T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration

Authors: Chuxiong Sun, Zehua Zang, Jiabao Li, Jiangmeng Li, Xiao Xu, Rui Wang, Changwen Zheng

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate our method on a diverse set of cooperative multi-agent tasks, with varying difficulties, involving different scales and ranging from Hallway, MPE to SMAC. The experiments indicate that the proposed model not only surpasses the stateof-the-art methods in terms of cooperative performance and communication efficiency, but also exhibits impressive generalization.
Researcher Affiliation Academia 1Science & Technology on Integrated Information System Laboratory, Institute of Software Chinese Academy of Sciences 2State Key Laboratory of Intelligent Game 3University of Chinese Academy of Sciences 4School of Automation and Electrical Engineering, University of Science and Technology Beijing
Pseudocode Yes Algorithm 1: T2MAC
Open Source Code No The paper does not explicitly state that open-source code for the methodology is provided, nor does it include a link to a code repository.
Open Datasets Yes We subjected T2MAC to rigorous testing across various MARL environments, such as Hallway, MPE, and SMAC.
Dataset Splits No The paper does not provide specific details on training, validation, and test dataset splits in terms of percentages, sample counts, or explicit splitting methodology.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library names with version numbers.
Experiment Setup Yes To ensure transparency and reproducibility, the intricate details of our method s architecture and our hyperparameter choices are extensively detailed in Table 1. Module Architecture: Obs Encoder Linear(obs dim, 64) Linear(64, 64) Linear(64, 64) RNN(64, 64) Evidence Encoder n*Linear(64, K) Selector Network Linear(64, n)