该数据集构建于2025年6月，利用Python仿真平台与MPE粒子导航任务环境，借助Wandb自动采集，旨在对比沙普利分红（Shapley Dividend）与传统沙普利值（Shapley Value）两种信用分配机制嵌入多智能体强化学习算法（SD3PG与SQDDPG）后的性能差异。实验在相同网络结构与超参数条件下运行，每组数据均基于5个不同随机种子采集训练过程中每回合的平均奖励与碰撞频数，并以最大值、最小值和平均数三种统计量进行汇总，以全面反映算法的期望表现、最优边界及鲁棒性。数据集包含2个csv表格文件，分别为mean_end_reward.csv和mean_ep_collisions.csv，包含训练奖励曲线、碰撞趋势图及收敛速度分析表等可视化与衍生指标文件。通过对比训练曲线的收敛速度、最终奖励峰值及波动范围，可验证沙普利分红相较于沙普利值能够更有效地引导智能体在导航任务中形成协同策略，不仅加速合作行为的进化过程，降低碰撞频率，且在最终性能上取得更优且更稳定的合作效果，为多智能体信用分配机制的研究提供了可复用的基准数据与分析依据。
", "ds_source": "本数据集为完全仿真生成数据，不源自特定文献、实测或第三方下载。
", "ds_process_way": "该数据集利用Python仿真平台通过Wandb自动采集，每组数据都是在5个不同随机种子下训练结果的统计数值：包括最大值、最小值以及平均数。
", "ds_quality": "该数据集由系统自动采集完成，具有完整性和可分析性。通过分析训练曲线，我们可以验证以下结论：沙普利分红较沙普利值而言，更加速合作进化过程，并取得更优的合作效果。
", "ds_acq_start_time": "2025-01-01 00:00:00", "ds_acq_end_time": null, "ds_acq_place": "南京", "ds_acq_lon_east": null, "ds_acq_lat_south": null, "ds_acq_lon_west": null, "ds_acq_lat_north": null, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "open-access", "ds_total_size": 58938, "ds_files_count": 0, "ds_format": ".csv", "ds_space_res": "", "ds_time_res": "", "ds_coordinate": "无", "ds_projection": "", "ds_thumbnail": "e7ac428b-1269-4651-a511-4317dcdd9cea.png", "ds_thumb_from": 0, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "", "ds_from_station": "", "organization_id": "9ecaaa78-39e9-411e-9f24-274e12aa643f", "ds_serv_man": "王和", "ds_serv_phone": "15105193069", "ds_serv_mail": "wanghe91@seu.edu.cn", "doi_value": "", "subject_codes": [ "410" ], "quality_level": 0, "publish_time": "2026-07-09 10:58:51", "last_updated": "2026-07-09 10:58:51", "protected": false, "protected_to": "2028-06-30 00:00:00", "lang": "zh", "cstr": "", "i18n": { "en": { "title": "Performance Comparison Dataset of Shapley Dividend and Shapley Value in Particle Navigation Tasks", "ds_format": ".csv", "ds_source": "This dataset is completely synthetically generated through simulation and does not originate from specific literature, field measurements, or third-party downloads.", "ds_quality": "This dataset was automatically collected by the system, ensuring completeness and analytical viability. By analyzing the training curves, we can verify the following conclusion: compared with the Shapley value, the Shapley dividend more effectively accelerates the cooperative evolution process and achieves superior cooperative performance.", "ds_ref_way": "", "ds_abstract": "This dataset was constructed in June 2025 using a Python simulation platform and the MPE (Multi-Agent Particle Environment) navigation task framework, with automated data collection facilitated by Wandb. It is designed to compare the performance differences between two credit assignment mechanisms—Shapley Dividend and the conventional Shapley Value—when embedded into multi-agent reinforcement learning algorithms (SD3PG and SQDDPG). All experiments were conducted under identical network architectures and hyperparameter configurations. For each set of conditions, data were collected across five distinct random seeds, recording the per-episode average reward and collision count during training. Summary statistics, including maximum, minimum, and mean values, were computed to comprehensively reflect the expected performance, optimal bounds, and robustness of the algorithms. The dataset comprises two CSV table files, namely mean_end_reward.csv and mean_ep_collisions.csv, along with additional visualization and derivative metric files, such as training reward curves, collision trend plots, and convergence speed analysis tables. By comparing convergence speed, peak final rewards, and fluctuation ranges across training curves, it can be verified that Shapley Dividend, relative to Shapley Value, more effectively guides agents to form cooperative strategies in navigation tasks. It not only accelerates the evolution of cooperative behavior and reduces collision frequency, but also achieves superior and more stable final collaborative performance. This dataset provides reusable benchmark data and analytical foundations for research on credit assignment mechanisms in multi-agent systems.", "ds_time_res": "", "ds_acq_place": "Nanjing", "ds_space_res": "", "ds_projection": "", "ds_process_way": "This dataset was automatically collected via Wandb using a Python simulation platform. Each set of data comprises statistical summaries from training runs under five different random seeds, including maximum, minimum, and mean values.", "ds_ref_instruction": "" } }, "submit_center_id": "ncdc", "data_level": 0, "recommendation_value": 0, "license_type": "https://creativecommons.org/licenses/by/4.0/", "doi_reg_from": "reg_local", "cstr_reg_from": "reg_local", "doi_not_reg_reason": null, "cstr_not_reg_reason": null, "is_paper_in_submitting": false, "belong_to_nieer": false, "ds_topic_tags": [ "强化学习", "合作博弈", "沙普利值" ], "ds_subject_tags": [ "工程与技术科学基础学科" ], "ds_class_tags": [], "ds_locus_tags": [], "ds_time_tags": [], "ds_contributors": [ { "true_name": "何继超", "email": "jichaohe@seu.edu.cn", "work_for": "东南大学网络空间安全学院", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "何继超", "email": "jichaohe@seu.edu.cn", "work_for": "东南大学网络空间安全学院", "country": "中国" } ], "ds_managers": [ { "true_name": "王和", "email": "wanghe91@seu.edu.cn", "work_for": "东南大学", "country": "中国" } ], "category": "其他" }