1
0
mirror of https://github.com/gryf/coach.git synced 2026-04-05 03:53:32 +02:00

Trace tests update

This commit is contained in:
Shadi Endrawis
2018-08-20 13:01:17 +03:00
parent c1f428666e
commit 3abb6cd415
99 changed files with 12876 additions and 39 deletions

View File

@@ -0,0 +1,31 @@
Episode #,Training Iter,In Heatup,ER #Transitions,ER #Episodes,Episode Length,Total steps,Epsilon,Shaped Training Reward,Training Reward,Update Target Network,Evaluation Reward,Shaped Evaluation Reward,Success Rate,Loss/Mean,Loss/Stdev,Loss/Max,Loss/Min,Learning Rate/Mean,Learning Rate/Stdev,Learning Rate/Max,Learning Rate/Min,Grads (unclipped)/Mean,Grads (unclipped)/Stdev,Grads (unclipped)/Max,Grads (unclipped)/Min,Q/Mean,Q/Stdev,Q/Max,Q/Min
1,0.0,1.0,486.0,486.0,486.0,486.0,1.0,,,0.0,,,,,,,,,,,,,,,,,,,
2,0.0,1.0,573.0,573.0,87.0,573.0,1.0,,,0.0,,,,,,,,,,,,,,,,,,,
3,0.0,1.0,722.0,722.0,149.0,722.0,1.0,,,0.0,,,,,,,,,,,,,,,,,,,
4,0.0,1.0,1057.0,1057.0,335.0,1057.0,1.0,,,0.0,,,,,,,,,,,,,,,,,,,
5,51.0,0.0,1259.0,1259.0,202.0,1259.0,0.999818200000006,3.0,35.0,0.0,,,,0.002354268465055879,0.0022267908155453207,0.008399246260523796,8.872663784131873e-06,0.00025,0.0,0.00025,0.00025,0.007744235,0.005350461,0.022665123,0.0008465818,,,,
6,81.0,0.0,1382.0,1382.0,123.0,1382.0,0.9997075000000096,4.0,55.0,0.0,,,,0.006926822468327979,0.002244478491556321,0.0135076642036438,0.0033381427638232712,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.018759595,0.0053872466,0.032931123,0.009214188,,,,
7,152.0,0.0,1665.0,1665.0,283.0,1665.0,0.9994528000000179,2.0,45.0,0.0,,,,0.00354002532754159,0.0019023348592878372,0.009204687550663948,0.00030229013646021485,0.00025,0.0,0.00025,0.00025,0.01304985,0.0035053138,0.024019292,0.008035132,,,,
8,208.0,0.0,1887.0,1887.0,222.0,1887.0,0.9992530000000246,1.0,20.0,0.0,,,,0.003386984325646024,0.0014584238962574282,0.006831846199929714,0.0003159668995067477,0.00025,0.0,0.00025,0.00025,0.013196401000000002,0.0034898983,0.025287742000000002,0.008569226,,,,
9,220.0,0.0,1938.0,1938.0,51.0,1938.0,0.999207100000026,0.0,0.0,0.0,,,,0.003167361059846977,0.0015483758671841056,0.006221367511898279,0.0007139326771721244,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.013424491,0.002968179,0.0176331,0.009279029,,,,
10,269.0,0.0,2131.0,2131.0,193.0,2131.0,0.9990334000000318,1.0,5.0,0.0,,,,0.0032611473170061573,0.0016850956682255482,0.007028852589428425,0.00020222167950123549,0.00025,0.0,0.00025,0.00025,0.013227931,0.0036521524,0.021845128,0.007127245999999999,,,,
11,363.0,0.0,2510.0,2510.0,379.0,2510.0,0.9986923000000429,8.0,100.0,0.0,,,,0.003091246536449886,0.001322660534422889,0.006632269825786352,0.00032261264277622104,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.013847044,0.0034531087,0.023722986,0.008786425,0.08158561,0.036171492,0.17906709,0.03910739
12,403.0,0.0,2670.0,2670.0,160.0,2670.0,0.9985483000000478,1.0,25.0,0.0,,,,0.0033887081764987672,0.001894344488589778,0.00896457675844431,0.00035247692721895874,0.00025,0.0,0.00025,0.00025,0.014799103000000001,0.005142509,0.03727644,0.008755262,,,,
13,566.0,0.0,3319.0,3319.0,649.0,3319.0,0.997964200000067,20.0,515.0,0.0,,,,0.0033814117187088463,0.001794335243639714,0.00981593132019043,0.00033476535463705664,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.01542785,0.0042213122,0.035808,0.008857572,,,,
14,608.0,0.0,3490.0,3490.0,171.0,3490.0,0.997810300000072,2.0,15.0,0.0,,,,0.00307327011181596,0.0014598479376536175,0.007876500487327577,0.0004184547869954258,0.00025,0.0,0.00025,0.00025,0.015182586000000001,0.003907353,0.025957266,0.008718804,,,,
15,661.0,0.0,3699.0,3699.0,209.0,3699.0,0.9976222000000784,3.0,30.0,0.0,,,,0.003574654932204142,0.0013611143826604485,0.006663748994469643,0.0012790606124326589,0.00025,0.0,0.00025,0.00025,0.015538703000000001,0.0037677127,0.02521416,0.009612316999999999,,,,
16,699.0,0.0,3853.0,3853.0,154.0,3853.0,0.9974836000000828,3.0,75.0,0.0,,,,0.003063707425577664,0.0016034075091713835,0.007304192055016756,0.00034941814374178653,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.016172405,0.0048504383,0.027080176,0.008548103,,,,
17,743.0,0.0,4030.0,4030.0,177.0,4030.0,0.997324300000088,3.0,30.0,0.0,,,,0.00310047399133592,0.0014594212466929055,0.0075475480407476425,0.0003596151655074209,0.00025,0.0,0.00025,0.00025,0.015252826,0.0038106788,0.029333811,0.009897261,0.109428376,0.08142622,0.25112388,0.031323746
18,763.0,0.0,4107.0,4107.0,77.0,4107.0,0.9972550000000904,2.0,15.0,0.0,,,,0.00320658921264112,0.0014737941431521605,0.006449719425290823,0.0006320171523839235,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.015207966000000002,0.0041951295,0.026854733,0.009781642,,,,
19,799.0,0.0,4254.0,4254.0,147.0,4254.0,0.9971227000000948,2.0,35.0,0.0,,,,0.003265373379690573,0.0015747774825930286,0.006731272675096989,0.0007752227247692645,0.00025,0.0,0.00025,0.00025,0.016477453,0.0043514105,0.030398313,0.009153037,,,,
20,857.0,0.0,4485.0,4485.0,231.0,4485.0,0.9969148000001016,7.0,110.0,0.0,,,,0.0033697776560639514,0.0017829018890948177,0.009337665513157845,0.0005270092515274882,0.00025,0.0,0.00025,0.00025,0.017007816999999998,0.004538108,0.034457795,0.0102955345,0.086831845,0.028143487999999998,0.11529497,0.041701294
21,954.0,0.0,4871.0,4871.0,386.0,4871.0,0.9965674000001129,1.0,10.0,0.0,,,,0.0032097528227748944,0.0014270266361265948,0.0072808810509741315,0.00034487116499803966,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.016735202,0.0040815175,0.029879992999999997,0.009203656999999999,0.08063345,0.06771858,0.22763099,-0.04870935
22,987.0,0.0,5006.0,5006.0,135.0,5006.0,0.9964459000001171,1.0,15.0,0.0,,,,0.00348929021944941,0.0013416678040725266,0.006667369976639748,0.0004941442748531699,0.00025,0.0,0.00025,0.00025,0.017052516,0.0037629176,0.02555473,0.010013681,,,,
23,1038.0,0.0,5208.0,5208.0,202.0,5208.0,0.9962641000001229,3.0,30.0,0.0,,,,0.003096698048323685,0.001467369498213491,0.006518170703202486,0.0005598508287221193,0.00025,0.0,0.00025,0.00025,0.017208265,0.004186028,0.02688086,0.009457254,,,,
24,1054.0,0.0,5274.0,5274.0,66.0,5274.0,0.9962047000001251,2.0,15.0,0.0,,,,0.0023996760137379174,0.0011494210259765632,0.005033135414123535,0.00040235067717731,0.00025,0.0,0.00025,0.00025,0.014471052,0.0028194014,0.018233253,0.0090312585,0.09159353,0.073366776,0.19782996,-0.007508415
25,1076.0,0.0,5359.0,5359.0,85.0,5359.0,0.9961282000001276,1.0,15.0,0.0,,,,0.0031479224470041863,0.0018338206488306352,0.008050543256103992,0.00018393099890090525,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.016573252,0.0058718068000000005,0.02915352,0.005962694,,,,
26,1133.0,0.0,5587.0,5587.0,228.0,5587.0,0.9959230000001342,4.0,50.0,0.0,,,,0.002919742441327687,0.001194507040554492,0.006624207831919193,0.00057441764511168,0.00025,0.0,0.00025,0.00025,0.016612988000000002,0.00332599,0.026537797999999998,0.010939502,0.09447273,0.045939725,0.15817265,0.033776283
27,1153.0,0.0,5667.0,5667.0,80.0,5667.0,0.9958510000001366,1.0,15.0,0.0,,,,0.00301869151298888,0.0013370276603479855,0.006056639365851879,0.001242607831954956,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.016518693,0.003245745,0.022646153,0.010498283999999998,,,,
28,1173.0,0.0,5749.0,5749.0,82.0,5749.0,0.995777200000139,0.0,0.0,0.0,,,,0.0031465753330849108,0.0012105911527881745,0.0058187893591821185,0.0013689068146049974,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.018286983,0.005796103299999999,0.036277987000000005,0.011089685,,,,
29,1218.0,0.0,5928.0,5928.0,179.0,5928.0,0.9956161000001444,1.0,5.0,0.0,,,,0.0031859539345734647,0.001230199051850356,0.005495925433933735,0.0007681638235226274,0.00025,0.0,0.00025,0.00025,0.017322628,0.004681325,0.032449782,0.008565956999999999,,,,
30,1232.0,0.0,5983.0,5983.0,55.0,5983.0,0.9955666000001461,2.0,15.0,0.0,,,,0.0033092185206312157,0.0009492089431610681,0.0049632079899311074,0.0016535777831450105,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.016791698,0.0036438016999999997,0.024807067999999998,0.012081898999999998,,,,
1 Episode # Training Iter In Heatup ER #Transitions ER #Episodes Episode Length Total steps Epsilon Shaped Training Reward Training Reward Update Target Network Evaluation Reward Shaped Evaluation Reward Success Rate Loss/Mean Loss/Stdev Loss/Max Loss/Min Learning Rate/Mean Learning Rate/Stdev Learning Rate/Max Learning Rate/Min Grads (unclipped)/Mean Grads (unclipped)/Stdev Grads (unclipped)/Max Grads (unclipped)/Min Q/Mean Q/Stdev Q/Max Q/Min
2 1 0.0 1.0 486.0 486.0 486.0 486.0 1.0 0.0
3 2 0.0 1.0 573.0 573.0 87.0 573.0 1.0 0.0
4 3 0.0 1.0 722.0 722.0 149.0 722.0 1.0 0.0
5 4 0.0 1.0 1057.0 1057.0 335.0 1057.0 1.0 0.0
6 5 51.0 0.0 1259.0 1259.0 202.0 1259.0 0.999818200000006 3.0 35.0 0.0 0.002354268465055879 0.0022267908155453207 0.008399246260523796 8.872663784131873e-06 0.00025 0.0 0.00025 0.00025 0.007744235 0.005350461 0.022665123 0.0008465818
7 6 81.0 0.0 1382.0 1382.0 123.0 1382.0 0.9997075000000096 4.0 55.0 0.0 0.006926822468327979 0.002244478491556321 0.0135076642036438 0.0033381427638232712 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.018759595 0.0053872466 0.032931123 0.009214188
8 7 152.0 0.0 1665.0 1665.0 283.0 1665.0 0.9994528000000179 2.0 45.0 0.0 0.00354002532754159 0.0019023348592878372 0.009204687550663948 0.00030229013646021485 0.00025 0.0 0.00025 0.00025 0.01304985 0.0035053138 0.024019292 0.008035132
9 8 208.0 0.0 1887.0 1887.0 222.0 1887.0 0.9992530000000246 1.0 20.0 0.0 0.003386984325646024 0.0014584238962574282 0.006831846199929714 0.0003159668995067477 0.00025 0.0 0.00025 0.00025 0.013196401000000002 0.0034898983 0.025287742000000002 0.008569226
10 9 220.0 0.0 1938.0 1938.0 51.0 1938.0 0.999207100000026 0.0 0.0 0.0 0.003167361059846977 0.0015483758671841056 0.006221367511898279 0.0007139326771721244 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.013424491 0.002968179 0.0176331 0.009279029
11 10 269.0 0.0 2131.0 2131.0 193.0 2131.0 0.9990334000000318 1.0 5.0 0.0 0.0032611473170061573 0.0016850956682255482 0.007028852589428425 0.00020222167950123549 0.00025 0.0 0.00025 0.00025 0.013227931 0.0036521524 0.021845128 0.007127245999999999
12 11 363.0 0.0 2510.0 2510.0 379.0 2510.0 0.9986923000000429 8.0 100.0 0.0 0.003091246536449886 0.001322660534422889 0.006632269825786352 0.00032261264277622104 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.013847044 0.0034531087 0.023722986 0.008786425 0.08158561 0.036171492 0.17906709 0.03910739
13 12 403.0 0.0 2670.0 2670.0 160.0 2670.0 0.9985483000000478 1.0 25.0 0.0 0.0033887081764987672 0.001894344488589778 0.00896457675844431 0.00035247692721895874 0.00025 0.0 0.00025 0.00025 0.014799103000000001 0.005142509 0.03727644 0.008755262
14 13 566.0 0.0 3319.0 3319.0 649.0 3319.0 0.997964200000067 20.0 515.0 0.0 0.0033814117187088463 0.001794335243639714 0.00981593132019043 0.00033476535463705664 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.01542785 0.0042213122 0.035808 0.008857572
15 14 608.0 0.0 3490.0 3490.0 171.0 3490.0 0.997810300000072 2.0 15.0 0.0 0.00307327011181596 0.0014598479376536175 0.007876500487327577 0.0004184547869954258 0.00025 0.0 0.00025 0.00025 0.015182586000000001 0.003907353 0.025957266 0.008718804
16 15 661.0 0.0 3699.0 3699.0 209.0 3699.0 0.9976222000000784 3.0 30.0 0.0 0.003574654932204142 0.0013611143826604485 0.006663748994469643 0.0012790606124326589 0.00025 0.0 0.00025 0.00025 0.015538703000000001 0.0037677127 0.02521416 0.009612316999999999
17 16 699.0 0.0 3853.0 3853.0 154.0 3853.0 0.9974836000000828 3.0 75.0 0.0 0.003063707425577664 0.0016034075091713835 0.007304192055016756 0.00034941814374178653 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.016172405 0.0048504383 0.027080176 0.008548103
18 17 743.0 0.0 4030.0 4030.0 177.0 4030.0 0.997324300000088 3.0 30.0 0.0 0.00310047399133592 0.0014594212466929055 0.0075475480407476425 0.0003596151655074209 0.00025 0.0 0.00025 0.00025 0.015252826 0.0038106788 0.029333811 0.009897261 0.109428376 0.08142622 0.25112388 0.031323746
19 18 763.0 0.0 4107.0 4107.0 77.0 4107.0 0.9972550000000904 2.0 15.0 0.0 0.00320658921264112 0.0014737941431521605 0.006449719425290823 0.0006320171523839235 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.015207966000000002 0.0041951295 0.026854733 0.009781642
20 19 799.0 0.0 4254.0 4254.0 147.0 4254.0 0.9971227000000948 2.0 35.0 0.0 0.003265373379690573 0.0015747774825930286 0.006731272675096989 0.0007752227247692645 0.00025 0.0 0.00025 0.00025 0.016477453 0.0043514105 0.030398313 0.009153037
21 20 857.0 0.0 4485.0 4485.0 231.0 4485.0 0.9969148000001016 7.0 110.0 0.0 0.0033697776560639514 0.0017829018890948177 0.009337665513157845 0.0005270092515274882 0.00025 0.0 0.00025 0.00025 0.017007816999999998 0.004538108 0.034457795 0.0102955345 0.086831845 0.028143487999999998 0.11529497 0.041701294
22 21 954.0 0.0 4871.0 4871.0 386.0 4871.0 0.9965674000001129 1.0 10.0 0.0 0.0032097528227748944 0.0014270266361265948 0.0072808810509741315 0.00034487116499803966 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.016735202 0.0040815175 0.029879992999999997 0.009203656999999999 0.08063345 0.06771858 0.22763099 -0.04870935
23 22 987.0 0.0 5006.0 5006.0 135.0 5006.0 0.9964459000001171 1.0 15.0 0.0 0.00348929021944941 0.0013416678040725266 0.006667369976639748 0.0004941442748531699 0.00025 0.0 0.00025 0.00025 0.017052516 0.0037629176 0.02555473 0.010013681
24 23 1038.0 0.0 5208.0 5208.0 202.0 5208.0 0.9962641000001229 3.0 30.0 0.0 0.003096698048323685 0.001467369498213491 0.006518170703202486 0.0005598508287221193 0.00025 0.0 0.00025 0.00025 0.017208265 0.004186028 0.02688086 0.009457254
25 24 1054.0 0.0 5274.0 5274.0 66.0 5274.0 0.9962047000001251 2.0 15.0 0.0 0.0023996760137379174 0.0011494210259765632 0.005033135414123535 0.00040235067717731 0.00025 0.0 0.00025 0.00025 0.014471052 0.0028194014 0.018233253 0.0090312585 0.09159353 0.073366776 0.19782996 -0.007508415
26 25 1076.0 0.0 5359.0 5359.0 85.0 5359.0 0.9961282000001276 1.0 15.0 0.0 0.0031479224470041863 0.0018338206488306352 0.008050543256103992 0.00018393099890090525 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.016573252 0.0058718068000000005 0.02915352 0.005962694
27 26 1133.0 0.0 5587.0 5587.0 228.0 5587.0 0.9959230000001342 4.0 50.0 0.0 0.002919742441327687 0.001194507040554492 0.006624207831919193 0.00057441764511168 0.00025 0.0 0.00025 0.00025 0.016612988000000002 0.00332599 0.026537797999999998 0.010939502 0.09447273 0.045939725 0.15817265 0.033776283
28 27 1153.0 0.0 5667.0 5667.0 80.0 5667.0 0.9958510000001366 1.0 15.0 0.0 0.00301869151298888 0.0013370276603479855 0.006056639365851879 0.001242607831954956 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.016518693 0.003245745 0.022646153 0.010498283999999998
29 28 1173.0 0.0 5749.0 5749.0 82.0 5749.0 0.995777200000139 0.0 0.0 0.0 0.0031465753330849108 0.0012105911527881745 0.0058187893591821185 0.0013689068146049974 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.018286983 0.005796103299999999 0.036277987000000005 0.011089685
30 29 1218.0 0.0 5928.0 5928.0 179.0 5928.0 0.9956161000001444 1.0 5.0 0.0 0.0031859539345734647 0.001230199051850356 0.005495925433933735 0.0007681638235226274 0.00025 0.0 0.00025 0.00025 0.017322628 0.004681325 0.032449782 0.008565956999999999
31 30 1232.0 0.0 5983.0 5983.0 55.0 5983.0 0.9955666000001461 2.0 15.0 0.0 0.0033092185206312157 0.0009492089431610681 0.0049632079899311074 0.0016535777831450105 0.0002500000000000001 1.0842021724855042e-19 0.00025 0.00025 0.016791698 0.0036438016999999997 0.024807067999999998 0.012081898999999998