Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration
Chao Yu (Tsinghua University), Xinyi Yang (Tsinghua University), Jiaxuan Gao (Tsinghua University), Jiayu Chen (Tsinghua University), Yunfei Li (Tsinghua University), Jijia Liu (Tongji University), Yunfei Xiang (Tsinghua University), Ruixin Huang (Tsinghua University), Huazhong Yang (Tsinghua University), Yi Wu (Tsinghua University & Shanghai Qi Zhi Institute), Yu Wang (Tsinghua University)
Abstract
We consider the problem of cooperative exploration where multiple robots need to cooperatively explore an unknown region as fast as possible. Multi-agent reinforcement learning (MARL) has recently become a trending paradigm for solving this challenge.
