A learning control system is provided in each of a plurality of subsystems of a system and includes a plurality of agents that performs learning to control of the subsystem using a control model and a learning management agent that manages and controls learning of each of the plurality of agents. The learning management agent is operated with a plurality of experiment systems including the plurality of control model sets of the plurality of agents and determines a plurality of updating control model sets in the plurality of experiment systems of a next generation from an evaluation result of the plurality of experiment systems of the current generation. The agent transmits control model information of a current generation to the learning management agent and receives control model information of the next generation from the learning management agent.