Reinforcement Learning Benchmark Results
Average Score
|
qlearn |
exploit |
near |
explore |
far |
random |
example |
Average |
| small_01 |
5865.00 |
5107.00 |
2762.00 |
-1000.00 |
2762.00 |
-506.00 |
-158.00 |
2118.90 |
| small_02 |
12395.00 |
12395.00 |
12395.00 |
12395.00 |
-1000.00 |
-146.00 |
-35.00 |
6914.10 |
| small_03 |
3688.00 |
3688.00 |
3121.00 |
-1000.00 |
-999.00 |
-350.00 |
-432.00 |
1102.30 |
| small_04 |
7372.00 |
7372.00 |
7372.00 |
5650.00 |
8749.00 |
315.00 |
99.00 |
5275.60 |
| small_05 |
11810.00 |
11810.00 |
11810.00 |
11810.00 |
9081.00 |
424.00 |
400.00 |
8163.60 |
| small_06 |
4374.00 |
4374.00 |
4374.00 |
5101.00 |
6375.00 |
-463.00 |
-443.00 |
3384.60 |
| small_07 |
7918.00 |
7918.00 |
5826.00 |
7918.00 |
7542.00 |
-725.00 |
-602.00 |
5113.60 |
| small_08 |
6860.00 |
6860.00 |
17074.00 |
19200.00 |
19200.00 |
107.00 |
85.00 |
9912.30 |
| small_09 |
8988.00 |
8988.00 |
7671.00 |
6705.00 |
-998.00 |
-531.00 |
-411.00 |
4344.60 |
| small_10 |
5741.00 |
7137.00 |
3422.00 |
-999.00 |
5741.00 |
-379.00 |
-797.00 |
2838.00 |
| medium_01 |
10059.00 |
10059.00 |
10059.00 |
9810.00 |
8344.00 |
204.00 |
-160.00 |
6910.70 |
| medium_02 |
6056.00 |
7774.00 |
-997.00 |
-999.00 |
-999.00 |
-789.00 |
-985.00 |
1294.40 |
| medium_03 |
5805.00 |
2986.00 |
2986.00 |
4248.00 |
-999.00 |
-455.00 |
-595.00 |
1996.60 |
| medium_04 |
5050.00 |
7559.00 |
5264.00 |
-998.00 |
-1000.00 |
-541.00 |
-592.00 |
2106.00 |
| medium_05 |
4783.00 |
4783.00 |
-997.00 |
-1000.00 |
-999.00 |
-605.00 |
-990.00 |
710.70 |
| medium_06 |
6805.00 |
6029.00 |
6076.00 |
-999.00 |
-1000.00 |
-687.00 |
-985.00 |
2177.00 |
| medium_07 |
4828.00 |
4828.00 |
892.00 |
3461.00 |
-1000.00 |
-374.00 |
-412.00 |
1746.10 |
| medium_08 |
4635.00 |
4635.00 |
-992.00 |
5332.00 |
-999.00 |
16.00 |
-987.00 |
1662.90 |
| medium_09 |
-993.00 |
-978.00 |
-976.00 |
-996.00 |
-978.00 |
-949.00 |
-18.00 |
-841.10 |
| medium_10 |
6039.00 |
5797.00 |
3548.00 |
8720.00 |
-997.00 |
-983.00 |
-802.00 |
3046.00 |
| large_01 |
9808.00 |
9808.00 |
8348.00 |
-997.00 |
-1000.00 |
-976.00 |
-680.00 |
3473.00 |
| large_02 |
5397.00 |
5397.00 |
5397.00 |
5397.00 |
-999.00 |
-889.00 |
-984.00 |
2673.70 |
| large_03 |
4587.00 |
12093.00 |
12093.00 |
-999.00 |
-1000.00 |
-206.00 |
-290.00 |
3754.00 |
| large_04 |
14813.00 |
14813.00 |
14813.00 |
16206.00 |
16206.00 |
51.00 |
709.00 |
11087.30 |
| large_05 |
8037.00 |
8037.00 |
-996.00 |
-1000.00 |
8037.00 |
-606.00 |
-553.00 |
2993.70 |
| large_06 |
5216.00 |
-982.00 |
-983.00 |
7358.00 |
-1000.00 |
-970.00 |
-713.00 |
1132.30 |
| large_07 |
8287.00 |
-992.00 |
-972.00 |
-1000.00 |
8287.00 |
-558.00 |
-593.00 |
1779.90 |
| large_08 |
-968.00 |
-968.00 |
-995.00 |
-968.00 |
-996.00 |
-973.00 |
-974.00 |
-977.40 |
| large_09 |
-940.00 |
-969.00 |
-961.00 |
-988.00 |
-994.00 |
-980.00 |
-966.00 |
-971.10 |
| large_10 |
2832.00 |
2223.00 |
6271.00 |
2223.00 |
5037.00 |
-899.00 |
-729.00 |
2422.60 |
| Average |
6171.60 |
5919.40 |
4756.80 |
3919.70 |
2913.50 |
-480.80 |
-486.40 |
3244.80 |
Total Score
|
qlearn |
exploit |
near |
explore |
far |
random |
example |
Total |
| small_01 |
5865.00 |
5107.00 |
2762.00 |
-1000.00 |
2762.00 |
-506.00 |
-158.00 |
14832.00 |
| small_02 |
12395.00 |
12395.00 |
12395.00 |
12395.00 |
-1000.00 |
-146.00 |
-35.00 |
48399.00 |
| small_03 |
3688.00 |
3688.00 |
3121.00 |
-1000.00 |
-999.00 |
-350.00 |
-432.00 |
7716.00 |
| small_04 |
7372.00 |
7372.00 |
7372.00 |
5650.00 |
8749.00 |
315.00 |
99.00 |
36929.00 |
| small_05 |
11810.00 |
11810.00 |
11810.00 |
11810.00 |
9081.00 |
424.00 |
400.00 |
57145.00 |
| small_06 |
4374.00 |
4374.00 |
4374.00 |
5101.00 |
6375.00 |
-463.00 |
-443.00 |
23692.00 |
| small_07 |
7918.00 |
7918.00 |
5826.00 |
7918.00 |
7542.00 |
-725.00 |
-602.00 |
35795.00 |
| small_08 |
6860.00 |
6860.00 |
17074.00 |
19200.00 |
19200.00 |
107.00 |
85.00 |
69386.00 |
| small_09 |
8988.00 |
8988.00 |
7671.00 |
6705.00 |
-998.00 |
-531.00 |
-411.00 |
30412.00 |
| small_10 |
5741.00 |
7137.00 |
3422.00 |
-999.00 |
5741.00 |
-379.00 |
-797.00 |
19866.00 |
| medium_01 |
10059.00 |
10059.00 |
10059.00 |
9810.00 |
8344.00 |
204.00 |
-160.00 |
48375.00 |
| medium_02 |
6056.00 |
7774.00 |
-997.00 |
-999.00 |
-999.00 |
-789.00 |
-985.00 |
9061.00 |
| medium_03 |
5805.00 |
2986.00 |
2986.00 |
4248.00 |
-999.00 |
-455.00 |
-595.00 |
13976.00 |
| medium_04 |
5050.00 |
7559.00 |
5264.00 |
-998.00 |
-1000.00 |
-541.00 |
-592.00 |
14742.00 |
| medium_05 |
4783.00 |
4783.00 |
-997.00 |
-1000.00 |
-999.00 |
-605.00 |
-990.00 |
4975.00 |
| medium_06 |
6805.00 |
6029.00 |
6076.00 |
-999.00 |
-1000.00 |
-687.00 |
-985.00 |
15239.00 |
| medium_07 |
4828.00 |
4828.00 |
892.00 |
3461.00 |
-1000.00 |
-374.00 |
-412.00 |
12223.00 |
| medium_08 |
4635.00 |
4635.00 |
-992.00 |
5332.00 |
-999.00 |
16.00 |
-987.00 |
11640.00 |
| medium_09 |
-993.00 |
-978.00 |
-976.00 |
-996.00 |
-978.00 |
-949.00 |
-18.00 |
-5888.00 |
| medium_10 |
6039.00 |
5797.00 |
3548.00 |
8720.00 |
-997.00 |
-983.00 |
-802.00 |
21322.00 |
| large_01 |
9808.00 |
9808.00 |
8348.00 |
-997.00 |
-1000.00 |
-976.00 |
-680.00 |
24311.00 |
| large_02 |
5397.00 |
5397.00 |
5397.00 |
5397.00 |
-999.00 |
-889.00 |
-984.00 |
18716.00 |
| large_03 |
4587.00 |
12093.00 |
12093.00 |
-999.00 |
-1000.00 |
-206.00 |
-290.00 |
26278.00 |
| large_04 |
14813.00 |
14813.00 |
14813.00 |
16206.00 |
16206.00 |
51.00 |
709.00 |
77611.00 |
| large_05 |
8037.00 |
8037.00 |
-996.00 |
-1000.00 |
8037.00 |
-606.00 |
-553.00 |
20956.00 |
| large_06 |
5216.00 |
-982.00 |
-983.00 |
7358.00 |
-1000.00 |
-970.00 |
-713.00 |
7926.00 |
| large_07 |
8287.00 |
-992.00 |
-972.00 |
-1000.00 |
8287.00 |
-558.00 |
-593.00 |
12459.00 |
| large_08 |
-968.00 |
-968.00 |
-995.00 |
-968.00 |
-996.00 |
-973.00 |
-974.00 |
-6842.00 |
| large_09 |
-940.00 |
-969.00 |
-961.00 |
-988.00 |
-994.00 |
-980.00 |
-966.00 |
-6798.00 |
| large_10 |
2832.00 |
2223.00 |
6271.00 |
2223.00 |
5037.00 |
-899.00 |
-729.00 |
16958.00 |
| Total |
185147.00 |
177581.00 |
142705.00 |
117591.00 |
87404.00 |
-14423.00 |
-14593.00 |
681412.00 |
Transitions Used During Learning
|
qlearn |
exploit |
near |
explore |
far |
random |
example |
Total |
| small_01 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
27.00 |
500027.00 |
| small_02 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
55.00 |
500055.00 |
| small_03 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
7.00 |
500007.00 |
| small_04 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
14.00 |
500014.00 |
| small_05 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
14.00 |
500014.00 |
| small_06 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
5.00 |
500005.00 |
| small_07 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
225.00 |
500225.00 |
| small_08 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
22.00 |
500022.00 |
| small_09 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
43.00 |
500043.00 |
| small_10 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
16.00 |
500016.00 |
| medium_01 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
13.00 |
500013.00 |
| medium_02 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
902.00 |
500902.00 |
| medium_03 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
36.00 |
500036.00 |
| medium_04 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
9.00 |
500009.00 |
| medium_05 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
26.00 |
500026.00 |
| medium_06 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
9.00 |
500009.00 |
| medium_07 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
5.00 |
500005.00 |
| medium_08 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
3.00 |
500003.00 |
| medium_09 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
14.00 |
500014.00 |
| medium_10 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
61.00 |
500061.00 |
| large_01 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
166.00 |
500166.00 |
| large_02 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
136.00 |
500136.00 |
| large_03 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
81.00 |
500081.00 |
| large_04 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
8.00 |
500008.00 |
| large_05 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
14.00 |
500014.00 |
| large_06 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
19.00 |
500019.00 |
| large_07 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
7.00 |
500007.00 |
| large_08 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
9.00 |
500009.00 |
| large_09 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
7.00 |
500007.00 |
| large_10 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
100000.00 |
0.00 |
9.00 |
500009.00 |
| Total |
3000000.00 |
3000000.00 |
3000000.00 |
3000000.00 |
3000000.00 |
0.00 |
1962.00 |
15001962.00 |
Time Spent Learning
|
qlearn |
exploit |
near |
explore |
far |
random |
example |
Total |
| small_01 |
58.00 |
73.00 |
67.00 |
100.00 |
48.00 |
1.00 |
12.00 |
359.00 |
| small_02 |
41.00 |
51.00 |
46.00 |
48.00 |
60.00 |
0.00 |
0.00 |
246.00 |
| small_03 |
40.00 |
47.00 |
38.00 |
29.00 |
44.00 |
0.00 |
0.00 |
198.00 |
| small_04 |
42.00 |
50.00 |
41.00 |
56.00 |
37.00 |
0.00 |
0.00 |
226.00 |
| small_05 |
52.00 |
56.00 |
50.00 |
37.00 |
45.00 |
0.00 |
0.00 |
240.00 |
| small_06 |
37.00 |
64.00 |
39.00 |
40.00 |
51.00 |
0.00 |
0.00 |
231.00 |
| small_07 |
59.00 |
55.00 |
58.00 |
32.00 |
57.00 |
0.00 |
0.00 |
261.00 |
| small_08 |
44.00 |
48.00 |
47.00 |
41.00 |
45.00 |
0.00 |
0.00 |
225.00 |
| small_09 |
61.00 |
75.00 |
52.00 |
44.00 |
84.00 |
0.00 |
0.00 |
316.00 |
| small_10 |
50.00 |
69.00 |
62.00 |
50.00 |
55.00 |
0.00 |
0.00 |
286.00 |
| medium_01 |
116.00 |
121.00 |
80.00 |
68.00 |
100.00 |
0.00 |
0.00 |
485.00 |
| medium_02 |
85.00 |
128.00 |
87.00 |
240.00 |
109.00 |
0.00 |
0.00 |
649.00 |
| medium_03 |
91.00 |
110.00 |
96.00 |
69.00 |
93.00 |
0.00 |
0.00 |
459.00 |
| medium_04 |
79.00 |
97.00 |
75.00 |
76.00 |
73.00 |
0.00 |
0.00 |
400.00 |
| medium_05 |
101.00 |
108.00 |
88.00 |
71.00 |
92.00 |
0.00 |
0.00 |
460.00 |
| medium_06 |
110.00 |
102.00 |
91.00 |
51.00 |
87.00 |
0.00 |
0.00 |
441.00 |
| medium_07 |
66.00 |
86.00 |
80.00 |
63.00 |
58.00 |
0.00 |
0.00 |
353.00 |
| medium_08 |
109.00 |
149.00 |
98.00 |
94.00 |
118.00 |
0.00 |
0.00 |
568.00 |
| medium_09 |
97.00 |
117.00 |
96.00 |
113.00 |
103.00 |
0.00 |
0.00 |
526.00 |
| medium_10 |
110.00 |
104.00 |
93.00 |
67.00 |
91.00 |
0.00 |
0.00 |
465.00 |
| large_01 |
112.00 |
155.00 |
108.00 |
101.00 |
97.00 |
0.00 |
0.00 |
573.00 |
| large_02 |
94.00 |
113.00 |
93.00 |
94.00 |
115.00 |
0.00 |
0.00 |
509.00 |
| large_03 |
118.00 |
123.00 |
127.00 |
72.00 |
113.00 |
0.00 |
0.00 |
553.00 |
| large_04 |
112.00 |
113.00 |
107.00 |
75.00 |
113.00 |
0.00 |
0.00 |
520.00 |
| large_05 |
89.00 |
108.00 |
135.00 |
77.00 |
104.00 |
0.00 |
0.00 |
513.00 |
| large_06 |
114.00 |
159.00 |
97.00 |
87.00 |
100.00 |
0.00 |
0.00 |
557.00 |
| large_07 |
169.00 |
145.00 |
111.00 |
94.00 |
133.00 |
0.00 |
0.00 |
652.00 |
| large_08 |
126.00 |
136.00 |
107.00 |
94.00 |
113.00 |
0.00 |
0.00 |
576.00 |
| large_09 |
129.00 |
152.00 |
120.00 |
150.00 |
120.00 |
0.00 |
0.00 |
671.00 |
| large_10 |
86.00 |
189.00 |
82.00 |
83.00 |
85.00 |
0.00 |
0.00 |
525.00 |
| Total |
2597.00 |
3103.00 |
2471.00 |
2316.00 |
2543.00 |
1.00 |
12.00 |
13043.00 |