Credit Assignment and Fine-Tuning Enhanced Reinforcement Learning for Collaborative Spatial Crowdsourcing

Chen, Wei; Li, Yafei; Mei, Baolong; Zhu, Guanglei; Wu, Jiaqi; Xu, Mingliang

doi:10.24963/ijcai.2025/459

Credit Assignment and Fine-Tuning Enhanced Reinforcement Learning for Collaborative Spatial Crowdsourcing

Wei Chen, Yafei Li, Baolong Mei, Guanglei Zhu, Jiaqi Wu, Mingliang Xu

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 4119-4127.

https://doi.org/10.24963/ijcai.2025/459

Keywords

Humans and AI: HAI: Applications
Agent-based and Multi-agent Systems: MAS: Applications
Humans and AI: HAI: Human computation and crowdsourcing

Abstract

Collaborative spatial crowdsourcing leverages distributed workers' collective intelligence to accomplish spatial tasks. A central challenge is to efficiently assign suitable workers to collaborate on these tasks. Although mainstream reinforcement learning (RL) methods have proven effective in task allocation, they face two key obstacles: delayed reward feedback and non-stationary data distributions, both hindering optimal allocation and collaborative efficiency. To address these limitations, we propose CAFE (credit assignment and fine-tuning enhanced), a novel multi-agent RL framework for spatial crowdsourcing. CAFE introduces a credit assignment mechanism that distributes rewards based on workers' contributions and spatiotemporal constraints, coupled with bi-level meta-optimization to jointly optimize credit assignment and RL policy. To handle non-stationary spatial task distributions, CAFE employs an adaptive fine-tuning procedure that efficiently adjusts credit assignment parameters while preserving collaborative knowledge. Experiments on two real-world datasets validate the effectiveness of our framework, demonstrating superior performance in terms of task completion and equitable reward redistribution.

Wei Chen, Yafei Li, Baolong Mei, Guanglei Zhu, Jiaqi Wu, and Mingliang Xu. 2025. Credit Assignment and Fine-Tuning Enhanced Reinforcement Learning for Collaborative Spatial Crowdsourcing. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 4119–4127. https://doi.org/10.24963/ijcai.2025/459

@inproceedings{ijcai2025p459,
  title     = {Credit Assignment and Fine-Tuning Enhanced Reinforcement Learning for Collaborative Spatial Crowdsourcing},
  author    = {Chen, Wei and Li, Yafei and Mei, Baolong and Zhu, Guanglei and Wu, Jiaqi and Xu, Mingliang},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {4119--4127},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/459},
  url       = {https://doi.org/10.24963/ijcai.2025/459},
}

TY  - CPAPER
TI  - Credit Assignment and Fine-Tuning Enhanced Reinforcement Learning for Collaborative Spatial Crowdsourcing
AU  - Chen, Wei
AU  - Li, Yafei
AU  - Mei, Baolong
AU  - Zhu, Guanglei
AU  - Wu, Jiaqi
AU  - Xu, Mingliang
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 4119
EP  - 4127
DO  - 10.24963/ijcai.2025/459
UR  - https://doi.org/10.24963/ijcai.2025/459
ER  -