Scheduling method, scheduling system, and scheduling apparatus for calculating a current scheduling decision based on a previous reward feedback

A scheduling method, comprising:

• sending, by a terminal device, a first reward feedback in an ith time unit, wherein i≥1 and i is an integer;
• and
• receiving, by the terminal device in an (i+N)th time unit, a first scheduling decision from a first scheduler based on the first reward feedback, wherein the first reward feedback is determined by the terminal device based on a second scheduling decision, the second scheduling decision is a previous scheduling decision received from the first scheduler before the first scheduling decision, and N>1 and N is an integer,
• wherein the method further comprises:
• sending, by the terminal device, a second reward feedback in an (i+j)th time unit, wherein 1≤j≤N−1 and j is an integer;
• and
• receiving, by the terminal device in an (i+j+M)th time unit, a third scheduling decision from a second scheduler based the second reward feedback, wherein M>1 and M is an integer, wherein
• the second reward feedback is determined by the terminal device based on a fourth scheduling decision, and the fourth scheduling decision is a previous scheduling decision received from the second scheduler before the third scheduling decision;
• and
• the scheduling decision received from the first scheduler and the scheduling decision received from the second scheduler are respectively scheduling decisions of the first scheduler and the second scheduler for a same task.

An apparatus, comprising:

• a memory storing computer-readable instructions;
• and
• one or more processors connected to the memory, wherein the processor is configured to execute the computer-readable instructions to:
• send a first reward feedback in an ith time unit, wherein i≥1 and i is an integer;
• and
• receive in an (i+N)th time unit, a first scheduling decision from a first scheduler based on the first reward feedback, wherein the first reward feedback is based on a second scheduling decision, the second scheduling decision is a previous scheduling decision received before the first scheduling decision, and N>1 and N is an integer,
• wherein the one or more processors are further configured to:
• send a second reward feedback in an (i+j)th time unit, wherein 1≤j≤N−1 and j is an integer;
• and
• receive in an (i+j+M)th time unit, a third scheduling decision from a second scheduler based the second reward feedback, wherein M>1 and M is an integer, wherein
• the second reward feedback is based on a fourth scheduling decision, and the fourth scheduling decision is a previous scheduling decision received from the second scheduler before the third scheduling decision;
• and
• the fourth scheduling decision and the third scheduling decision are respectively scheduling decisions for a same task.