ACE: Cooperative Multi-Agent Q-learning with Bidirectional Action-Dependency

Authors: Chuming Li, Jie Liu, Yinmin Zhang, Yuhong Wei, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical experiments demonstrate that ACE outperforms the state-of-the-art algorithms on Google Research Football and Star Craft Multi-Agent Challenge by a large margin.
Researcher Affiliation Collaboration Chuming Li1, 2*, Jie Liu2*, Yinmin Zhang1, 2*, Yuhong Wei3, Yazhe Niu2, 3, Yaodong Yang4 , Yu Liu2, 3 , Wanli Ouyang1, 2 1 The University of Sydney, Sense Time Computer Vision Group, Australia, 2 Shanghai Artificial Intelligence Laboratory, 3 Sense Time Group LTD, 4 Institute for AI, Peking University
Pseudocode No The paper describes its method in prose and diagrams (Figure 3), but does not contain a formal pseudocode or algorithm block.
Open Source Code No The paper does not provide any explicit statement about making the source code available or include a link to a code repository for its methodology.
Open Datasets Yes For complex tasks, we choose two benchmark scenarios in Google Research Football (GRF) 2020 environment and eight micromanagement tasks in Star Craft Multi-Agent Challenge (SMAC) 2019. The Spiders-and-Fly problem is first proposed in 2019.
Dataset Splits No The paper describes evaluation procedures like running '32 test episodes' and using '5 seeds', but it does not specify explicit training/test/validation dataset splits (e.g., percentages or sample counts) for reproducibility, as the data is generated through interaction with environments rather than from a static dataset.
Hardware Specification No The paper does not provide any specific hardware details such as GPU/CPU models, memory amounts, or detailed computer specifications used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiment.
Experiment Setup No The paper describes the evaluation metrics and general experimental setup for benchmarks (e.g., '32 test episodes', '5 seeds'), but it does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) or detailed training configurations for its method ACE in the main text.