English

CH-MARL: A Multimodal Benchmark for Cooperative, Heterogeneous Multi-Agent Reinforcement Learning

Artificial Intelligence 2022-08-30 v1 Computer Vision and Pattern Recognition Machine Learning Multiagent Systems Robotics

Abstract

We propose a multimodal (vision-and-language) benchmark for cooperative and heterogeneous multi-agent learning. We introduce a benchmark multimodal dataset with tasks involving collaboration between multiple simulated heterogeneous robots in a rich multi-room home environment. We provide an integrated learning framework, multimodal implementations of state-of-the-art multi-agent reinforcement learning techniques, and a consistent evaluation protocol. Our experiments investigate the impact of different modalities on multi-agent learning performance. We also introduce a simple message passing method between agents. The results suggest that multimodality introduces unique challenges for cooperative multi-agent learning and there is significant room for advancing multi-agent reinforcement learning methods in such settings.

Keywords

Cite

@article{arxiv.2208.13626,
  title  = {CH-MARL: A Multimodal Benchmark for Cooperative, Heterogeneous Multi-Agent Reinforcement Learning},
  author = {Vasu Sharma and Prasoon Goyal and Kaixiang Lin and Govind Thattai and Qiaozi Gao and Gaurav S. Sukhatme},
  journal= {arXiv preprint arXiv:2208.13626},
  year   = {2022}
}
R2 v1 2026-06-25T02:03:29.145Z