Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization

Authors: Jianhao Wang, Zhizhou Ren, Beining Han, Jianing Ye, Chongjie Zhang

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, to support our theoretical implications in practical realization, we conduct an empirical analysis of state-of-the-art deep multi-agent Q-learning algorithms on didactic examples and a broad set of Star Craft II unit micromanagement tasks.
Researcher Affiliation Academia Jianhao Wang1 , Zhizhou Ren2 , Beining Han1, Jianing Ye1, Chongjie Zhang1 1Institute for Interdisciplinary Information Sciences, Tsinghua University 2Department of Computer Science, University of Illinois at Urbana-Champaign
Pseudocode Yes Algorithm 1 Factorized Multi-Agent Fitted Q-Iteration (FMA-FQI)
Open Source Code No No explicit statement or link providing open-source code for the methodology described in this paper was found.
Open Datasets Yes We utilize Star Craft Multi-Agent Challenge (SMAC) benchmark [20]
Dataset Splits No The paper describes the collection of an offline dataset but does not explicitly provide training/validation/test dataset splits with specific percentages, counts, or a detailed splitting methodology for the models evaluated.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory) used for running experiments were mentioned.
Software Dependencies No No specific ancillary software details, such as library names with version numbers, were provided.
Experiment Setup No A detailed description of the experiment setting is deferred to Appendix E.