RALPH-MEA may only work in domains where the Markov assumption holds: that all relevent information about a system be discernable from the present state. I.e. there is no hidden, history-dependent information in the environment that cannot be derived from present sensor values and that can impact the execution of RALPH-MEA's plans.
This is an important simplifying assumption which reduces the complexity of planning sequences of actions. It allows the influence diagrams to remove states once they have left a specified time window because it is assumed that the state no longer has any effect on the current state.
Recent work by the RALPH developers has addressed this methodological assumption by making a distinction between perceived state and actual state. The actual state does contain all relevant information, but the perceived state may not be complete because of sensor errors (or the lack of a sensor to perceive certain information). Therefore, the actual state by definition obeys the Markov assumption, but the perceived state may not. The developers model sensor errors with a joint probabilistic network, which maintains a representation of the joint distribution over world states. This allows RALPH to probabilistically react to the actual state notwithstanding sensor errors.