DS/CS 442 Spring 2021
Project 3: Reinforcement Learning
Due: Sunday 3/28 at 11:59 pm
In this project, you will implement value iteration and Q-learning. You will test your agents first on Gridworld
(from class), then apply them to a simulated robot controller (Crawler) and Pacman.
As in previous projects, this project includes an autograder for you to grade your solutions on your machine. This
can be run on all questions with the command:
It can be run for one particular question, such as q2, by:
It can be run for one particular test by commands of the form:
The code for this project contains the following files, available as a zip archive.
Files you'll edit:
valueIterationAgents.py A value iteration agent for solving known MDPs.
qlearningAgents.py Q-learning agents for Gridworld, Crawler and Pacman.
analysis.py A file to put your answers to questions given in the project.
Files you should read but NOT edit:
mdp.py Defines methods on general MDPs.
learningAgents.py Defines the base classes ValueEstimationAgent and
QLearningAgent , which your agents will extend.
util.py Utilities, including util.Counter , which is particularly
useful for Q-learners.
gridworld.py The Gridworld implementation.
featureExtractors.py Classes for extracting features on (state, action) pairs. Used fo
the approximate Q-learning agent (in
Files you can ignore:
environment.py Abstract class for general reinforcement learning environments.
Used by gridworld.py .
graphicsGridworldDisplay.py Gridworld graphical display.
graphicsUtils.py Graphics utilities.
textGridworldDisplay.py Plug-in for the Gridworld text interface.
crawler.py The crawler code and test harness. You will run this but not edit
graphicsCrawlerDisplay.py GUI for the crawler robot.
autograder.py Project autograde
testParser.py Parses autograder test and solution files
testClasses.py General autograding test classes
python autograder.py -q q2
python autograder.py -t test_cases/q2/1-
test_cases/ Directory containing the test cases for each question
einforcementTestClasses.py Project 3 specific autograding test classes
Files to Edit and Submit: You will fill in portions of valueIterationAgents.py ,
qlearningAgents.py , and analysis.py during the assignment. Please do not change the other files in
this distribution or submit any of our original files other than these files.
Note: You only need to submit reinforcement.token , generated by running
submission_autograder.py . It contains the evaluation results from your local autograder, and a copy of
all your code. You do not need to submit any other files.
Evaluation: Your code will be autograded for technical co
ectness. Please do not change the names of any
provided functions or classes within the code, or you will wreak havoc on the autograder. However, the
ectness of your implementation – not the autograder’s judgements – will be the final judge of your score. If
necessary, we will review and grade assignments individually to ensure that you receive due credit for your work.
Academic Dishonesty: We will be checking your code against other submissions in the class for logical
edundancy. If you copy someone else’s code and submit it with minor changes, we will know. These cheat
detectors are quite hard to fool, so please don’t try. We trust you all to submit your own work only; please don’t
let us down. If you do, we will pursue the strongest consequences available to us.
Getting Help: You are not alone! If you find yourself stuck on something, contact the course staff for help.
Office hours, section, and the discussion forum are there for your support; please use them. If you can’t make ou
office hours, let us know and we will schedule more. We want these projects to be rewarding and instructional,
not frustrating and demoralizing. But, we don’t know when or how to help unless you ask.
Discussion: Please be careful not to post spoilers.
To get started, run Gridworld in manual control mode, which uses the a
You will see the two-exit layout from class. The blue dot is the agent. Note that when you press up, the agent
only actually moves north 80% of the time. Such is the life of a Gridworld agent!
You can control many aspects of the simulation. A full list of options is available by running:
The default agent moves randomly
You should see the random agent bounce around the grid until it happens upon an exit. Not the finest hour for an
Note: The Gridworld MDP is such that you first must enter a pre-terminal state (the double boxes shown in the
GUI) and then take the special ‘exit’ action before the episode actually ends (in the true terminal state called
TERMINAL_STATE , which is not shown in the GUI). If you run an episode manually, your total return may be
less than you expected, due to the discount rate ( -d to change; 0.9 by default).
Look at the console output that accompanies the graphical output (or use -t for all text). You will be told about
each transition the agent experiences (to turn this off, use -q ).
As in Pacman, positions are represented by (x,y) Cartesian coordinates and any a
ays are indexed by
[x][y] , with 'north' being the direction of increasing y , etc. By default, most transitions will receive a
eward of zero, though you can change this with the living reward option ( -r ).
Question 1 (4 points): Value Iteration
Recall the value iteration state update equation:
Write a value iteration agent in ValueIterationAgent , which has been partially specified for you in
valueIterationAgents.py . Your value iteration agent is an offline planner, not a reinforcement learning
agent, and so the relevant training option is the number of iterations of value iteration it should run (option -i )
in its initial planning phase. ValueIterationAgent takes an MDP on construction and runs value iteration
for the specified number of iterations before the constructor returns.
python gridworld.py -m
python gridworld.py -h
python gridworld.py -g MazeGrid
Value iteration computes -step estimates of the optimal values, . In addition to running value iteration,
implement the following methods for ValueIterationAgent using .
computeActionFromValues(state) computes the best action according to the value function
given by self.values .
computeQValueFromValues(state, action) returns the Q-value of the (state, action) pair given
y the value function given by self.values .
These quantities are all displayed in the GUI: values are numbers in squares, Q-values are numbers in square
quarters, and policies are a
ows out from each square.
Important: Use the “batch” version of value iteration where each vector is computed from a fixed vector
(like in lecture), not the “online” version where one single weight vector is updated in place. This means that
when a state’s value is updated in iteration based on the values of its successor states, the successor state values
used in the value update computation should be those from iteration (even if some of the successor states
had already been updated in iteration ). The difference is discussed in Sutton & Barto in Chapter 4.1 on page 91.
Note: A policy synthesized from values of depth (which reflect the next rewards) will actually reflect the next
rewards (i.e. you return ). Similarly, the Q-values will also reflect one more reward than the values
(i.e. you return ).
You should return the synthesized policy .
Hint: You may optionally use the util.Counter class in util.py , which is a dictionary with a default
value of zero. However, be careful with argMax : the actual argmax you want may be a key not in the counter!
Note: Make sure to handle the case when a state has no available actions in an MDP (think about what this means
for future rewards).
To test your implementation, run the autograder:
The following command loads your ValueIterationAgent , which will compute a policy and execute it 10
times. Press a key to cycle through values, Q-values, and the simulation. You should find that the value of the
start state ( V(start) , which you can read off of the GUI) and the empirical resulting average reward (printed
after the 10 rounds of execution finish) are quite close.
Hint: On the default BookGrid, running value iteration for 5 iterations should give you this output:
Grading: Your value iteration agent will be graded on a new grid. We will check your values, Q-values, and
policies after fixed numbers of iterations and at convergence (e.g. after 100 iterations).
Question 2 (1 point): Bridge Crossing Analysis
k − 1
k + 1 πk+1
python autograder.py -q q1
python gridworld.py -a value -i 100 -k 10
python gridworld.py -a value -i 5
BridgeGrid is a grid world map with the a low-reward terminal state and a high-reward terminal state
separated by a na
idge”, on either side of which is a chasm of high negative reward. The agent starts nea
the low-reward state. With the default discount of 0.9 and the default noise of 0.2, the optimal policy does not
idge. Change only ONE of the discount and noise parameters so that the optimal policy causes the
agent to attempt to cross the
idge. Put your answer in question2() of analysis.py . (Noise refers to
how often an agent ends up in an unintended successor state when they perform an action.) The default
Grading: We will check that you only changed one of the given parameters, and that with this change, a co
value iteration agent should cross the
idge. To check your answer, run the autograder:
Question 3 (5 points): Policies
Consider the DiscountGrid layout, shown below. This grid has two terminal states with positive payoff (in
the middle row), a close exit with payoff +1 and a distant exit with payoff +10. The bottom row of the grid
consists of terminal states with negative payoff (shown in red); each state in this “cliff” region has payoff -10.
The starting state is the yellow square. We distinguish between two types of paths: (1) paths that “risk the cliff”
and travel near the bottom row of the grid; these paths are shorter but risk earning a large negative payoff, and
are represented by the red a
ow in the figure below. (2) paths that “avoid the cliff” and travel along the top edge
of the grid. These paths are longer but are less likely to incur huge negative payoffs. These paths are represented
y the green a
ow in the figure below.
In this question, you will choose settings of the discount, noise, and living reward parameters for this MDP to