Learning Individually Inferred Communication for Multi-Agent Cooperation

Authors: Ziluo Ding, Tiejun Huang, Zongqing Lu

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate I2C in three multi-agent cooperative tasks: cooperative navigation, predator prey, and traffic junction. For cooperative navigation and predator prey, I2C is built on MADDPG [10] to learn agent-agent communication. For traffic junction [19], our main purpose is to investigate the effectiveness of I2C on communication reduction, and thus we built I2C directly on Tar MAC [1] and it serves as communication control. In the experiments, I2C and baselines are parameter-sharing.
Researcher Affiliation Academia Ziluo Ding Tiejun Huang Zongqing Lu Peking University {ziluo,tjhuang,zongqing.lu}@pku.edu.cn
Pseudocode No The paper provides mathematical formulations for loss functions and gradients but does not include any structured pseudocode or algorithm blocks (e.g., a figure or section labeled 'Algorithm').
Open Source Code No The paper does not provide any concrete access to source code, nor does it explicitly state that code will be released or is available.
Open Datasets No The paper uses standard multi-agent cooperative tasks (cooperative navigation, predator prey, traffic junction) which are simulation environments rather than discrete datasets. It does not provide specific links, DOIs, repository names, or formal citations with author/year for accessing the exact data used in their simulations.
Dataset Splits No The paper mentions 'three training runs' but does not provide specific dataset split information (exact percentages, sample counts, or citations to predefined splits) for training, validation, or test sets.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., Python, PyTorch, TensorFlow versions, or specific library versions) needed to replicate the experiment.
Experiment Setup No The paper mentions that hyperparameters are detailed in supplementary materials: 'Please refer to the supplementary for the hyperparameter settings.' Therefore, specific experimental setup details are not provided in the main text.