Efficient Multi-agent Communication via Self-supervised Information Aggregation

Authors: Cong Guan, Feng Chen, Lei Yuan, Chenghe Wang, Hao Yin, Zongzhang Zhang, Yang Yu

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results demonstrate that our method significantly outperforms strong baselines on multiple cooperative MARL tasks for various task settings.
Researcher Affiliation Collaboration Cong Guan1 , Feng Chen1 , Lei Yuan1,2, Chenghe Wang1, Hao Yin1, Zongzhang Zhang1, Yang Yu1,2 1 National Key Laboratory for Novel Software Technology, Nanjing University 2 Polixir Technologies
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes The codes are available at https://github.com/chenf-ai/MASIA
Open Datasets Yes To evaluate our method, we conduct extensive experiments on various cooperative multi-agent benchmarks, including Hallway [48], Level-Based Foraging [34], Traffic Junction [4], and two maps from Star Craft Multi-Agent Challenge (SMAC) [48].
Dataset Splits No The paper evaluates on benchmarks and reports "Median Test Win Rate %", implying a test set, but does not explicitly detail training, validation, and test dataset splits (e.g., specific percentages or sample counts).
Hardware Specification No The paper states that hardware specifications are presented in Appendix A.3, but this appendix is not provided in the given text. The main body of the paper does not specify the exact hardware used (e.g., specific GPU models, CPU models, or cloud instances).
Software Dependencies Yes Our experiments are all based on the Py MARL framework, which uses SC2.4.6.2.6923.
Experiment Setup Yes Details about benchmarks, network architecture and hyper-parameter choices of our method are all presented in Appendices A.1, and A.3, respectively.