' and an 'E-commerce platform, Taobao'. |
| Software Dependencies | No | The paper mentions using specific DRL algorithms (DQN, DDPG, PPO) but does not provide specific version numbers for these algorithms or any other software dependencies, which is necessary for reproducible ancillary software details. |
| Experiment Setup | No | The paper states that 'The hyperparameters for each algorithm are set to the best we found after grid-search optimization,' but it does not provide any specific values for these hyperparameters or other detailed experimental setup configurations in the main text. |