发明者
Mrinal Kalakrishnan, Yunfei Bai, Paul Wohlhart, Eric Jang, Chelsea Finn, Seyed Mohammad Khansari Zadeh, Sergey Levine, Allan Zhou, Alexander Herzog, Daniel Kappler
发表日期
2022/4/7
专利局
US
专利申请号
17422260
简介
Techniques are disclosed that enable training a meta-learn ing model, for use in causing a robot to perform a task, using imitation learning as well as reinforcement learning. Some implementations relate to training the meta-learning model using imitation learning based on one or more human guided demonstrations of the task. Additional or alternative imple mentations relate to training the meta-learning model using reinforcement learning based on trials of the robot attempt ing to perform the task. Further implementations relate to using the trained meta-learning model to few shot (or one shot) learn a new task based on a human guided demonstra tion of the new task.
学术搜索中的文章
M Kalakrishnan, Y Bai, P Wohlhart, E Jang, C Finn… - US Patent App. 17/422,260, 2022