公开(公告)号：US20200250493A1

公开(公告)日：2020-08-06

申请号：US16749658

申请日：2020-01-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Riley SIMMONS-EDLER ,  Ben EISNER ,  Eric MITCHELL ,  Daniel Dongyuel LEE ,  Sebastian SEUNG

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06N5/04

Abstract: An apparatus for performing continuous actions includes a memory storing instructions, and a processor configured to execute the instructions to obtain a first action of an agent, based on a current state of the agent, using a cross-entropy guided policy (CGP) neural network, and control to perform the obtained first action. The CGP neural network is trained using a cross-entropy method (CEM) policy neural network for obtaining a second action of the agent based on an input state of the agent, and the CEM policy neural network is trained using a CEM and trained separately from the training of the CGP neural network.