OpenTechnical
This is a record of a document published elsewhere, first published by the United States Patent and Trademark Office, as US-2026070214-A1, on 12 March 2026. OpenTechnical did not first disclose it. The identifier, hashes and timestamps below record what this library served and when, not when the material became public. View the original.

OT-2026-000001947

Method and electronic device for training policy model based on reinforcement learning

Published
Permanent URL
Classification
Robotics & Automation › Robot Architectures
Inventors
FU YUWEI, XU WEI, ZHANG HAICHAO
Assignee
HORIZON ROBOTICS INC
Original source
US-2026070214-A1, the United States Patent and Trademark Office, 12 March 2026
Document SHA-256
9fa7f122b3da144e06310a59d693541ceef7aba48de689b19d716cb33298cbb5

Abstract

The embodiment of the present discloses a method for training a policy model based on reinforcement learning and apparatus, and an electronic device. The method includes: determining an observation data sequence generated by an agent during a time period of executing a target task, a preset time window, and an expert data sequence corresponding to the target task; determining a cost matrix and a transport matrix based on the preset time window, the observation data sequence, and the expert data sequence; determining a reward value for each observation data in the observation data sequence based on the cost matrix and the transport matrix; and training the policy model based on the observation data and the reward value of the observation data.

Publication information

Plain textMarkdownManifestIntegrity record

Citation

OpenTechnical Publication OT-2026-000001947, “Method and electronic device for training policy model based on reinforcement learning,” published September 15, 2026 at 19:09:41 UTC, https://opentechnical.org/p/OT-2026-000001947.

To cite specific content, add the paragraph or figure numbers.

Terms

This record reproduces a document published elsewhere and is provided for reference and study. Rights in the original remain with its owner. See the publication policy.