公开(公告)号：US11188821B1

公开(公告)日：2021-11-30

申请号：US15705601

申请日：2017-09-15

Applicant: X Development LLC

Inventor： Mrinal Kalakrishnan ,  Ali Hamid Yahya Valdovinos ,  Adrian Ling Hin Li ,  Yevgen Chebotar ,  Sergey Vladimir Levine

IPC: G06N3/08 ,  G06N20/00 ,  B25J9/16

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, of training a global policy neural network. One of the methods includes initializing an instance of the robotic task for multiple local workers, generating a trajectory of state-action pairs by selecting actions to be performed by the robotic agent while performing the instance of the robotic task, optimizing a local policy controller on the trajectory, generating an optimized trajectory using the optimized local controller, and storing the optimized trajectory in a replay memory associated with the local worker. The method includes sampling, for multiple global workers, an optimized trajectory from one of one or more replay memories associated with the global worker, and training the replica of the global policy neural network maintained by the global worker on the sampled optimized trajectory to determine delta values for the parameters of the global policy neural network.

公开(公告)号：US10960539B1

公开(公告)日：2021-03-30

申请号：US15705655

申请日：2017-09-15

Applicant: X Development LLC

Inventor： Mrinal Kalakrishnan ,  Ali Hamid Yahya Valdovinos ,  Adrian Ling Hin Li ,  Yevgen Chebotar ,  Sergey Vladimir Levine

IPC: B25J9/16 ,  G05B13/02

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, of training a global policy neural network. One of the methods includes initializing a plurality of instances of the robotic task. For each instance of the robotic task, the method includes generating a trajectory of state-action pairs by selecting actions to be performed by the robotic agent while performing the instance of the robotic task in accordance with current values of the parameters of the global policy neural network, and optimizing a local policy controller that is specific to the instance on the trajectory of state-action pairs for the instance. The method further includes generating training data for the global policy neural network using the local policy controllers, and training the global policy neural network on the training data to adjust the current values of the parameters of the global policy neural network.