A diagram of RALPH-MEA.
An agent is defined to be a function f : P* --> D, where P* is the set of all perceptions available from the environment and D is the set of possible action decisions, either internal or external. The method of choosing the best action depends on the type of knowledge available. The multiple knowledge types define four different paths from perception to action, called Execution Architectures:
Each Execution Architecture runs in parallel, and the arbitrator chooses which action to take, based on environmental constraints. A diagram of the reasoning process is available.After generating an action, RALPH-MEA executes the action and monitors its results. If an error is detected, RALPH-MEA employs its replanning component.
RALPH's reasoning is guided by the Maximum Expected Utility (MEU) principle. This principle can be summarized as "Do the Right Thing". The equation for computing the ideal action is in the Methodology section. Each execution architecture produces its own plan according to its own knowledge types. In particular, the Action-Utility and the Decision-Theoretic architectures utilize an MEU function to evaluate the best actions given knowledge of current and future states.