Classical Planning
Describe actions by what they change and a solver can read the description itself: the same schemas that define the problem also generate the heuristics that solve it, which is something no black-box search can offer.
Sign in to take quizzes, earn XP, and unlock stages as you reach 90% mastery.
Representing Actions with PDDL
25 min · 100 XPStates as sets of ground positive fluents under the closed-world assumption, actions as lifted schemas with an add list and a delete list, and the frame problem sidestepped by mentioning only what changes.
Open lesson →Sign in to take the 3-question quiz.
Planning as State-Space Search
25 min · 100 XPProgression from the initial state and regression from the goal, the branching factor that grounding produces, and why the winning combination turned out to be the naive direction with a good heuristic.
Open lesson →Sign in to take the 3-question quiz.
Relaxations and the Planning Graph
30 min · 120 XPTwo heuristics obtained by editing the action schemas, then a layered graph with mutual-exclusion links that yields three more heuristics and settles which of them may be trusted to underestimate.
Open lesson →Sign in to take the 3-question quiz.