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