navigation
hledat
Rozdíly
Zde můžete vidět rozdíly mezi vybranou verzí a aktuální verzí dané stránky.
|
courses:b4m36smu [2018/06/06 17:54] rozumden [Zkouška] |
courses:b4m36smu [2025/01/03 18:23] (aktuální) |
||
|---|---|---|---|
| Řádek 12: | Řádek 12: | ||
| 06.06.2018 | 06.06.2018 | ||
| - | - (**5 pnts**) Difference between PAC-learning agent and mistake-bound agent. What does it mean when an agent in both frameworks learns? What does it mean when it learns efficiently? Online? | + | - (**5 pnts**) Difference between PAC-learning agent and mistake-bound agent. |
| - | - (**10 pnts**) Space-version agent. There are given two agent with different hypotheses spaces. First is all possible 3-conjunctions (non-negative) of n variables. Second is all n-conjunctions of positive and negative literals. For each agent: does it learn online? does it learn efficiently? For the first agent: given the first negative observation (0,1,1,1,...,1), what will be the agent's decision on the next observation (0,1,0,1,...)? | + | * (2 pnts) What does it mean when an agent in both frameworks learns? |
| + | * (3 pnts) What does it mean when it learns efficiently? Online? | ||
| + | - (**10 pnts**) Space-version agent. There are given two agent with different hypotheses spaces. First is all possible 3-conjunctions (non-negative) of n variables. Second is all n-conjunctions of positive and negative literals. | ||
| + | * (3 pnts) For each agent: does it learn online? | ||
| + | * (3 pnts) For each agent: does it learn efficiently? | ||
| + | * (4 pnts) For the first agent: given the first negative observation (0,1,1,1,...,1), what will be the agent's decision on the next observation (0,1,0,1,...)? | ||
| - (**15 pnts**) Relative Least General Generalization (rlgg). Given background knowledge B = {half(4,2), half(2,1), int(2), int(1)}. What will be the rlgg of o1 = even(4) and o2 = even(2) relative to the background? | - (**15 pnts**) Relative Least General Generalization (rlgg). Given background knowledge B = {half(4,2), half(2,1), int(2), int(1)}. What will be the rlgg of o1 = even(4) and o2 = even(2) relative to the background? | ||
| * (10 pnts) Apply algorithm, draw tables, theta functions. | * (10 pnts) Apply algorithm, draw tables, theta functions. | ||
| * (5 pnts) Make a reduction step relative to B. Why is it needed? | * (5 pnts) Make a reduction step relative to B. Why is it needed? | ||
| - | - (**10 pnts**) Bayesian networks. Find optimal, efficient, complete network (something like Season -> Temperature -> (two children: -> Ice Cream Sales, -> Heart Attack Rate)). Then compute CPT (conditional probability tables). For two queries compute its probability: 1) Pr(Spring|Good Ice Cream Sales, No Heart Attack) 2) Pr(Heart Attack|Winter, Bad Sales). | + | - (**10 pnts**) Bayesian networks. |
| + | * (2 pnts) Find optimal, efficient, complete network (something like Season -> Temperature -> (two children: -> Ice Cream Sales, -> Heart Attack Rate)). | ||
| + | * (2 pnts) Then compute CPT (conditional probability tables). | ||
| + | * (3 pnts) Compute Pr(Spring|Good Ice Cream Sales, No Heart Attack) | ||
| + | * (3 pnts) Compute Pr(Heart Attack|Winter, Bad Sales). | ||
| - (**5 pnts**) Q-learning. Given 5 small questions, response True/False and provide your reasoning. | - (**5 pnts**) Q-learning. Given 5 small questions, response True/False and provide your reasoning. | ||
| - | * Can Q-learning be extended to infinite states or action space? How would it handle this? | + | * (1 pnt) Can Q-learning be extended to infinite states or action space? How would it handle this? |
| - | * Does Q-learning use on-policy update? What is the difference from off-policy update? | + | * (1 pnt) Does Q-learning use on-policy update? What is the difference from off-policy update? |
| - | * Does Q-learning always converge? If so, is it conditioned by anything? By what? | + | * (1 pnt) Does Q-learning always converge? If so, is it conditioned by anything? By what? |
| - | * Is Q-learning just an instance of temporal difference learning? If not, what is different? | + | * (1 pnt) Is Q-learning just an instance of temporal difference learning? If not, what is different? |
| - | * What is the difference between Q-learning and direct utility estimation or adaptive dynamic programming? What is better? | + | * (1 pnt) What is the difference between Q-learning and direct utility estimation or adaptive dynamic programming? What is better? |
| - (**5 pnts**) Q-learning representation. | - (**5 pnts**) Q-learning representation. | ||
| * There is a robot moving in a swimming pool, which can move in either of 3 dimensions and it has exactly one propeller for each dimension. It can also move with two different speeds. There is a treasure at a specific place and a specific depth. There are mines at some places as well. If the robot hits a mine or the wall, it restarts at a random position. | * There is a robot moving in a swimming pool, which can move in either of 3 dimensions and it has exactly one propeller for each dimension. It can also move with two different speeds. There is a treasure at a specific place and a specific depth. There are mines at some places as well. If the robot hits a mine or the wall, it restarts at a random position. | ||
| - | * Describe states, actions, rewards of a specific game. You may provide two different representations. | + | * (3 pnts) Describe states, actions, rewards of a specific game. You may provide two different representations. |
| - | * Describe Q-learning representation, the update rule, gamma, alpha value. How are Q values defined? | + | * (2 pnts) Describe Q-learning representation, the update rule, gamma, alpha value. How are Q values defined? |
| ~~DISCUSSION~~ | ~~DISCUSSION~~ | ||
