Answered step by step
Verified Expert Solution
Link Copied!

Question

1 Approved Answer

Problem 5 [30 points]. Carry out policy iteration over the MDP example covered in class with R given in Table 2 and = 0.9. For

image text in transcribed
Problem 5 [30 points]. Carry out policy iteration over the MDP example covered in class with R given in Table 2 and = 0.9. For a state s, if R(s) = 1, s is a terminal state. F transition model, assume that the agent has 0.9 probability of going to the intended direction and 0.1 probability of moving to the left. For example, if the agent is at the lower left corner (coordinates (1, 1)) and intends to go right, then it will reach (2, 1) with 0.9 probability and (1,2) with 0.1 probability. If a target cell is not reachable, then the corresponding probability goes back to the current cell. For example, if the agent is at (3,3) and is trying to go up, then with 0.1 probability it goes to (2.3) and with 0.9 probability it is stuck at (3,3). For your answer you should provide: or the a) [15 points]. The first two iterations of your computation. b) [15 points). The converged rewards and the extracted policy. For this problem, you need to provide last two iterations showing that the value changes are within 0.001 for all cells. Table 2: Reward R for a 4 x 3 grid world 0.05 OBS 0.051 0.05 0.05 0.05 0.05 Problem 5 [30 points]. Carry out policy iteration over the MDP example covered in class with R given in Table 2 and = 0.9. For a state s, if R(s) = 1, s is a terminal state. F transition model, assume that the agent has 0.9 probability of going to the intended direction and 0.1 probability of moving to the left. For example, if the agent is at the lower left corner (coordinates (1, 1)) and intends to go right, then it will reach (2, 1) with 0.9 probability and (1,2) with 0.1 probability. If a target cell is not reachable, then the corresponding probability goes back to the current cell. For example, if the agent is at (3,3) and is trying to go up, then with 0.1 probability it goes to (2.3) and with 0.9 probability it is stuck at (3,3). For your answer you should provide: or the a) [15 points]. The first two iterations of your computation. b) [15 points). The converged rewards and the extracted policy. For this problem, you need to provide last two iterations showing that the value changes are within 0.001 for all cells. Table 2: Reward R for a 4 x 3 grid world 0.05 OBS 0.051 0.05 0.05 0.05 0.05

Step by Step Solution

There are 3 Steps involved in it

Step: 1

blur-text-image

Get Instant Access to Expert-Tailored Solutions

See step-by-step solutions with expert insights and AI powered tools for academic success

Step: 2

blur-text-image_2

Step: 3

blur-text-image_3

Ace Your Homework with AI

Get the answers you need in no time with our AI-driven, step-by-step assistance

Get Started

Recommended Textbook for

More Books

Students also viewed these Databases questions

Question

How do modern Dashboards differ from earlier implementations?

Answered: 1 week ago