MA2CL:Masked Attentive Contrastive Learning for Multi-Agent Reinforcement Learning

Authors: Haolin Song, Mingxiao Feng, Wengang Zhou, Houqiang Li

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments demonstrate that our method significantly improves the performance and sample efficiency of different MARL algorithms and outperforms other methods in various vision-based and state-based scenarios.
Researcher Affiliation Academia 1EEIS Department, University of Science and Technology of China 2Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China {hlsong, fmxustc}@mail.ustc.edu.cn, {zhwg, lihq}@ustc.edu.cn,
Pseudocode Yes Algorithm 1 Training Process for MA2CL
Open Source Code No The paper does not provide any statement or link regarding the public availability of its source code.
Open Datasets Yes In the MAQC environment, each agent receives an RGB video frame R64 48 4 as an observation, which is captured from a camera fixed on the drone. MAQC allows for continuous action settings of varying difficulty, including RPM and PID. ... We use a variety of state-based MARL scenarios, such as the Star Craft Multi-Agent Challenge (SMAC) [Samvelyan et al., 2019] and Multi-Agent Mu Jo Co [de Witt et al., 2020]...
Dataset Splits No The paper mentions using well-known benchmark datasets but does not explicitly provide the specific training, validation, or test dataset splits it used for its experiments. While these benchmarks typically have standard splits, the paper does not describe them directly.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU models, CPU types, memory) used for running the experiments.
Software Dependencies No The paper does not provide specific version numbers for any ancillary software dependencies (e.g., programming languages, libraries, frameworks).
Experiment Setup Yes We set mask agent number Nm = 1, attention layer L = 1. Other hyperparameters settings can be found in supplementary materials.