Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning

Authors: Shariq Iqbal, Christian A Schroeder De Witt, Bei Peng, Wendelin Boehmer, Shimon Whiteson, Fei Sha

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

Reproducibility Variable Result LLM Response
Research Type Experimental Our approach, Randomized Entity-wise Factorization for Imagined Learning (REFIL), outperforms all strong baselines by a significant margin in challenging multi-task Star Craft micromanagement settings. In our experiments, we aim to answer the following questions:
Researcher Affiliation Collaboration 1Department of Computer Science, University of Southern California 2Department of Computer Science, University of Oxford 3Department of Software Technology, Delft University of Technology 4Google Research.
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Code available at: https://github.com/shariqiqbal2810/REFIL
Open Datasets Yes We next test on the Star Craft multi-agent challenge (SMAC) (Samvelyan et al., 2019).
Dataset Splits No The paper references training and testing but does not provide specific details on validation splits or exact percentages for data partitioning.
Hardware Specification No The paper mentions an 'equipment grant from NVIDIA' but does not specify exact hardware details such as GPU/CPU models or memory used for experiments.
Software Dependencies No The paper does not provide specific version numbers for software dependencies or libraries used in the experiments.
Experiment Setup No The paper describes general model architecture and training procedures but does not explicitly provide concrete hyperparameter values or detailed system-level training settings in the main text.