Generated a good policy for n = 5

Author: ManuelMeraz

Policies.mat

@@ -1,15 +1,8 @@
-# Created by Octave 4.2.1, Tue Oct 10 19:41:20 2017 PDT <manny@dixy>
+# Created by Octave 4.2.1, Tue Oct 10 20:23:58 2017 PDT <manny@dixy>
 # name: Policies
 # type: cell
 # rows: 1
-# columns: 6
-# name: <cell-element>
-# type: matrix
-# rows: 0
-# columns: 0
-
-
-
+# columns: 5
 # name: <cell-element>
 # type: matrix
 # rows: 0
@@ -41,10 +34,10 @@
 # name: <cell-element>
 # type: matrix
 # rows: 3
-# columns: 36
- -0.7853981633974483 -0.7853981633974483 -0.7853981633974483 -0.7853981633974483 -0.7853981633974483 -0.7853981633974483 -0.471238898038469 -0.471238898038469 -0.471238898038469 -0.471238898038469 -0.471238898038469 -0.471238898038469 -0.1570796326794897 -0.1570796326794897 -0.1570796326794897 -0.1570796326794897 -0.1570796326794897 -0.1570796326794897 0.1570796326794897 0.1570796326794897 0.1570796326794897 0.1570796326794897 0.1570796326794897 0.1570796326794897 0.471238898038469 0.471238898038469 0.471238898038469 0.471238898038469 0.471238898038469 0.471238898038469 0.7853981633974483 0.7853981633974483 0.7853981633974483 0.7853981633974483 0.7853981633974483 0.7853981633974483
- -5 -3 -1 1 3 5 -5 -3 -1 1 3 5 -5 -3 -1 1 3 5 -5 -3 -1 1 3 5 -5 -3 -1 1 3 5 -5 -3 -1 1 3 5
- 100 100 100 100 100 84 100 100 100 83 38 -7 100 89 48 8 -32 -73 62 22 -19 -59 -99 -100 -5 -50 -94 -100 -100 -100 -99 -100 -100 -100 -100 -100
+# columns: 25
+ -0.7853981633974483 -0.7853981633974483 -0.7853981633974483 -0.7853981633974483 -0.7853981633974483 -0.3926990816987241 -0.3926990816987241 -0.3926990816987241 -0.3926990816987241 -0.3926990816987241 0 0 0 0 0 0.3926990816987241 0.3926990816987241 0.3926990816987241 0.3926990816987241 0.3926990816987241 0.7853981633974483 0.7853981633974483 0.7853981633974483 0.7853981633974483 0.7853981633974483
+ -5 -2.5 0 2.5 5 -5 -2.5 0 2.5 5 -5 -2.5 0 2.5 5 -5 -2.5 0 2.5 5 -5 -2.5 0 2.5 5
+ 100 100 100 10 -10 100 100 10 -10 -100 100 10 -10 -100 -100 10 -5 -100 -100 -100 1 -100 -100 -100 -100
 
 
 

main.m

@@ -11,7 +11,7 @@
 
 % Time step size
 dt = 0.1; % Seconds
-maxIterations = 500;
+maxIterations = 1000;
 
 % Number of dimensions state vector is in
 dimensions = 2;
@@ -27,7 +27,7 @@
 % depth of recursion tree
 state.depthLimit = 2;
 state.stateBounds = [state.setPoint-pi/4, state.setPoint+pi/4; -5, 5];
-state.numStates = 6;
+state.numStates = 5;
 
 
 % Calculates the step size between each upper and lower bound
@@ -39,7 +39,7 @@
 end
 
 % Set of actions
-A = [-100:100];
+A = [-100, -10, -5, -1, 0, 1, 5, 10, 100];
 
 % Set of states
 S = [linspace(state.stateBounds(1,1), state.stateBounds(1,2), state.numStates);...