Abstract: A method includes defining, using a first neural network, and based on a plurality of inputs, a first state associated with (1) an entity and (2) a first node from a plurality of nodes included in a reinforcement learning model. The reinforcement learning model determines, based on a reward, (1) a second state associated with a second node and (2) an indication of an action associated with a transition from the first state to the second state. The method also includes generating, using a second neural network, an implementation of the action based on the first state, the second state, and the indication of the action. In response to the implementation of the action being transmitted to the entity, a success metric, determined based on an outcome of the implementation of the action, is received. A third state associated with the entity is determined based on the success metric.

Abstract: A method includes defining, using a first neural network, and based on a plurality of inputs, a first state associated with (1) an entity and (2) a first node from a plurality of nodes included in a reinforcement learning model. The reinforcement learning model determines, based on a reward, (1) a second state associated with a second node and (2) an indication of an action associated with a transition from the first state to the second state. The method also includes generating, using a second neural network, an implementation of the action based on the first state, the second state, and the indication of the action. In response to the implementation of the action being transmitted to the entity, a success metric, determined based on an outcome of the implementation of the action, is received. A third state associated with the entity is determined based on the success metric.