EE466000 introduction to reinforcement learning
Homework 2: Gridworld
Goal
The goal of this assignment helps you understand bellman equation.
Todo
Implement two algorithms:
bellman equation for vπ(𝑠)
optimal value function.
Details
File description
o hw2_ipynb.ipynb: You’ll implement two algorithms in the file.
Gridworld environment
tables of two algorithms.
Requirements and Installation
Python version: 3.6
pip install matplotlib
pip install numpy
Report
Title, name, student ID
Implementation
Briefly describe your implementation.
Experiments and Analysis
Plot tables of two algorithms. (As example above)
Whether state values are reasonable?
Vary the discount rate(gamma), what happens? please plot it.
Reminder
Please upload your code main.py and report.pdf to iLMS before 4/11 (Sat.) 23:59. No late
submission allowed.
DO NOT zip your code into a single file.
Please do not copy&paste the code from your classmates.
Please write a README file to explain how to run your code if you implemented extra
functions.
