1
0
mirror of https://github.com/gryf/coach.git synced 2026-03-27 22:03:33 +01:00

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,,,,,,,,,,,,,,,,,,,
5,51.0,0.0,1260.0,1260.0,203.0,1260.0,0.9997990300000044,3.0,30.0,0.0,,,,30.53859548708972,44.314682007982455,150.4903564453125,0.16912639141082764,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,6.791042,6.4495187000000005,23.662077,1.2995651000000001,,,,
6,116.0,0.0,1519.0,1519.0,259.0,1519.0,0.99954262000001,3.0,30.0,0.0,,,,31.40286669318493,36.255547758346076,148.12547302246094,0.1828265339136124,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,8.923345,6.8456674,31.171175,1.5896469,,,,
7,154.0,0.0,1673.0,1673.0,154.0,1673.0,0.9993901600000132,0.0,0.0,0.0,,,,22.276954246194734,26.822031462503034,98.48810577392578,0.2816051840782165,4.999999999999999e-05,1.3552527156068802e-20,5e-05,5e-05,9.235014,4.645149,21.968481,3.4494073,,,,
8,188.0,0.0,1809.0,1809.0,136.0,1809.0,0.9992555200000162,0.0,0.0,0.0,,,,19.016328675781978,31.38710695896604,98.0995101928711,0.2720474898815155,5e-05,6.776263578034403e-21,5e-05,5e-05,8.611777,7.304164,30.532827,3.280274,,,,
9,218.0,0.0,1927.0,1927.0,118.0,1927.0,0.9991387000000188,4.0,50.0,0.0,,,,18.11380697687467,29.29193975183291,97.48050689697266,0.2490096986293793,4.999999999999999e-05,1.3552527156068802e-20,5e-05,5e-05,9.569202,8.223543,34.718906,2.933268,,,,
10,239.0,0.0,2013.0,2013.0,86.0,2013.0,0.9990535600000204,1.0,25.0,0.0,,,,23.42363277503423,38.412630669473316,145.73297119140625,0.36567768454551697,5e-05,6.776263578034403e-21,5e-05,5e-05,12.172969,9.590582000000001,44.762127,5.082082700000001,,,,
11,285.0,0.0,2197.0,2197.0,184.0,2197.0,0.9988714000000244,5.0,75.0,0.0,,,,16.187956988163613,30.38507923781825,145.3076934814453,0.281042754650116,5.0000000000000016e-05,1.3552527156068802e-20,5e-05,5e-05,9.950823,8.131824,45.485153000000004,3.1171607999999997,,,,
12,309.0,0.0,2293.0,2293.0,96.0,2293.0,0.9987763600000266,2.0,15.0,0.0,,,,16.55143442377448,26.695402296011764,95.4090576171875,0.2967992722988129,5e-05,0.0,5e-05,5e-05,9.013406,8.831133,46.1924,3.6614769,,,,
13,353.0,0.0,2467.0,2467.0,174.0,2467.0,0.9986041000000304,2.0,35.0,0.0,,,,14.740310977467082,24.52772692149401,97.43923950195312,0.23097966611385345,5.0000000000000016e-05,1.3552527156068802e-20,5e-05,5e-05,8.150308,6.594815700000001,31.787717999999998,2.299897,,,,
14,400.0,0.0,2658.0,2658.0,191.0,2658.0,0.9984150100000344,1.0,25.0,0.0,,,,32.32692400191693,34.86153399624781,98.53972625732422,0.29887062311172485,5.0000000000000016e-05,2.0328790734103208e-20,5e-05,5e-05,15.370679999999998,9.051497,42.453285,3.6067166,0.02061364021675521,0.0067769050257598246,0.0303798052680213,0.009173157039294895
15,420.0,0.0,2737.0,2737.0,79.0,2737.0,0.998336800000036,3.0,30.0,0.0,,,,28.536019751429556,30.448869863836503,93.33609008789062,0.7488499283790588,5e-05,0.0,5e-05,5e-05,22.326626,14.370629999999998,68.70875,11.235919,,,,
16,441.0,0.0,2822.0,2822.0,85.0,2822.0,0.998252650000038,1.0,20.0,0.0,,,,36.1884659301667,31.21200822910139,94.37825775146484,1.1034283638000488,5e-05,6.776263578034403e-21,5e-05,5e-05,27.31245,18.221214,95.95713,16.466019,,,,
17,497.0,0.0,3045.0,3045.0,223.0,3045.0,0.9980318800000428,2.0,30.0,0.0,,,,26.486526499901494,34.31913812205679,133.34033203125,0.8666461110115051,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,25.985167999999998,15.976610999999998,108.36258000000001,12.003894,0.02852728419992369,0.012236517428302918,0.04643445217803673,0.006784821223118342
18,519.0,0.0,3133.0,3133.0,88.0,3133.0,0.9979447600000446,1.0,10.0,0.0,,,,24.17923441258344,26.460502373684182,91.19527435302734,1.1007275581359863,5e-05,6.776263578034403e-21,5e-05,5e-05,25.493132,9.448856,61.914528000000004,15.315972,,,,
19,586.0,0.0,3399.0,3399.0,266.0,3399.0,0.9976814200000504,1.0,15.0,0.0,,,,19.367093969636887,30.53654667888193,138.79338073730472,0.5301144719123839,5.0000000000000016e-05,1.3552527156068802e-20,5e-05,5e-05,21.118656,17.394904999999998,100.10899,6.504474,,,,
20,644.0,0.0,3631.0,3631.0,232.0,3631.0,0.9974517400000552,3.0,30.0,0.0,,,,25.538421301492328,31.2238672301977,95.78995513916016,0.4987463653087616,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,22.084887,15.076464999999999,68.79476,6.562572500000001,0.011964818493931188,0.003264027026202129,0.01488947989215376,0.005563916421342583
21,691.0,0.0,3822.0,3822.0,191.0,3822.0,0.9972626500000594,1.0,5.0,0.0,,,,20.623328632496765,33.08831889922991,171.38589477539062,0.7546992301940918,5.0000000000000016e-05,2.0328790734103208e-20,5e-05,5e-05,26.541094,28.174709999999997,178.12593,10.046588,0.016623225918119714,0.008017604386992635,0.031264341372298075,0.005206719253328628
22,763.0,0.0,4110.0,4110.0,288.0,4110.0,0.9969775300000656,5.0,100.0,0.0,,,,20.81435759945048,30.01146336976207,135.20793151855472,0.9363594651222228,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,27.0196,18.976485999999998,94.14133000000001,12.538364,0.021093616302338584,0.008422554661489449,0.029779689924325795,0.004451211805862841
23,809.0,0.0,4291.0,4291.0,181.0,4291.0,0.9967983400000696,2.0,15.0,0.0,,,,21.38968964504159,34.311319777525604,183.166259765625,0.9679770469665528,5.0000000000000016e-05,1.3552527156068802e-20,5e-05,5e-05,30.949451,19.032299,116.2259,11.671700999999999,,,,
24,832.0,0.0,4384.0,4384.0,93.0,4384.0,0.9967062700000716,2.0,15.0,0.0,,,,28.32993198477704,28.347670124431954,91.72865295410156,0.9682503938674928,4.999999999999999e-05,1.3552527156068802e-20,5e-05,5e-05,30.348809999999997,16.9566,86.52797,12.740698,,,,
25,896.0,0.0,4639.0,4639.0,255.0,4639.0,0.996453820000077,3.0,50.0,0.0,,,,18.012998558580875,24.52147417904464,87.72151947021484,0.6401084065437317,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,27.058616999999998,18.284755999999998,101.61511999999999,8.696746000000001,0.020656253984173718,0.010331667719415127,0.0396795524546178,0.01031893009421765
26,947.0,0.0,4846.0,4846.0,207.0,4846.0,0.9962488900000814,1.0,25.0,0.0,,,,14.372732569189631,22.762665065523,95.37085723876952,0.6254499554634094,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,19.155935,11.796223,53.041355,8.059999000000001,,,,
27,963.0,0.0,4909.0,4909.0,63.0,4909.0,0.9961865200000828,2.0,15.0,0.0,,,,28.088446207344532,33.130785671948516,85.42578887939453,0.6590879559516907,5e-05,0.0,5e-05,5e-05,33.122856,31.809953999999998,107.821754,8.504436,,,,
28,982.0,0.0,4985.0,4985.0,76.0,4985.0,0.9961112800000844,0.0,0.0,0.0,,,,20.659159697984396,24.893216005275328,89.03260803222656,1.0471786260604858,5e-05,0.0,5e-05,5e-05,33.272964,22.24945,102.92742,13.571832,,,,
29,1048.0,0.0,5248.0,5248.0,263.0,5248.0,0.99585091000009,3.0,30.0,0.0,,,,15.208325591954319,24.90270362840188,125.36002349853516,0.6677142381668091,5.0000000000000016e-05,1.3552527156068802e-20,5e-05,5e-05,25.047573,18.866804000000002,122.81957,7.389894,0.007710378308947837,0.0065074938611493095,0.018967705124814528,-0.0025220525433542213
30,1117.0,0.0,5526.0,5526.0,278.0,5526.0,0.9955756900000959,3.0,75.0,0.0,,,,19.523073547992155,24.76386978059245,94.19256591796876,0.43752905726432795,5.0000000000000016e-05,1.3552527156068802e-20,5e-05,5e-05,27.299099,20.852268,93.84137,4.555567,,,,
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 1260.0 1260.0 203.0 1260.0 0.9997990300000044 3.0 30.0 0.0 30.53859548708972 44.314682007982455 150.4903564453125 0.16912639141082764 5.000000000000001e-05 6.776263578034403e-21 5e-05 5e-05 6.791042 6.4495187000000005 23.662077 1.2995651000000001
7 6 116.0 0.0 1519.0 1519.0 259.0 1519.0 0.99954262000001 3.0 30.0 0.0 31.40286669318493 36.255547758346076 148.12547302246094 0.1828265339136124 5.000000000000001e-05 6.776263578034403e-21 5e-05 5e-05 8.923345 6.8456674 31.171175 1.5896469
8 7 154.0 0.0 1673.0 1673.0 154.0 1673.0 0.9993901600000132 0.0 0.0 0.0 22.276954246194734 26.822031462503034 98.48810577392578 0.2816051840782165 4.999999999999999e-05 1.3552527156068802e-20 5e-05 5e-05 9.235014 4.645149 21.968481 3.4494073
9 8 188.0 0.0 1809.0 1809.0 136.0 1809.0 0.9992555200000162 0.0 0.0 0.0 19.016328675781978 31.38710695896604 98.0995101928711 0.2720474898815155 5e-05 6.776263578034403e-21 5e-05 5e-05 8.611777 7.304164 30.532827 3.280274
10 9 218.0 0.0 1927.0 1927.0 118.0 1927.0 0.9991387000000188 4.0 50.0 0.0 18.11380697687467 29.29193975183291 97.48050689697266 0.2490096986293793 4.999999999999999e-05 1.3552527156068802e-20 5e-05 5e-05 9.569202 8.223543 34.718906 2.933268
11 10 239.0 0.0 2013.0 2013.0 86.0 2013.0 0.9990535600000204 1.0 25.0 0.0 23.42363277503423 38.412630669473316 145.73297119140625 0.36567768454551697 5e-05 6.776263578034403e-21 5e-05 5e-05 12.172969 9.590582000000001 44.762127 5.082082700000001
12 11 285.0 0.0 2197.0 2197.0 184.0 2197.0 0.9988714000000244 5.0 75.0 0.0 16.187956988163613 30.38507923781825 145.3076934814453 0.281042754650116 5.0000000000000016e-05 1.3552527156068802e-20 5e-05 5e-05 9.950823 8.131824 45.485153000000004 3.1171607999999997
13 12 309.0 0.0 2293.0 2293.0 96.0 2293.0 0.9987763600000266 2.0 15.0 0.0 16.55143442377448 26.695402296011764 95.4090576171875 0.2967992722988129 5e-05 0.0 5e-05 5e-05 9.013406 8.831133 46.1924 3.6614769
14 13 353.0 0.0 2467.0 2467.0 174.0 2467.0 0.9986041000000304 2.0 35.0 0.0 14.740310977467082 24.52772692149401 97.43923950195312 0.23097966611385345 5.0000000000000016e-05 1.3552527156068802e-20 5e-05 5e-05 8.150308 6.594815700000001 31.787717999999998 2.299897
15 14 400.0 0.0 2658.0 2658.0 191.0 2658.0 0.9984150100000344 1.0 25.0 0.0 32.32692400191693 34.86153399624781 98.53972625732422 0.29887062311172485 5.0000000000000016e-05 2.0328790734103208e-20 5e-05 5e-05 15.370679999999998 9.051497 42.453285 3.6067166 0.02061364021675521 0.0067769050257598246 0.0303798052680213 0.009173157039294895
16 15 420.0 0.0 2737.0 2737.0 79.0 2737.0 0.998336800000036 3.0 30.0 0.0 28.536019751429556 30.448869863836503 93.33609008789062 0.7488499283790588 5e-05 0.0 5e-05 5e-05 22.326626 14.370629999999998 68.70875 11.235919
17 16 441.0 0.0 2822.0 2822.0 85.0 2822.0 0.998252650000038 1.0 20.0 0.0 36.1884659301667 31.21200822910139 94.37825775146484 1.1034283638000488 5e-05 6.776263578034403e-21 5e-05 5e-05 27.31245 18.221214 95.95713 16.466019
18 17 497.0 0.0 3045.0 3045.0 223.0 3045.0 0.9980318800000428 2.0 30.0 0.0 26.486526499901494 34.31913812205679 133.34033203125 0.8666461110115051 5.000000000000001e-05 6.776263578034403e-21 5e-05 5e-05 25.985167999999998 15.976610999999998 108.36258000000001 12.003894 0.02852728419992369 0.012236517428302918 0.04643445217803673 0.006784821223118342
19 18 519.0 0.0 3133.0 3133.0 88.0 3133.0 0.9979447600000446 1.0 10.0 0.0 24.17923441258344 26.460502373684182 91.19527435302734 1.1007275581359863 5e-05 6.776263578034403e-21 5e-05 5e-05 25.493132 9.448856 61.914528000000004 15.315972
20 19 586.0 0.0 3399.0 3399.0 266.0 3399.0 0.9976814200000504 1.0 15.0 0.0 19.367093969636887 30.53654667888193 138.79338073730472 0.5301144719123839 5.0000000000000016e-05 1.3552527156068802e-20 5e-05 5e-05 21.118656 17.394904999999998 100.10899 6.504474
21 20 644.0 0.0 3631.0 3631.0 232.0 3631.0 0.9974517400000552 3.0 30.0 0.0 25.538421301492328 31.2238672301977 95.78995513916016 0.4987463653087616 5.000000000000001e-05 6.776263578034403e-21 5e-05 5e-05 22.084887 15.076464999999999 68.79476 6.562572500000001 0.011964818493931188 0.003264027026202129 0.01488947989215376 0.005563916421342583
22 21 691.0 0.0 3822.0 3822.0 191.0 3822.0 0.9972626500000594 1.0 5.0 0.0 20.623328632496765 33.08831889922991 171.38589477539062 0.7546992301940918 5.0000000000000016e-05 2.0328790734103208e-20 5e-05 5e-05 26.541094 28.174709999999997 178.12593 10.046588 0.016623225918119714 0.008017604386992635 0.031264341372298075 0.005206719253328628
23 22 763.0 0.0 4110.0 4110.0 288.0 4110.0 0.9969775300000656 5.0 100.0 0.0 20.81435759945048 30.01146336976207 135.20793151855472 0.9363594651222228 5.000000000000001e-05 6.776263578034403e-21 5e-05 5e-05 27.0196 18.976485999999998 94.14133000000001 12.538364 0.021093616302338584 0.008422554661489449 0.029779689924325795 0.004451211805862841
24 23 809.0 0.0 4291.0 4291.0 181.0 4291.0 0.9967983400000696 2.0 15.0 0.0 21.38968964504159 34.311319777525604 183.166259765625 0.9679770469665528 5.0000000000000016e-05 1.3552527156068802e-20 5e-05 5e-05 30.949451 19.032299 116.2259 11.671700999999999
25 24 832.0 0.0 4384.0 4384.0 93.0 4384.0 0.9967062700000716 2.0 15.0 0.0 28.32993198477704 28.347670124431954 91.72865295410156 0.9682503938674928 4.999999999999999e-05 1.3552527156068802e-20 5e-05 5e-05 30.348809999999997 16.9566 86.52797 12.740698
26 25 896.0 0.0 4639.0 4639.0 255.0 4639.0 0.996453820000077 3.0 50.0 0.0 18.012998558580875 24.52147417904464 87.72151947021484 0.6401084065437317 5.000000000000001e-05 6.776263578034403e-21 5e-05 5e-05 27.058616999999998 18.284755999999998 101.61511999999999 8.696746000000001 0.020656253984173718 0.010331667719415127 0.0396795524546178 0.01031893009421765
27 26 947.0 0.0 4846.0 4846.0 207.0 4846.0 0.9962488900000814 1.0 25.0 0.0 14.372732569189631 22.762665065523 95.37085723876952 0.6254499554634094 5.000000000000001e-05 6.776263578034403e-21 5e-05 5e-05 19.155935 11.796223 53.041355 8.059999000000001
28 27 963.0 0.0 4909.0 4909.0 63.0 4909.0 0.9961865200000828 2.0 15.0 0.0 28.088446207344532 33.130785671948516 85.42578887939453 0.6590879559516907 5e-05 0.0 5e-05 5e-05 33.122856 31.809953999999998 107.821754 8.504436
29 28 982.0 0.0 4985.0 4985.0 76.0 4985.0 0.9961112800000844 0.0 0.0 0.0 20.659159697984396 24.893216005275328 89.03260803222656 1.0471786260604858 5e-05 0.0 5e-05 5e-05 33.272964 22.24945 102.92742 13.571832
30 29 1048.0 0.0 5248.0 5248.0 263.0 5248.0 0.99585091000009 3.0 30.0 0.0 15.208325591954319 24.90270362840188 125.36002349853516 0.6677142381668091 5.0000000000000016e-05 1.3552527156068802e-20 5e-05 5e-05 25.047573 18.866804000000002 122.81957 7.389894 0.007710378308947837 0.0065074938611493095 0.018967705124814528 -0.0025220525433542213
31 30 1117.0 0.0 5526.0 5526.0 278.0 5526.0 0.9955756900000959 3.0 75.0 0.0 19.523073547992155 24.76386978059245 94.19256591796876 0.43752905726432795 5.0000000000000016e-05 1.3552527156068802e-20 5e-05 5e-05 27.299099 20.852268 93.84137 4.555567