52 citations · 57 across the 5 of their papers we have counts for
5 papers
Robust Visual Imitation Learning with Inverse Dynamics Representations
Siyuan Li, Xun Wang, Rongchang Zuo +5
Imitation learning (IL) has achieved considerable success in solving complex sequential decision-making problems. However, current IL methods mainly assume that the environment for…
UNMAS: Multi-Agent Reinforcement Learning for Unshaped Cooperative Scenarios
Jiajun Chai, Weifan Li, Yuanheng Zhu +4
Multi-agent reinforcement learning methods such as VDN, QMIX, and QTRAN that adopt centralized training with decentralized execution (CTDE) framework have shown promising results i…
Density-based Curriculum for Multi-goal Reinforcement Learning with Sparse Rewards
Deyu Yang, Hanbo Zhang, Xuguang Lan +1
Multi-goal reinforcement learning (RL) aims to qualify the agent to accomplish multi-goal tasks, which is of great importance in learning scalable robotic manipulation skills. Howe…
MBDF-Net: Multi-Branch Deep Fusion Network for 3D Object Detection
Xun Tan, Xingyu Chen, Guowei Zhang +2
Point clouds and images could provide complementary information when representing 3D objects. Fusing the two kinds of data usually helps to improve the detection results. However,…
REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter
Hanbo Zhang, Deyu Yang, Han Wang +4
Despite the impressive progress achieved in robotic grasping, robots are not skilled in sophisticated tasks (e.g. search and grasp a specified target in clutter). Such tasks involv…