Data processing method based on reinforcement learning, electronic device and readable medium

By constructing execution nodes, policy nodes, and training nodes, the environment simulation-policy update process is decoupled, achieving efficient scheduling of computer hardware resources. This solves the problem that small and medium-sized resources cannot support complex tasks, and improves training speed and resource utilization efficiency.

CN116776097BActive Publication Date: 2026-04-28SHANGHAI QI ZHI INSTITUTE
2 Cites 0 Cited by

Patent Information

Application Number
CN202310658042.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-06-05
Publication Date
2026-04-28
Estimated Expiration
2043-06-05

AI Technical Summary

Technical Problem

Small- to medium-sized computer hardware resources are insufficient to effectively support complex reinforcement learning tasks. Existing reinforcement learning systems lack the support of large-scale distributed computer hardware resources, resulting in slow training speed and low resource utilization efficiency.

Method used

By constructing execution nodes, policy nodes, and training nodes, environment simulation, policy inference, and policy update are realized respectively. Data transmission is carried out using sample transport streams and inference transport streams, decoupling the environment simulation-policy update process and achieving efficient scheduling of computer hardware resources.

Benefits of technology

It improves the support of computer hardware resources for complex reinforcement learning tasks, meets the needs of efficient and high-speed training, and realizes effective scheduling and good scalability of large-scale computer hardware resources.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

Embodiments of the present disclosure disclose a data processing method based on reinforcement learning, an electronic device and a readable medium. The method is applied to an execution node, a policy node and a training node included in a reinforcement learning system, and a specific implementation of the method comprises: performing environment simulation by the execution node to obtain an observation result; performing policy updating by the training node according to a training sample and a model to be trained, wherein the training sample is transmitted from the execution node to the training node through a sample transmission stream; the policy node performs policy inference according to the observation result and updated policy information, wherein in a non-in-line inference mode, the execution node and the policy node perform data transmission on the observation result and an action to be executed through an inference transmission stream; and the execution node executes the action to be executed to generate an updated observation result. The implementation realizes effective scheduling of large-scale computer hardware resources, meets the training requirements for complex reinforcement learning tasks, and improves the training speed.
Need to check novelty before this filing date? Find Prior Art