Multi Agent Deep Reinforcement Learning
Multi-agent deep reinforcement learning (MADRL) focuses on training multiple AI agents to collaborate or compete within a shared environment, aiming to optimize collective performance through learning. Current research emphasizes developing efficient algorithms like MADDPG and variations of Q-learning, often incorporating transformer networks for improved feature representation and handling complex interactions, and exploring different training paradigms such as centralized training with decentralized execution. This field is significant for its potential to solve complex real-world problems across diverse domains, including autonomous driving, robotics, network optimization, and resource management, by enabling more robust and adaptable systems.
Papers
MASQ: Multi-Agent Reinforcement Learning for Single Quadruped Robot Locomotion
Qi Liu, Jingxiang Guo, Sixu Lin, Shuaikang Ma, Jinxuan Zhu, Yanjie Li
Multi-Agent Target Assignment and Path Finding for Intelligent Warehouse: A Cooperative Multi-Agent Deep Reinforcement Learning Perspective
Qi Liu, Jianqi Gao, Dongjie Zhu, Zhongjian Qiao, Pengbin Chen, Jingxiang Guo, Yanjie Li
An open source Multi-Agent Deep Reinforcement Learning Routing Simulator for satellite networks
Federico Lozano-Cuadra, Mathias D. Thorsager, Israel Leyva-Mayorga, Beatriz Soret
FedMRL: Data Heterogeneity Aware Federated Multi-agent Deep Reinforcement Learning for Medical Imaging
Pranab Sahoo, Ashutosh Tripathi, Sriparna Saha, Samrat Mondal