Graph-based Reinforcement Learning Meets Mixed Integer Programs: an Application to 3D Robot Assembly Discovery
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)（2022）
关键词
block-type selection,desired assembly commands,feasible levels,flexible graph-based representation,graph-based reinforcement learning,mixed integer programs,mixed-integer program,motion planning,predefined set,predefined target structures,Q-learning,resource allocation,RL policy,robot assembly discovery,robot joint movements,robot-in-the-loop,robotic feasibility,robotic manipulator,task execution,Tetris-like building blocks,underlying reinforcement learning policy
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要