I2Q: A Fully Decentralized Q-Learning Algorithm

Authors: Jiechuan Jiang, Zongqing Lu

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

Reproducibility Variable Result LLM Response
Research Type Experimental Empirically, we show that I2Q can achieve remarkable improvement in a variety of cooperative multi-agent tasks.
Researcher Affiliation Academia Jiechuan Jiang School of Computer Science Peking University jiechuan.jiang@pku.edu.cn Zongqing Lu School of Computer Science Peking University zongqing.lu@pku.edu.cn
Pseudocode Yes Algorithm 1. I2Q for each agent i
Open Source Code Yes 3. If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Yes]
Open Datasets Yes Multi-Agent Mu Jo Co [18]
Dataset Splits No The main paper text states 'More details about hyperparameters are available in Appendix C.' but does not explicitly provide training/validation/test dataset splits within the provided text.
Hardware Specification No The main paper text states 'We include the details of computation in Appendix C.' but does not explicitly provide specific hardware details such as GPU models or processor types within the provided text.
Software Dependencies No The paper mentions 'We adopt the implementation of Py MARL [23]' but does not provide specific version numbers for software dependencies or libraries.
Experiment Setup Yes More details about hyperparameters are available in Appendix C.