一句话：提出一种可扩展的规则式深度强化学习框架，用于求解下一发布问题。
论文题目指向软件发布规划中的下一发布问题（Next Release Problem），即从候选需求中选择发布内容以优化目标并满足约束。所给摘要并未描述具体技术方法，仅说明补充材料包含数据集、消融实验等额外实验输出，以及 Jupyter Notebook 形式的实现代码（Dual_DeepRL.ipynb），用于复现实验。因此，从现有信息可知该工作提出一个可扩展的、基于规则的深度强化学习框架，并提供实现与实验材料；但摘要未给出关键实验结果或具体评估指标。
Supplementary Materials Overview The supplementary materials accompanying this research include datasets, experimental outputs, and the implementation code used in the study. These materials are organized as follows: 1. Datasets All datasets used in this research are provided in the compressed file datasets.zip. This archive contains the data required to reproduce the experiments and analyses presented in the paper. 2. Supplementary Experimental Outputs Additional experimental results, including outputs from ablation study runs, are included in the compressed archive supplementary.zip. These files provide extended experimental evaluations that support the analysis discussed in the paper. 3. Implementation Code The implementation of the proposed approach is provided in the Jupyter Notebook Dual_DeepRL.ipynb. This notebook contains the code developed for the research, including the model implementation and experiment execution workflow. Notes The provided materials are intended to support reproducibility and provide additional insights into the experimental analysis. Each archive or file contains internal comments and structure to facilitate easy navigation and use.
@inproceedings{paperbot12325,
title = {A Scalable Rule-Based Deep Reinforcement Learning Framework for the Next Release Problem},
author = {Hemanth Gudaparthi and Nan Niu and Prem Swaroopaanda Ramalingam and Laxman Chowdary Kakara},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834348}
}