Is there a way to assign learning results to individual robots and run them simultaneously?


I am currently trying to do reinforcement learning for a robot modeled after an ant.
We are thinking of doing two types of reinforcement learning, one in which the robot goes for the food and the other in which it carries the food to the nest, and using them simultaneously.
We are trying to collect the results of reinforcement learning with one robot and one prey for each individual environment into one environment and run it with multiple robots at the same time.
However, I do not know how to assign the learning results to the robots within a single environment.
Do you have any references, helpful documents, or advice?

Thank you in advance.