Data processing method and device, storage medium and electronic equipment
By employing a multi-threaded parallel data processing approach within a distributed reinforcement learning framework, and utilizing C++ modules and multiple CPU cores, the low data processing efficiency caused by the GIL limitation in the Python ecosystem is resolved, achieving more efficient data reception and processing.
CN116451814BActive Publication Date: 2026-07-21NETEASE (HANGZHOU) NETWORK CO LTD
View PDF 1 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NETEASE (HANGZHOU) NETWORK CO LTD
- Filing Date
- 2023-04-14
- Publication Date
- 2026-07-21
Smart Images
Figure CN116451814B_ABST
Abstract
The present disclosure provides a data processing method, a data processing device, a computer storage medium and an electronic device, and relates to the technical field of computers. The data processing method comprises: in response to receiving a data transmission instruction transmitted by an actor, starting a plurality of worker threads between a learner and the actor according to the data transmission instruction; receiving first target experience data transmitted by the actor according to the plurality of worker threads; wherein the first target experience data is determined according to first network parameters of a reinforcement learning model; updating the first network parameters of the reinforcement learning model to second network parameters corresponding to the first target experience data, so that the actor generates experience data corresponding to the second network parameters. The present disclosure can improve the efficiency of data receiving and processing.
Need to check novelty before this filing date? Find Prior Art