**RL**
**Section Id :** 64065349326
**Section Number :** 7
**Section type :** Online
**Mandatory or Optional :** Mandatory
**Number of Questions :** 30
**Number of Questions to be attempted :** 30
**Section Marks :** 50
**Display Number Panel :** Yes
**Section Negative Marks :** 0
**Group All Questions :** No
**Enable Mark as Answered Mark for Review and**
Yes
**Clear Response :**
**Maximum Instruction Time :** 0
A published solution is not available for this question yet.
Assertion: Taking exploratory actions is important for RL agents
Reason: If the rewards obtained for actions are stochastic, an action which gave a high reward
once, might give lower reward next time.
6406532335299.
Assertion and Reason are both true and Reason is a correct explanation of
Assertion.
6406532335300.
Assertion and Reason are both true and Reason is not a correct explanation of
Assertion.
6406532335301.
Assertion is true and Reason is false
6406532335302.
Both Assertion and Reason are false.
A published solution is not available for this question yet.
Consider following assertion-reason pair:
Assertion: Monte Carlo value function approximation methods need knowledge of model to be
implemented.
Reason: Monte Carlo value function approximation methods require a way to sample trajectories
from the environment.
6406532335309.
Assertion and Reason are both true and Reason is a correct explanation of
Assertion.
6406532335310.
Assertion and Reason are both true and Reason is not a correct explanation of
Assertion.
6406532335311.
Assertion is true but Reason is false.
6406532335312.
Assertion is false but Reason is true.
A published solution is not available for this question yet.
In the naive method of state aggregation such as we have in a grid world, the assumption that
states that are close together have similar values breaks down for which of the following
scenarios?
6406532335347.
A pair of states that are in the middle of some cell.
6406532335348.
A pair of states that are close to the border with both of them lying in the same
cell.
6406532335349.
A pair of states that are close to the border with both of them lying in different
cells.
6406532335350.
None of these
A published solution is not available for this question yet.
As a consequence of the proposed fix for the non-stationarity of the target in DQN, the target
network changes at a _______ rate than the online network.
6406532335357.
faster
6406532335358.
slower
6406532335359.
None of these
A published solution is not available for this question yet.
Which of the following are correct about the notion of eligibility traces?
6406532335338.
It is the backward view of the TD(λ) algorithm.
6406532335339.
It is the forward view of the TD(λ) algorithm.
6406532335340.
The motivation behind eligibility traces is, if an agent receives a
reward/punishment at any time step, then which decisions in the past are eligible to get credit for
it.
6406532335341.
None of these
A published solution is not available for this question yet.
