Spring 2020 Project 7: Qlearning Robot - Revision history

Jfox44: /* Template */

2020-03-05T00:00:21Z

Template

Jfox44: /* Tasks */

2020-03-04T23:58:38Z

Tasks

Jfox44: /* Tasks */

2020-03-04T23:56:29Z

Tasks

Jfox44 at 23:55, 4 March 2020

2020-03-04T23:55:52Z

Jfox44 at 23:54, 4 March 2020

2020-03-04T23:54:56Z

Show changes

Jfox44 at 01:13, 2 January 2020

2020-01-02T01:13:26Z

Jfox44: Created page with "Under Construction"

2019-12-31T22:55:32Z

Created page with "Under Construction"

New page

Under Construction

@@ Line 23: / Line 23: @@
 == Template==
-* Download the template code here: [[File:19fall_qlearning_robot.zip]]
+* Download the template code here: [[File:20spring_qlearning_robot.zip]]
 * Implement the <tt>QLearner</tt> class in <tt>qlearning_robot/QLearner.py</tt>.
 * To debug your Q-learner, run <tt>'''python testqlearner.py'''</tt> from the <tt>qlearning_robot/</tt> directory. The grading script for this project is <tt>'''grade_robot_qlearning.py'''</tt>.

@@ Line 88: / Line 88: @@
 </PRE>
-===Navigation Problem Test Cases===
+====Navigation Problem Test Cases====
 We will test your Q-Learner with a navigation problem as follows.  Note that your Q-Learner does not need to be coded specially for this task.  In fact the code doesn't need to know anything about it.  The code necessary to test your learner with this navigation task is implemented in testqlearner.py for you.  The navigation task takes place in a 10 x 10 grid world.  The particular environment is expressed in a CSV file of integers, where the value in each position is interpreted as follows:
@@ Line 177: / Line 177: @@
 </pre>
-Check the template code for examples. We are adding those to the repo now, but it might not be there if you check right away.  Implementing this method correctly does not provide any points, but there will be a penalty for not implementing it.
+Implementing this method correctly does not provide any points, but there will be a penalty for not implementing it.
 ==What to turn in==

@@ Line 41: / Line 41: @@
 ==Tasks==
-===Part 1: Implement Q-Learner (95 points)===
+===Implement Q-Learner (95 points)===
 Your QLearner class should be implemented in the file <tt>QLearner.py</tt>.  It should implement EXACTLY the API defined below.  DO NOT import any modules besides those allowed below.  Your class should implement the following methods:
@@ Line 88: / Line 88: @@
 </PRE>
-===Part 2: Navigation Problem Test Cases===
+===Navigation Problem Test Cases===
 We will test your Q-Learner with a navigation problem as follows.  Note that your Q-Learner does not need to be coded specially for this task.  In fact the code doesn't need to know anything about it.  The code necessary to test your learner with this navigation task is implemented in testqlearner.py for you.  The navigation task takes place in a 10 x 10 grid world.  The particular environment is expressed in a CSV file of integers, where the value in each position is interpreted as follows:
@@ Line 153: / Line 153: @@
 [[mc3_p2_dyna_examples]]
-===Part 3: Implement Dyna (5 points)===
+===Implement Dyna (5 points)===
 Add additional components to your QLearner class so that multiple "hallucinated" experience tuples are used to update the Q-table for each "real" experience.  The addition of this component should speed convergence in terms of the number of calls to query(), <b>not necessarily running time</b>.
@@ Line 159: / Line 159: @@
 Note that it is not important that you implement Dyna exactly as described in the lecture.  The key requirement is that your code should somehow hallucinate additional experiences.  The precise method you use for discovering those experiences is flexible.  We will test your code on several test worlds with 50 epochs and with dyna = 200.  Our expectation is that with Dyna, the solution should be much better after 50 epochs than without.
-===Part 4: Implement author() Method (up to 20 point penalty)===
+===Implement author() Method (up to 20 point penalty)===
 You  should implement a method called <tt>author()</tt> that returns your Georgia Tech user ID as a string. This is the ID you use to log into canvas.  It is not your 9 digit student number.  Here is an example of how you might implement author() within a learner object:

@@ Line 27: / Line 27: @@
 * To debug your Q-learner, run <tt>'''python testqlearner.py'''</tt> from the <tt>qlearning_robot/</tt> directory. The grading script for this project is <tt>'''grade_robot_qlearning.py'''</tt>.
 * Note that example navigation problems are provided in the <tt>qlearning_robot/testworlds</tt> directory.
 ==Tasks==

← Older revision		Revision as of 01:13, 2 January 2020
Line 1:		Line 1:
−	~~Under Construction~~	+	==Revisions==
		+
		+	==Overview==
		+
		+	== Template==
		+
		+	==Tasks==
		+
		+	==What to turn in==
		+
		+	==Rubric==
		+
		+	===Report===
		+
		+	===Code===
		+
		+	==Required, Allowed & Prohibited==