***********************************************************
Puddle World using Consistent Bellman Equation
***********************************************************

Options used when running:

1: Puddle World
20: Order --- this means we will have 20^2 = 400 weights to tune
1: No value averaging
1: Consistent Bellman
100: Number of interations of value iteration
16: Number of threads used by value iteration (set to your number of cores)
16: Number of threads used to evaluate a policy (set to your number of cores)
1: Evaluate policy after every iteration
0: Print results to file
out_Consistent_PuddleWorld.txt: The file to print the results to

Console output:

Select environment:
[0] Mountain Car
[1] Puddle World
[2] Acrobot
[3] Cart Pole
[4] Pendulum Swing-Up and Balance
[5] Bicycle
Selection: 1
Enter the order (state is 2 dimensional): 20
Select value averaging:
[0] Yes
[1] No
Selection: 1
Select maxQ Variant:
[0] Ordinary Bellman
[1] Consistent Bellman
Selection: 1
Enter number of iterations of value iteration: 100
Enter number of threads for value-iteration (we suggest # available cores): 16
Enter number of threads for policy evaluation (we suggest # available cores): 16
Evaluate policy every how-many iterations? 1
Select Print results to file:
[0] Yes
[1] No
Selection: 0
Enter filename: out_Consistent_PuddleWorld.txt

Initially: Undiscounted return = -1061.23
Iteration: 1	Undiscounted return = -1000.25
Iteration: 2	Undiscounted return = -1000
Iteration: 3	Undiscounted return = -1000
Iteration: 4	Undiscounted return = -1000
Iteration: 5	Undiscounted return = -999.245
Iteration: 6	Undiscounted return = -1000
Iteration: 7	Undiscounted return = -997.68
Iteration: 8	Undiscounted return = -981.885
Iteration: 9	Undiscounted return = -982.67
Iteration: 10	Undiscounted return = -943.508
Iteration: 11	Undiscounted return = -789.979
Iteration: 12	Undiscounted return = -590.405
Iteration: 13	Undiscounted return = -403.398
Iteration: 14	Undiscounted return = -330.667
Iteration: 15	Undiscounted return = -47.575
Iteration: 16	Undiscounted return = -96.279
Iteration: 17	Undiscounted return = -40.197
Iteration: 18	Undiscounted return = -40.709
Iteration: 19	Undiscounted return = -39.039
Iteration: 20	Undiscounted return = -37.844
Iteration: 21	Undiscounted return = -37.815
Iteration: 22	Undiscounted return = -37.582
Iteration: 23	Undiscounted return = -35.9255
Iteration: 24	Undiscounted return = -35.767
Iteration: 25	Undiscounted return = -35.767
Iteration: 26	Undiscounted return = -35.475
Iteration: 27	Undiscounted return = -35.52
Iteration: 28	Undiscounted return = -35.569
Iteration: 29	Undiscounted return = -35.1851
Iteration: 30	Undiscounted return = -35.1692
Iteration: 31	Undiscounted return = -34.786
Iteration: 32	Undiscounted return = -34.855
Iteration: 33	Undiscounted return = -34.8017
Iteration: 34	Undiscounted return = -34.7727
Iteration: 35	Undiscounted return = -34.8443
Iteration: 36	Undiscounted return = -34.7808
Iteration: 37	Undiscounted return = -34.9469
Iteration: 38	Undiscounted return = -34.565
Iteration: 39	Undiscounted return = -34.7276
Iteration: 40	Undiscounted return = -34.806
Iteration: 41	Undiscounted return = -35.0089
Iteration: 42	Undiscounted return = -34.8
Iteration: 43	Undiscounted return = -34.7612
Iteration: 44	Undiscounted return = -34.8771
Iteration: 45	Undiscounted return = -34.7457
Iteration: 46	Undiscounted return = -35.0515
Iteration: 47	Undiscounted return = -35.0564
Iteration: 48	Undiscounted return = -34.9039
Iteration: 49	Undiscounted return = -34.7113
Iteration: 50	Undiscounted return = -34.6759
Iteration: 51	Undiscounted return = -34.908
Iteration: 52	Undiscounted return = -34.823
Iteration: 53	Undiscounted return = -34.7381
Iteration: 54	Undiscounted return = -34.8693
Iteration: 55	Undiscounted return = -34.7736
Iteration: 56	Undiscounted return = -34.7325
Iteration: 57	Undiscounted return = -34.8641
Iteration: 58	Undiscounted return = -34.5457
Iteration: 59	Undiscounted return = -34.906
Iteration: 60	Undiscounted return = -34.8623
Iteration: 61	Undiscounted return = -34.7786
Iteration: 62	Undiscounted return = -34.8784
Iteration: 63	Undiscounted return = -34.8525
Iteration: 64	Undiscounted return = -34.7929
Iteration: 65	Undiscounted return = -34.8123
Iteration: 66	Undiscounted return = -34.862
Iteration: 67	Undiscounted return = -34.9968
Iteration: 68	Undiscounted return = -34.8816
Iteration: 69	Undiscounted return = -34.74
Iteration: 70	Undiscounted return = -34.8196
Iteration: 71	Undiscounted return = -34.945
Iteration: 72	Undiscounted return = -35.004
Iteration: 73	Undiscounted return = -34.793
Iteration: 74	Undiscounted return = -34.922
Iteration: 75	Undiscounted return = -34.777
Iteration: 76	Undiscounted return = -34.7383
Iteration: 77	Undiscounted return = -34.997
Iteration: 78	Undiscounted return = -34.7793
Iteration: 79	Undiscounted return = -34.7788
Iteration: 80	Undiscounted return = -34.8867
Iteration: 81	Undiscounted return = -34.7941
Iteration: 82	Undiscounted return = -34.8115
Iteration: 83	Undiscounted return = -34.7331
Iteration: 84	Undiscounted return = -34.6635
Iteration: 85	Undiscounted return = -34.7542
Iteration: 86	Undiscounted return = -34.7091
Iteration: 87	Undiscounted return = -34.9141
Iteration: 88	Undiscounted return = -34.8221
Iteration: 89	Undiscounted return = -34.8071
Iteration: 90	Undiscounted return = -34.5161
Iteration: 91	Undiscounted return = -34.79
Iteration: 92	Undiscounted return = -34.6931
Iteration: 93	Undiscounted return = -34.7477
Iteration: 94	Undiscounted return = -34.8516
Iteration: 95	Undiscounted return = -34.9701
Iteration: 96	Undiscounted return = -34.9818
Iteration: 97	Undiscounted return = -34.8305
Iteration: 98	Undiscounted return = -34.8171
Iteration: 99	Undiscounted return = -34.908
Iteration: 100	Undiscounted return = -34.8099
Printing results to out_Consistent_PuddleWorld.txt
