System reinforcement learning method and apparatus, and computer storage medium
AssigneeShanghai Sensetime Intelligent Technology Co., Ltd.
InventorsShuqin XIE, Zitian CHEN, Chao XU, Cewu LU
Life of this patent
Estimating the term…
Abstract
A system reinforcement learning method includes: processing an input image based on a first network of a system to obtain a first result; inputting the first result to a second network of the system to obtain a second result; and obtaining a reinforcement operation based on the second result by means of a reinforcement network, and adjusting the first result based on the reinforcement operation to obtain a target result. According to the embodiments of the present disclosure, information is fed back from downstream to upstream by means of the reinforcement network, and an output result of the system is optimized.
Claims20
A system reinforcement learning method, comprising:
- processing an input image based on a first network of a system to obtain a first result;
- inputting the first result into a second network of the system to obtain a second result;
- and
- obtaining a reinforcement operation based on the second result by using a reinforcement network, adjusting the first result based on the reinforcement operation, and obtaining a target result based on the adjusted first result.
A system reinforcement learning apparatus, comprising:
- a processor;
- and
- a memory configured to store instructions executable by the processor,
- wherein the processor is configured to:
- process an input image to obtain a first result;
- process the first result to obtain a second result;
- obtain a reinforcement operation based on the second result;
- and
- adjust the first result based on the reinforcement operation and obtain a target result based on the adjusted first result.
A non-transitory computer storage medium, configured to store computer readable instructions, wherein the instructions, when being executed, implement a system reinforcement learning method, the method comprising:
- processing an input image based on a first network of a system to obtain a first result;
- inputting the first result into a second network of the system to obtain a second result;
- and
- obtaining a reinforcement operation based on the second result by using a reinforcement network, adjusting the first result based on the reinforcement operation, and obtaining a target result based on the adjusted first result.
Dependencies are inferred from the claim text.