1
0
mirror of https://github.com/gryf/coach.git synced 2026-03-10 19:45:48 +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,,,,3.931728353687361,1.7148335424993695e-05,3.9317572116851807,3.931634187698364,0.00025,0.0,0.00025,0.00025,0.0015541904000000001,0.0023056455,0.009599385,0.0007559575999999999,,,,
6,116.0,0.0,1519.0,1519.0,259.0,1519.0,0.99954262000001,3.0,30.0,0.0,,,,3.9316723786867582,5.269867767456892e-05,3.9317219257354736,3.9313907623291016,0.00025,0.0,0.00025,0.00025,0.001739312,0.0026554922,0.009864504,0.00067749363,,,,
7,154.0,0.0,1673.0,1673.0,154.0,1673.0,0.9993901600000132,0.0,0.0,0.0,,,,3.931619857486925,6.473394968283058e-05,3.9316527843475337,3.931235074996948,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0012083224,0.0019307991,0.009499238,0.0006370891400000001,,,,
8,188.0,0.0,1809.0,1809.0,136.0,1809.0,0.9992555200000162,0.0,0.0,0.0,,,,3.931548202739042,7.783996401137547e-05,3.9316082000732417,3.9312365055084233,0.00025,0.0,0.00025,0.00025,0.0022799673,0.0033626328000000002,0.01030305,0.0006125771299999999,,,,
9,218.0,0.0,1927.0,1927.0,118.0,1927.0,0.9991387000000188,4.0,50.0,0.0,,,,3.9314806302388514,0.00010239504684735038,3.931550741195679,3.931047201156616,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0016353407000000001,0.002778357,0.01035096,0.0005981442500000001,,,,
10,239.0,0.0,2013.0,2013.0,86.0,2013.0,0.9990535600000204,1.0,25.0,0.0,,,,3.9313772519429526,0.00020685918056109227,3.931517362594605,3.9308536052703857,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0034886056,0.004297202,0.010684523999999999,0.00061402726,,,,
11,285.0,0.0,2197.0,2197.0,184.0,2197.0,0.9988714000000244,5.0,75.0,0.0,,,,3.9313522369965264,7.248832757213434e-05,3.931442975997925,3.931007385253906,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0017790395999999998,0.0030002112,0.011006265,0.0006065490000000001,,,,
12,309.0,0.0,2293.0,2293.0,96.0,2293.0,0.9987763600000266,2.0,15.0,0.0,,,,3.931213736534119,0.0002593847407516344,3.93136215209961,3.9304351806640634,0.00025,0.0,0.00025,0.00025,0.0028233638,0.0041352687,0.011190076,0.0005888872,,,,
13,353.0,0.0,2467.0,2467.0,174.0,2467.0,0.9986041000000304,2.0,35.0,0.0,,,,3.9310338009487498,0.0002957116497356457,3.9312725067138667,3.929877519607544,0.00025,0.0,0.00025,0.00025,0.0030289008,0.0042545744,0.012507513,0.0006166726000000001,,,,
14,406.0,0.0,2680.0,2680.0,213.0,2680.0,0.9983932300000348,3.0,60.0,0.0,,,,3.930882449419993,0.00035235950786128846,3.9310703277587886,3.929490327835083,0.00025,0.0,0.00025,0.00025,0.0028729883,0.004979132,0.022557117,0.0007968402,0.012837511921922923,0.022259134634650783,0.040622540563345584,-0.024907390773295932
15,422.0,0.0,2745.0,2745.0,65.0,2745.0,0.9983288800000364,2.0,15.0,0.0,,,,3.9306667894124985,0.0004889590223132316,3.9309356212615967,3.929192781448364,0.00025,0.0,0.00025,0.00025,0.003993525,0.005016152,0.013677783,0.00091032905,,,,
16,442.0,0.0,2826.0,2826.0,81.0,2826.0,0.998248690000038,0.0,0.0,0.0,,,,3.930476784706116,0.0005833675931495567,3.9308347702026367,3.92863392829895,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0037356387,0.0048887976000000005,0.014913436,0.00089475035,,,,
17,501.0,0.0,3060.0,3060.0,234.0,3060.0,0.9980170300000429,4.0,35.0,0.0,,,,3.9304699938176038,0.00041264778275723504,3.9306838512420654,3.928467988967896,0.00025,0.0,0.00025,0.00025,0.0030552953999999997,0.0041774893,0.01554886,0.0010523795,0.023353116586804973,0.020788514387939237,0.05141336545348224,-0.0014774784445756026
18,526.0,0.0,3161.0,3161.0,101.0,3161.0,0.9979170400000452,1.0,20.0,0.0,,,,3.9306457805633546,0.00023956495978218428,3.930816650390625,3.929875612258911,0.00025,0.0,0.00025,0.00025,0.002464988,0.003725262,0.013498537,0.00077633635,,,,
19,589.0,0.0,3413.0,3413.0,252.0,3413.0,0.9976675600000506,2.0,55.0,0.0,,,,3.9304992774176224,0.00034951799503506604,3.9307899475097656,3.9290616512298575,0.00025,0.0,0.00025,0.00025,0.0029548485999999997,0.0043363147,0.01425068,0.0007409669,,,,
20,646.0,0.0,3642.0,3642.0,229.0,3642.0,0.9974408500000556,2.0,15.0,0.0,,,,3.930309973264996,0.0005540508390044677,3.930628061294556,3.928320169448853,0.00025,0.0,0.00025,0.00025,0.0032555721999999996,0.004834081,0.015668849,0.0008300698,0.026904297930499418,0.021589106230980433,0.05910116657614764,0.005408810079098325
21,698.0,0.0,3849.0,3849.0,207.0,3849.0,0.99723592000006,4.0,50.0,0.0,,,,3.929926037788391,0.0006353061160591977,3.9303271770477295,3.9271233081817623,0.00025,0.0,0.00025,0.00025,0.004353328,0.006303993000000001,0.029395893,0.0010768827,0.02748812679201423,0.0217088123519984,0.057050981000066316,0.0017140418291097805
22,738.0,0.0,4010.0,4010.0,161.0,4010.0,0.9970765300000636,4.0,90.0,0.0,,,,3.92977910041809,0.0005514096791911278,3.930201768875122,3.9283792972564697,0.00025,0.0,0.00025,0.00025,0.004639727,0.005436519,0.015939886,0.0013534969000000001,,,,
23,789.0,0.0,4214.0,4214.0,204.0,4214.0,0.996874570000068,2.0,10.0,0.0,,,,3.929426656049841,0.0008124188909974342,3.929957151412964,3.925875425338745,0.00025,0.0,0.00025,0.00025,0.005286702,0.0059416015,0.024375048,0.0017462726,0.030502823988597175,0.02342976988309637,0.06656642369926036,0.0004357606172566697
24,854.0,0.0,4474.0,4474.0,260.0,4474.0,0.9966171700000734,5.0,80.0,0.0,,,,3.929753776697012,0.0006802738781902477,3.9303853511810303,3.926770448684693,0.00025,0.0,0.00025,0.00025,0.0032921252,0.004323490399999999,0.018876718,0.0008184177999999999,0.030289770103991618,0.011228381833076877,0.046150057762861824,0.014975410327315919
25,901.0,0.0,4662.0,4662.0,188.0,4662.0,0.9964310500000776,3.0,30.0,0.0,,,,3.929939036673688,0.0008579045062845213,3.9304828643798833,3.926759004592896,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0043313909999999995,0.0071201716,0.033504024,0.0006334899,,,,
26,969.0,0.0,4934.0,4934.0,272.0,4934.0,0.9961617700000832,1.0,5.0,0.0,,,,3.929590607390684,0.0006133207352767329,3.930098295211792,3.927515745162964,0.00025,0.0,0.00025,0.00025,0.0038270776,0.005072999999999999,0.021740799999999998,0.0010850433,,,,
27,1028.0,0.0,5168.0,5168.0,234.0,5168.0,0.9959301100000884,3.0,30.0,0.0,,,,3.930041709188688,0.0004330404189005426,3.9302978515625,3.927629232406616,0.00025,0.0,0.00025,0.00025,0.0031090009999999997,0.004790003,0.02229039,0.0008657125,,,,
28,1047.0,0.0,5245.0,5245.0,77.0,5245.0,0.99585388000009,2.0,45.0,0.0,,,,3.9298872069308635,0.0005701280611071911,3.9302644729614262,3.9285831451416016,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0042041945,0.0059060673,0.016562391,0.0008514148599999999,0.03760540119061923,0.01643017217867538,0.05344712957739886,0.01295695789158402
29,1107.0,0.0,5486.0,5486.0,241.0,5486.0,0.9956152900000952,6.0,105.0,0.0,,,,3.929187309741974,0.0007912253650240303,3.930028200149536,3.92718768119812,0.00025,0.0,0.00025,0.00025,0.0057351263,0.0060241455000000005,0.018669646,0.0012705077,,,,
30,1170.0,0.0,5738.0,5738.0,252.0,5738.0,0.9953658100001006,0.0,0.0,0.0,,,,3.9288085188184474,0.0009372335274004561,3.929582357406616,3.926055908203125,0.00025,0.0,0.00025,0.00025,0.0061082826,0.006076769,0.019835133,0.001853791,,,,
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 3.931728353687361 1.7148335424993695e-05 3.9317572116851807 3.931634187698364 0.00025 0.0 0.00025 0.00025 0.0015541904000000001 0.0023056455 0.009599385 0.0007559575999999999
7 6 116.0 0.0 1519.0 1519.0 259.0 1519.0 0.99954262000001 3.0 30.0 0.0 3.9316723786867582 5.269867767456892e-05 3.9317219257354736 3.9313907623291016 0.00025 0.0 0.00025 0.00025 0.001739312 0.0026554922 0.009864504 0.00067749363
8 7 154.0 0.0 1673.0 1673.0 154.0 1673.0 0.9993901600000132 0.0 0.0 0.0 3.931619857486925 6.473394968283058e-05 3.9316527843475337 3.931235074996948 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.0012083224 0.0019307991 0.009499238 0.0006370891400000001
9 8 188.0 0.0 1809.0 1809.0 136.0 1809.0 0.9992555200000162 0.0 0.0 0.0 3.931548202739042 7.783996401137547e-05 3.9316082000732417 3.9312365055084233 0.00025 0.0 0.00025 0.00025 0.0022799673 0.0033626328000000002 0.01030305 0.0006125771299999999
10 9 218.0 0.0 1927.0 1927.0 118.0 1927.0 0.9991387000000188 4.0 50.0 0.0 3.9314806302388514 0.00010239504684735038 3.931550741195679 3.931047201156616 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.0016353407000000001 0.002778357 0.01035096 0.0005981442500000001
11 10 239.0 0.0 2013.0 2013.0 86.0 2013.0 0.9990535600000204 1.0 25.0 0.0 3.9313772519429526 0.00020685918056109227 3.931517362594605 3.9308536052703857 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.0034886056 0.004297202 0.010684523999999999 0.00061402726
12 11 285.0 0.0 2197.0 2197.0 184.0 2197.0 0.9988714000000244 5.0 75.0 0.0 3.9313522369965264 7.248832757213434e-05 3.931442975997925 3.931007385253906 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.0017790395999999998 0.0030002112 0.011006265 0.0006065490000000001
13 12 309.0 0.0 2293.0 2293.0 96.0 2293.0 0.9987763600000266 2.0 15.0 0.0 3.931213736534119 0.0002593847407516344 3.93136215209961 3.9304351806640634 0.00025 0.0 0.00025 0.00025 0.0028233638 0.0041352687 0.011190076 0.0005888872
14 13 353.0 0.0 2467.0 2467.0 174.0 2467.0 0.9986041000000304 2.0 35.0 0.0 3.9310338009487498 0.0002957116497356457 3.9312725067138667 3.929877519607544 0.00025 0.0 0.00025 0.00025 0.0030289008 0.0042545744 0.012507513 0.0006166726000000001
15 14 406.0 0.0 2680.0 2680.0 213.0 2680.0 0.9983932300000348 3.0 60.0 0.0 3.930882449419993 0.00035235950786128846 3.9310703277587886 3.929490327835083 0.00025 0.0 0.00025 0.00025 0.0028729883 0.004979132 0.022557117 0.0007968402 0.012837511921922923 0.022259134634650783 0.040622540563345584 -0.024907390773295932
16 15 422.0 0.0 2745.0 2745.0 65.0 2745.0 0.9983288800000364 2.0 15.0 0.0 3.9306667894124985 0.0004889590223132316 3.9309356212615967 3.929192781448364 0.00025 0.0 0.00025 0.00025 0.003993525 0.005016152 0.013677783 0.00091032905
17 16 442.0 0.0 2826.0 2826.0 81.0 2826.0 0.998248690000038 0.0 0.0 0.0 3.930476784706116 0.0005833675931495567 3.9308347702026367 3.92863392829895 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.0037356387 0.0048887976000000005 0.014913436 0.00089475035
18 17 501.0 0.0 3060.0 3060.0 234.0 3060.0 0.9980170300000429 4.0 35.0 0.0 3.9304699938176038 0.00041264778275723504 3.9306838512420654 3.928467988967896 0.00025 0.0 0.00025 0.00025 0.0030552953999999997 0.0041774893 0.01554886 0.0010523795 0.023353116586804973 0.020788514387939237 0.05141336545348224 -0.0014774784445756026
19 18 526.0 0.0 3161.0 3161.0 101.0 3161.0 0.9979170400000452 1.0 20.0 0.0 3.9306457805633546 0.00023956495978218428 3.930816650390625 3.929875612258911 0.00025 0.0 0.00025 0.00025 0.002464988 0.003725262 0.013498537 0.00077633635
20 19 589.0 0.0 3413.0 3413.0 252.0 3413.0 0.9976675600000506 2.0 55.0 0.0 3.9304992774176224 0.00034951799503506604 3.9307899475097656 3.9290616512298575 0.00025 0.0 0.00025 0.00025 0.0029548485999999997 0.0043363147 0.01425068 0.0007409669
21 20 646.0 0.0 3642.0 3642.0 229.0 3642.0 0.9974408500000556 2.0 15.0 0.0 3.930309973264996 0.0005540508390044677 3.930628061294556 3.928320169448853 0.00025 0.0 0.00025 0.00025 0.0032555721999999996 0.004834081 0.015668849 0.0008300698 0.026904297930499418 0.021589106230980433 0.05910116657614764 0.005408810079098325
22 21 698.0 0.0 3849.0 3849.0 207.0 3849.0 0.99723592000006 4.0 50.0 0.0 3.929926037788391 0.0006353061160591977 3.9303271770477295 3.9271233081817623 0.00025 0.0 0.00025 0.00025 0.004353328 0.006303993000000001 0.029395893 0.0010768827 0.02748812679201423 0.0217088123519984 0.057050981000066316 0.0017140418291097805
23 22 738.0 0.0 4010.0 4010.0 161.0 4010.0 0.9970765300000636 4.0 90.0 0.0 3.92977910041809 0.0005514096791911278 3.930201768875122 3.9283792972564697 0.00025 0.0 0.00025 0.00025 0.004639727 0.005436519 0.015939886 0.0013534969000000001
24 23 789.0 0.0 4214.0 4214.0 204.0 4214.0 0.996874570000068 2.0 10.0 0.0 3.929426656049841 0.0008124188909974342 3.929957151412964 3.925875425338745 0.00025 0.0 0.00025 0.00025 0.005286702 0.0059416015 0.024375048 0.0017462726 0.030502823988597175 0.02342976988309637 0.06656642369926036 0.0004357606172566697
25 24 854.0 0.0 4474.0 4474.0 260.0 4474.0 0.9966171700000734 5.0 80.0 0.0 3.929753776697012 0.0006802738781902477 3.9303853511810303 3.926770448684693 0.00025 0.0 0.00025 0.00025 0.0032921252 0.004323490399999999 0.018876718 0.0008184177999999999 0.030289770103991618 0.011228381833076877 0.046150057762861824 0.014975410327315919
26 25 901.0 0.0 4662.0 4662.0 188.0 4662.0 0.9964310500000776 3.0 30.0 0.0 3.929939036673688 0.0008579045062845213 3.9304828643798833 3.926759004592896 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.0043313909999999995 0.0071201716 0.033504024 0.0006334899
27 26 969.0 0.0 4934.0 4934.0 272.0 4934.0 0.9961617700000832 1.0 5.0 0.0 3.929590607390684 0.0006133207352767329 3.930098295211792 3.927515745162964 0.00025 0.0 0.00025 0.00025 0.0038270776 0.005072999999999999 0.021740799999999998 0.0010850433
28 27 1028.0 0.0 5168.0 5168.0 234.0 5168.0 0.9959301100000884 3.0 30.0 0.0 3.930041709188688 0.0004330404189005426 3.9302978515625 3.927629232406616 0.00025 0.0 0.00025 0.00025 0.0031090009999999997 0.004790003 0.02229039 0.0008657125
29 28 1047.0 0.0 5245.0 5245.0 77.0 5245.0 0.99585388000009 2.0 45.0 0.0 3.9298872069308635 0.0005701280611071911 3.9302644729614262 3.9285831451416016 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.0042041945 0.0059060673 0.016562391 0.0008514148599999999 0.03760540119061923 0.01643017217867538 0.05344712957739886 0.01295695789158402
30 29 1107.0 0.0 5486.0 5486.0 241.0 5486.0 0.9956152900000952 6.0 105.0 0.0 3.929187309741974 0.0007912253650240303 3.930028200149536 3.92718768119812 0.00025 0.0 0.00025 0.00025 0.0057351263 0.0060241455000000005 0.018669646 0.0012705077
31 30 1170.0 0.0 5738.0 5738.0 252.0 5738.0 0.9953658100001006 0.0 0.0 0.0 3.9288085188184474 0.0009372335274004561 3.929582357406616 3.926055908203125 0.00025 0.0 0.00025 0.00025 0.0061082826 0.006076769 0.019835133 0.001853791