Episodes - artificial intelligence:
If an agent's current choice of action not based on its past reactions, then the environment is known as episodic. In the non-episodic environments, the agent will have to plan ahead, because its current action will rear affect subsequent ones.
Considering only the goal of getting to and from exhibits, the individual trips can be seen between exhibits as episodes in RHINO's actions. When it had arrived to one exhibit, as how it got there would not normally too affect its choices in getting to the next exhibit. If we also think about the goal of giving a guided tour, however, RHINO at least must remember the exhibits it had already visited, in order to duplicate itself. So, at the high level, its actions were not episodic.