{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

lecture15

# lecture15 - Articial Intelligence Probabilities Nilsson...

This preview shows pages 1–9. Sign up to view the full content.

Probabilities; page 1 of 26 Artificial Intelligence Probabilities this starts our excursion into probabilistic knowledge representation and reasoning and probabilistic planning Russell and Norvig - Chapter 13 Nilsson - Chapter 19

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Probabilities; page 2 of 26 search and planning - so far start goal actions have deterministic effects states are completely observable a plan is a sequence of actions that can be executed blindly in the world
Probabilities; page 3 of 26 search and planning: robot navigation example (1) noisy actuators noisy sensors of limited range uncertainty in the interpretation of the sensor data map uncertainty uncertainty about the (initial) location of the robot uncertainty about the dynamic state of the environment

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Probabilities; page 4 of 26 search and planning: robot navigation example (2)
Probabilities; page 5 of 26 actions have nondeterministic effects states are not completely observable search and planning: more realistic framework need to distinguish between actions that achieve a task and actions that gather information plans are no longer sequences of actions and can no longer be executed blindly in the world

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Probabilities; page 6 of 26 probabilities - frequentist view - objectivist view - subjectivist view we need to learn more about probabilities
Probabilities; page 7 of 26 notation P(Var = value) the probability that (random) variable VAR takes on the given value P(STUDENTS = 38) = 0.93 P(propositional_sentence) the probability that the given propositional sentence is true P(happy) = 0.40 P(happy AND NOT hungry) = 0.39 (Note: P(A, B) means P(A AND B).)

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Probabilities; page 8 of 26 conditional probabilities P(happy | hungry) = 0.02 P(A AND B) = P(A) P(B | A) P(B | A) = P(A AND B) / P(A) happy 0.39 hungry 0.54 0.01
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}