HW2.pdf - Homework 2 ELEN E6885 Reinforcement Learning Problem 1(n-Step Return 15 Credits The expected value of all n-step returns is guaranteed to

# HW2.pdf - Homework 2 ELEN E6885 Reinforcement Learning...

• Homework Help
• 2

This preview shows page 1 - 2 out of 2 pages.

Homework 2 ELEN E6885: Reinforcement Learning November 15, 2018 Problem 1 ( n -Step Return, 15 Credits ) The expected value of all n -step returns is guaranteed to improve in a certain way over the current value function as an approximation to the true value function. Prove the following error reduction property of n-step returns max s E π n R ( n ) t s t = s o - V π ( s ) γ n max s V ( s ) - V π ( s ) , where R ( n ) t is n -step return at time t . Problem 2 ( Value-Based RL, 20 Credits ) Consider the small corridor gridworld shown in Fig. 1 below. S and G represents the start and goal (terminal) states, respectively. In each of the two non-terminal states there are only two actions, right and left . These actions have their usual consequences in the start state (left causes no movement in the first state), but in the second state they are reversed, so that right moves to the left and left moves to the right. The reward is - 1 per step as usual. We approximate the action-value function using two features x 1 ( s, a ) = 1 ( a = right ) and x 2 ( s, a ) = 1 ( a = left

• Fall '19

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern