Abstract: A computer accesses a dataset for computing an action including multiple decision items and a configuration for a directed acyclic graph (DAG) comprising nodes representing dimensions. Each dimension is associated with a decision item of the action. The computer computes a value for a first decision item associated with a top level dimension of the DAG based on the dataset and using a reinforcement learning agent for the top level dimension. The computer computes a value for a second decision item associated with a non-top level dimension from the DAG based on the dataset and a specified subset of outputs of reinforcement learning engines for dimensions upstream from the non-top level dimension in the DAG and using a reinforcement learning agent for the non-top level dimension. The computer provides the computed action including the value for the first decision item and the value for the second decision item.

Abstract: A computing machine receives a request for an action by a meta-agent at the computing machine. The computing machine selects, using the meta-agent, an agent for determining an action responsive to the request. The agent is selected from a plurality of reinforcement learning agents. The agent is selected based on values in a dataset associated with the request. At least a portion of the dataset has predefined value types. The meta-agent and each agent from the plurality of reinforcement learning agents is trained using datasets including the predefined value types. The computing machine transmits, to the selected agent, the request for the action to cause the agent to compute the action.

Abstract: Methods and systems of using reinforcement learning for promotions. A first promotion is offered to a customer for a product and/or service. A first reward or penalty is determined, via a reinforcement machine learning model, based on the customer's reaction to the first promotion, wherein the reinforcement machine learning model is at a first state. Feedback to the reinforcement machine learning model is provided based on the first reward or penalty. A state of the reinforcement machine learning model is changed, based on the feedback, from the first state to a second state.

Abstract: Methods and systems for using reinforcement learning to optimizing promotions. A promotion for a product and/or service is offered to a customer using a reinforcement learning model. The customer's reaction is observed. A reward or a penalty is collected based on the customer's reaction. The reinforcement learning model is adapted based on the reward or penalty.