Looking for ITI0210 Tehisintellekti ja masinõppe alused (2025/26 sügis) test answers and solutions? Browse our comprehensive collection of verified answers for ITI0210 Tehisintellekti ja masinõppe alused (2025/26 sügis) at moodle.taltech.ee.
Get instant access to accurate answers and detailed explanations for your course questions. Our community-driven platform helps students succeed!
In Q-Learning, we often use an -greedy strategy.
Task: 1. Explain what the parameter 2. Imagine a scenario: A robot is learning to navigate a cliff edge. It receives -100 for falling off and -1 for every step. If
The Vaccuum World contains two rooms: A and B, and an intelligent agent, the vaccuum cleaner. The task of the agent is to keep the rooms clean.
The agent's actions:
| Action | Cost | Effect |
|---|---|---|
| Right | 1 | Moves right (to room B) |
| Left | 1 | Moves left (to room A) |
| Vacuum | 1 | Room becomes clean |
| NoOp | 0 | - |
def decide_action(room, status):
if status == "dirty": return "Vacuum"
elif room == "A": return "Right"
else: return "Left"
Suppose the agent works n=10 steps from the state given in the picture above. We evaluate the performance of the agent as follows:What is the performance of the agent after 10 steps?Calculate P(IAIB3=yes|KnowsBayes=yes)P(IAIB3=yes|KnowsBayes=yes)
Calculate P(IAIB3=yes)
Calculate P(KnowsBayes=yes)P(KnowsBayes=yes).
Can be calculated from the probabilities we found so far, check the formulas given in the beginning.
What is the probability P(KnowsBayes=yes|IAIB3=no) given in the text?