Peer-reviewed publications

Reputation-Filtered Reward Reshaping: Encouraging Cooperation in High-Dimensional Semi-Cooperative Multi-agent Settings

Hassan Raissouni, Wissal Bekhti, Btissam El Khamlichi, Amal El Fallah Seghrouchni

AAMAS 2025 Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, Detroit, MI, USA · IFAAMAS · pp. 1736–1744

In semi-cooperative settings, agents share an environment but pursue individual objectives, and differences in competence can cause cooperation to break down. This work introduces a reputation mechanism together with filtered reward-shaping functions that align agents' individual incentives with a common objective in high-dimensional environments, and compares the approach against baselines including IQL, Partial Q-MIX, and PED-DQN.

@inproceedings{raissouni2025reputation,
  author    = {Raissouni, Hassan and Bekhti, Wissal and
               El Khamlichi, Btissam and El Fallah Seghrouchni, Amal},
  title     = {Reputation-Filtered Reward Reshaping: Encouraging Cooperation
               in High-Dimensional Semi-Cooperative Multi-agent Settings},
  booktitle = {Proceedings of the 24th International Conference on Autonomous
               Agents and Multiagent Systems (AAMAS 2025)},
  year      = {2025},
  pages     = {1736--1744},
  address   = {Detroit, Michigan, USA},
  publisher = {International Foundation for Autonomous Agents and
               Multiagent Systems (IFAAMAS)}
}