Multi-Agent Incentive Communication via Decentralized Teammate Modeling
Authors: Lei Yuan, Jianhao Wang, Fuxiang Zhang, Chenghe Wang, ZongZhang Zhang, Yang Yu, Chongjie Zhang9466-9474
AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Empirical results demonstrate that our method significantly outperforms baselines and achieves excellent performance on multiple cooperative MARL tasks. We extensively evaluate MAIC on diverse MARL benchmarks, including level-based foraging (Papoudakis et al. 2021), Hallway (Wang et al. 2020d), and Star Craft Multi-Agent Challenge (SMAC) (Samvelyan et al. 2019). |
| Researcher Affiliation | Collaboration | 1National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China 2Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing 100084, China 3Polixir Technologies, Nanjing 210000, China 4Peng Cheng Laboratory, Shenzhen 518055, China |
| Pseudocode | No | The paper does not contain any pseudocode or algorithm blocks. The method is described textually and through diagrams. |
| Open Source Code | Yes | Code available at https://github.com/mansicer/MAIC |
| Open Datasets | Yes | We extensively evaluate MAIC on diverse MARL benchmarks, including level-based foraging (Papoudakis et al. 2021), Hallway (Wang et al. 2020d), and Star Craft Multi-Agent Challenge (SMAC) (Samvelyan et al. 2019). |
| Dataset Splits | No | The paper uses various benchmarks and mentions 'average performance and 25 75% deviation over five random seeds' for its evaluations. However, it does not specify explicit training, validation, or test dataset splits (e.g., percentages or sample counts) for the datasets/environments used. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., GPU model, CPU model, memory, or cloud instance types) used for running the experiments. |
| Software Dependencies | Yes | All hyperparameters for training and in-game AI are the same as Py MARL2 on Star Craft 2.4.6. |
| Experiment Setup | No | The paper states, 'All hyperparameters for training and in-game AI are the same as Py MARL2 on Star Craft 2.4.6.' This defers the details of the experimental setup and hyperparameters to an external source (PyMARL), rather than explicitly listing them within the paper itself. |