Agent instantiation and calibration for multi-agent simulator platform

One or more computer-readable media having computer-executable instructions stored thereon that, when executed by at least one processor of a multi-agent simulator computing system, cause the multi-agent simulator computing system to perform computer-implemented operations for agent instantiation and calibration in a virtual world, the operations comprising:

• instantiating a set of agents using a set of input traits;
• executing a first simulation session by causing the set of agents to generate a first output set;
• detecting a change event in the virtual world;
• based on the change event, causing a trained model to generate an evolution operation recommendation;
• generating an evolved set of agents by performing one or more recommended evolution operations comprising at least one of mutation of agent traits, selection of agents, crossover of agent traits, or deletion of agents;
• persisting at least a portion of the first output set in a memory associated with the multi-agent simulator computing system;
• using the evolved set of agents, executing a second simulation session to generate a second output set;
• and
• displaying at least a portion of the persisted first output set and second output set at a graphical user interface associated with the multi-agent simulator computing system.

A multi-agent simulator computing system having at least one processor and at least one memory having computer-executable instructions stored thereon that, when executed by the at least one processor, cause the multi-agent simulator computing system to perform computer-implemented operations for agent instantiation and calibration in a virtual world, the operations comprising:

• instantiate a set of agents using a set of input traits;
• execute a first simulation session by causing the set of agents to generate a first output set;
• detect a change event in the virtual world;
• based on the change event, cause a trained model to generate an evolution operation recommendation;
• generate an evolved set of agents by performing one or more recommended evolution operations comprising at least one of mutation of agent traits, selection of agents, crossover of agent traits, or deletion of agents;
• persist at least a portion of the first output set in a memory associated with the multi-agent simulator computing system;
• using the evolved set of agents, execute a second simulation session to generate a second output set;
• and
• display at least a portion of the persisted first output set and second output set at a graphical user interface associated with the multi-agent simulator computing system.