CSCI4155/CSCS6505 (2014) - Revision history

Tt: /* Assignment 7: Due: Presentation Dec 2, report Dec 3 */

2014-11-27T19:33:41Z

Assignment 7: Due: Presentation Dec 2, report Dec 3

2014-11-25T15:35:38Z

Assignment 7: Due: Presentation Dec 2, report Dec 3

2014-11-25T15:31:37Z

Assignment 7: Due: Presentation Dec 2, report Dec 3

2014-11-25T15:31:13Z

Assignment 7: Due: Presentation Dec 2, report Dec 3

2014-11-25T15:30:39Z

Assignment 7: Due TBA

2014-11-18T15:10:37Z

Assignment 6: Due Wednesday, November 12

2014-11-04T20:52:22Z

Assignment 6: Due Wednesday, November 12

2014-11-04T19:11:43Z

Assignment 6: Due Wednesday, November 12

2014-11-04T19:07:55Z

Assignment 5: Due Monday, November 3

2014-10-28T20:34:05Z

Assignment 5: Due Monday, November 11

@@ Line 151: / Line 151: @@
   The basic goal of this last assignment is to implement a tic-tac-toe game engine that learns through reinforcement learning.
   Implement a temporal difference learner and show how its performance change with learning. Discuss the relation of your
-  method to another reinforcement learning algorithm such as random sampling. You need to present your results in class on Dec 2
+  method to another reinforcement learning procedure such as random sampling of actions. You need to present your results in class on Dec 2
   and submit a written report in pdf format on Dec 3. Please send your report together with your programs to prof4155@gmail.com.

@@ Line 157: / Line 157: @@
   the look-up table and discuss its performance in relation to the original method. Also, discuss the scaling properties of
   the algorithms by considering a connect-4 game engine.
 === Programming environment ===

@@ Line 154: / Line 154: @@
   and submit a written report in pdf format on Dec 3. Please send your report together with your programs to prof4155@gmail.com.
-  \emph{Grad students}: In addition to the basic tic-tac-toe game engine described above, apply a function approximator to represent
+  '''Grad students''': In addition to the basic tic-tac-toe game engine described above, apply a function approximator to represent
   the look-up table and discuss its performance in relation to the original method. Also, discuss the scaling properties of
   the algorithms by considering a connect-4 game engine.

@@ Line 154: / Line 154: @@
   and submit a written report in pdf format on Dec 3. Please send your report together with your programs to prof4155@gmail.com.
-  Grad students: In addition to the basic tic-tac-toe game engine described above, apply a function approximator to represent
+  \emph{Grad students}: In addition to the basic tic-tac-toe game engine described above, apply a function approximator to represent
   the look-up table and discuss its performance in relation to the original method. Also, discuss the scaling properties of
   the algorithms by considering a connect-4 game engine.

@@ Line 144: / Line 144: @@
      where the size of the symbol should correspond to the frequency.
-==== Assignment 7: Due TBA ====
+==== Assignment 7: Due: Presentation Dec 2, report Dec 3 ====
 Reinforcement learning:
-  Implement a tic-tac-toe and four in a row game engine with reinforcement learning
+  The basic goal of this last assignment is to implement a tic-tac-toe game engine that learns through reinforcement learning.
-  and evaluate their performance.
+ Implement a temporal difference learner and show how its performance change with learning. Discuss the relation of your
 === Programming environment ===

@@ Line 134: / Line 134: @@
   In this assignment you should explore different unsupervised learning algorithms. We will use the IRIS dataset here.
-  You should implement the algorithms listed below and evaluate their performance. Write up your findings (no page limit)
+  You should implement the algorithms listed below and evaluate their performance. You can assume k=3.
- and submit a pdf to prof4155@gmail.com with subject line A6.
+ Write up your findings (no page limit) and submit a pdf to prof4155@gmail.com with subject line A6.
   a) Implement a simple perceptron (This is of course supervised learning but should give us some baseline)

@@ Line 125: / Line 125: @@
    In [5]: TRAIN_DATA.shape
    Out[5]: (131450, 3)
 === Programming environment ===

← Older revision		Revision as of 20:34, 28 October 2014
Line 95:		Line 95:


−	==== Assignment 5: Due Monday, November 11 ====	+	==== Assignment 5: Due Monday, November 3 ====

	Reading:		Reading: