We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 9b88cff commit 0fd38b8Copy full SHA for 0fd38b8
P4/README.txt
@@ -0,0 +1,25 @@
1
+Raphael Gontijo Lopes
2
+903062081
3
+
4
+CS 4641 - Machine Learning
5
6
+A description of the MDPs used can be found in the analysis pdf
7
+This project used CMU's Reinforcement Learning Simulator.
8
+The original source can be found here:
9
+http://www.cs.cmu.edu/~awm/rlsim/
10
+The fork I used (which has helpful image-saving features) can be found here:
11
+https://github.com/theJenix/rl_sim_fork
12
13
+The compiled RLSim jar is included in my submission, along with the source.
14
15
+To run RLSim, do:
16
+`java -cp rl.jar MainUI`
17
18
+The problem mazes used were:
19
20
+Small map:
21
+4_multipleGoals2.maze
22
23
+Large Map:
24
+7_medium_complex_multigoal.maze
25
0 commit comments