This work explores the large-scale multi-agent communication mechanism for multi-agent reinforcement learning (MARL). We summarize the general topology categories for …
We study the problem of inferring communication structures that can solve cooperative multi- agent planning problems while minimizing the amount of communication. We quantify the …
S Xie, H Zhang, H Yu, Y Li, Z Zhang, X Luo - Knowledge-Based Systems, 2022 - Elsevier
Many real-world multi-agent systems require agents to cooperate with each other. However, it is challenging to generate optimal cooperative strategies (eg, location coordination or …
J Jiang, Z Lu - International Conference on Machine …, 2021 - proceedings.mlr.press
Individuality is essential in human society. It induces the division of labor and thus improves the efficiency and productivity. Similarly, it should also be a key to multi-agent cooperation …
J Wang, M Yuan, Y Li, Z Zhao - Neural Networks, 2023 - Elsevier
Most multi-agent reinforcement learning (MARL) approaches optimize strategy by improving itself, while ignoring the limitations of homogeneous agents that may have single function …
J Wang, Y Zeng, Y Gong - IEEE Transactions on Intelligent …, 2023 - ieeexplore.ieee.org
3D object detection from LiDAR point cloud is a challenging task in autonomous driving systems. Collaborative perception can incorporate information from spatially diverse sensors …
X Liu, D Guo, H Liu, F Sun - IEEE Robotics and Automation …, 2022 - ieeexplore.ieee.org
In visual semantic navigation, the robot navigates to a target object with egocentric visual observations and the class label of the target is given. It is a meaningful task inspiring a …
Y Zhai, B Ding, X Liu, H Jia, Y Zhao… - IEEE Robotics and …, 2021 - ieeexplore.ieee.org
Deep reinforcement learning has been demonstrated to be an effective solution to the multi- robot collision avoidance problem. However, with existing methods, robots typically …