公开(公告)号：US20210325894A1

公开(公告)日：2021-10-21

申请号：US17275459

申请日：2019-09-13

Applicant: Google LLC

Inventor： Aleksandra Faust ,  Hao-tien Chiang ,  Anthony Francis ,  Marek Fiser

IPC: G05D1/02 ,  G06N3/08 ,  G06N3/04

Abstract: Using reinforcement learning to train a policy network that can be utilized, for example, by a robot in performing robot navigation and/or other robotic tasks. Various implementations relate to techniques for automatically learning a reward function for training of a policy network through reinforcement learning, and automatically learning a neural network architecture for the policy network.