公开(公告)号：US20190126472A1

公开(公告)日：2019-05-02

申请号：US16174112

申请日：2018-10-29

Applicant: DeepMind Technologies Limited

Inventor： Saran Tunyasuvunakool ,  Yuke Zhu ,  Joshua Merel ,  Janos Kramar ,  Ziyu Wang ,  Nicolas Manfred Otto Heess

IPC: B25J9/16 ,  G06N3/08

Abstract: A neural network control system for controlling an agent to perform a task in a real-world environment, operates based on both image data and proprioceptive data describing the configuration of the agent. The training of the control system includes both imitation learning, using datasets generated from previous performances of the task, and reinforcement learning, based on rewards calculated from control data output by the control system.

公开(公告)号：US20230330848A1

公开(公告)日：2023-10-19

申请号：US18306711

申请日：2023-04-25

Applicant: DeepMind Technologies Limited

Inventor： Saran Tunyasuvunakool ,  Yuke Zhu ,  Joshua Merel ,  János Kramár ,  Ziyu Wang ,  Nicolas Manfred Otto Heess

IPC: B25J9/16 ,  G06N3/08 ,  G06N3/008 ,  G06N3/084 ,  G06N3/044 ,  G06N3/045

CPC classification number: B25J9/163 ,  G06N3/08 ,  B25J9/161 ,  B25J9/1697 ,  G06N3/008 ,  G06N3/084 ,  G06N3/044 ,  G06N3/045

Abstract: A neural network control system for controlling an agent to perform a task in a real-world environment, operates based on both image data and proprioceptive data describing the configuration of the agent. The training of the control system includes both imitation learning, using datasets generated from previous performances of the task, and reinforcement learning, based on rewards calculated from control data output by the control system.