MauryaHub PYQ Practice

Reinforcement Learning · End Term · May 2023 · FN

Reinforcement Learning · End Term · May 2023 FN

← Course papers · Start practice / exam

This page contains the reliably extracted subset, not the complete original paper.

Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.

0 / 18 published solutions

Question 215 MCQ · 7.0 marks

Source diagram or notation
6406532050488.
I have written answers on the answer sheets
6406532050489.
Not applicable       **RL** **Section Id :** 64065341418 **Section Number :** 10 **Section type :** Online **Mandatory or Optional :** Mandatory **Number of Questions :** 16 **Number of Questions to be attempted :** 16 **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.

Report a correction for Q215

Question 217 MCQ · 3.0 marks

Source diagram or notation
6406532050492.Source diagram or notation
6406532050493.Source diagram or notation
6406532050494.Source diagram or notation
6406532050495.Source diagram or notation
6406532050496.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q217

Question 218 MCQ · 3.0 marks

Source diagram or notation
6406532050497.Source diagram or notation
6406532050498.Source diagram or notation
6406532050499.Source diagram or notation
6406532050500.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q218

Question 219 MCQ · 3.0 marks

Select the most appropriate statement concerning the behaviour policy in Q-learning.
6406532050501.Source diagram or notation
6406532050502.Source diagram or notation
6406532050503.Source diagram or notation
6406532050504.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q219

Question 220 MCQ · 3.0 marks

Source diagram or notation
6406532050505.Source diagram or notation
6406532050506.Source diagram or notation
6406532050507.Source diagram or notation
6406532050508.Source diagram or notation
Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q220

Question 221 MCQ · 3.0 marks

Given a problem with a well defined hierarchy, what ordering would you expect on the total expected reward for a hierarchically optimal policy (H), a recursively optimal policy (R) and a flat optimal policy (F)?
6406532050509.Source diagram or notation
6406532050510.Source diagram or notation
6406532050511.Source diagram or notation
6406532050512.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q221

Question 222 MCQ · 3.0 marks

Which of the following corresponds to an update for the actor in the case of one-step actor-critic method?
6406532050513.Source diagram or notation
6406532050514.Source diagram or notation
6406532050515.Source diagram or notation
6406532050516.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q222

Question 223 MSQ · 4.0 marks

Source diagram or notation
6406532050517.Source diagram or notation
6406532050518.Source diagram or notation
Source diagram or notation
6406532050519.Source diagram or notation
6406532050520.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q223

Question 224 MSQ · 3.0 marks

Select all true statements.
6406532050521.
Policy gradient methods use a parameterized policy that can select actions without consulting a value function.
6406532050522.
Policy gradient methods **must** use a value function to learn the policy parameters.
6406532050523.
According to the policy gradient theorem, computing the gradient of the performance requires the computation of the gradient of the state distribution μ(s).
6406532050524.
In REINFORCE with baseline, the baseline **cannot** be a function of the actions.

A published solution is not available for this question yet.

Report a correction for Q224

Question 225 NAT · 3.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q225

Question 226 NAT · 3.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q226

Question 227 NAT · 3.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q227

Question 228 NAT · 3.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q228

Question 229 MCQ · 4.0 marks

Which of the following is the TD error used in the TD(0) algorithm?
6406532050526.Source diagram or notation
6406532050527.Source diagram or notation
6406532050528.Source diagram or notation
6406532050529.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q229

Question 230 NAT · 2.5 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Find the TD error for this transition.

A published solution is not available for this question yet.

Report a correction for Q230

Question 231 NAT · 1.5 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q231

Question 232 NAT · 3.5 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q232

Question 233 MCQ · 1.5 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
If the eligibility traces are replacing in nature, which state would have highest eligibility trace at the end of a trajectory, and what will be the value of the eligibility trace of the corresponding state?
6406532050536.Source diagram or notation
6406532050537.Source diagram or notation
6406532050538.Source diagram or notation
6406532050539.Source diagram or notation
      **Statistical Computing** **Section Id :** 64065341419 **Section Number :** 11 **Section type :** Online **Mandatory or Optional :** Mandatory **Number of Questions :** 6 **Number of Questions to be attempted :** 6 **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.

Report a correction for Q233