gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-04-11 15:43:40 +02:00
Code Issues Projects Releases Wiki Activity

Trace tests update

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files

31
rl_coach/traces/Atari_DDQN_with_PER_space_invaders/trace.csv Normal file
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,,,,,,,,,,,,,,,,,,,
5,51.0,0.0,1259.0,1259.0,202.0,1259.0,0.9998000200000045,3.0,35.0,0.0,,,,0.0034466183491281745,0.003340898543875149,0.01218117494136095,2.661944745341316e-05,6.25e-05,0.0,6.25e-05,6.25e-05,0.011219176,0.007470515600000001,0.02738716,0.0017668923,,,,
6,81.0,0.0,1382.0,1382.0,123.0,1382.0,0.9996782500000072,4.0,55.0,0.0,,,,0.011165372235700487,0.004458774445701718,0.021819429472088814,0.005195816047489643,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.027822528,0.007687265,0.04223389599999999,0.016463846,,,,
7,152.0,0.0,1665.0,1665.0,283.0,1665.0,0.9993980800000132,2.0,45.0,0.0,,,,0.00623855225964856,0.0030330486680636712,0.013224589638412,0.0007156636565923692,6.25e-05,0.0,6.25e-05,6.25e-05,0.018865645,0.005285673,0.033977974,0.010334366999999999,,,,
8,208.0,0.0,1887.0,1887.0,222.0,1887.0,0.9991783000000178,1.0,20.0,0.0,,,,0.0038385935840778975,0.0021158033238458662,0.00906903576105833,0.0003513850388117134,6.25e-05,0.0,6.25e-05,6.25e-05,0.013778427,0.0030470558,0.021373875,0.008706516,,,,
9,220.0,0.0,1938.0,1938.0,51.0,1938.0,0.9991278100000188,0.0,0.0,0.0,,,,0.003801035270347105,0.0018785112794797772,0.006776161491870879,0.0003781157138291746,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.012194245,0.0018602667000000002,0.01696095,0.01006682,,,,
10,269.0,0.0,2131.0,2131.0,193.0,2131.0,0.9989367400000232,1.0,5.0,0.0,,,,0.003452837460066135,0.0021161494549021354,0.010810058563947678,0.0002755867608357221,6.25e-05,0.0,6.25e-05,6.25e-05,0.012883931999999999,0.0038414826,0.026179705,0.007717976999999999,,,,
11,363.0,0.0,2509.0,2509.0,378.0,2509.0,0.9985625200000312,8.0,105.0,0.0,,,,0.0038385342929185312,0.002197450802281801,0.013560933992266657,0.000329795788275078,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.013579085,0.0045603695000000005,0.035137113,0.0076442054,0.060884252,0.008807714,0.07398923,0.044078137999999996
12,403.0,0.0,2667.0,2667.0,158.0,2667.0,0.9984061000000346,1.0,20.0,0.0,,,,0.0039893238288641435,0.0021892620525771848,0.009860016405582428,0.0002942612045444548,6.25e-05,0.0,6.25e-05,6.25e-05,0.013888638,0.0039621494,0.028397342000000002,0.008886355,,,,
13,424.0,0.0,2753.0,2753.0,86.0,2753.0,0.9983209600000365,1.0,25.0,0.0,,,,0.003456612211829495,0.0020587698243105523,0.008297181688249111,0.00038015557220205675,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.012752383999999999,0.0027827478,0.020799935,0.009112617,,,,
14,487.0,0.0,3003.0,3003.0,250.0,3003.0,0.9980734600000418,4.0,35.0,0.0,,,,0.0035351967242258117,0.0021189242929216105,0.009568667039275171,0.00023944152053445575,6.25e-05,0.0,6.25e-05,6.25e-05,0.013402411000000001,0.0034090402000000004,0.022448676,0.008539663000000001,,,,
15,559.0,0.0,3292.0,3292.0,289.0,3292.0,0.997787350000048,3.0,45.0,0.0,,,,0.0035738618094506404,0.0020785595659065575,0.009401696734130384,0.0003029023064300418,6.25e-05,0.0,6.25e-05,6.25e-05,0.013828838999999999,0.004127528,0.024494877,0.008980279,,,,
16,591.0,0.0,3421.0,3421.0,129.0,3421.0,0.9976596400000508,1.0,20.0,0.0,,,,0.002270541154302918,0.0013220278591834814,0.005336767993867397,0.00015750376041978598,6.25e-05,0.0,6.25e-05,6.25e-05,0.008640400999999999,0.0027808861,0.015539816000000001,0.0048837294,,,,
17,641.0,0.0,3619.0,3619.0,198.0,3619.0,0.9974636200000552,4.0,50.0,0.0,,,,0.0023200249412911947,0.001272970510092554,0.005772919394075871,0.00016006443183869123,6.25e-05,0.0,6.25e-05,6.25e-05,0.008547546999999999,0.0024141644,0.014635223999999999,0.00513471,,,,
18,659.0,0.0,3694.0,3694.0,75.0,3694.0,0.9973893700000568,2.0,15.0,0.0,,,,0.00222514630392349,0.0012230397213823035,0.0049801948480308065,0.00019548021373339,6.25e-05,0.0,6.25e-05,6.25e-05,0.008170923,0.0017159204,0.012074826,0.0055588847,,,,
19,676.0,0.0,3761.0,3761.0,67.0,3761.0,0.997323040000058,0.0,0.0,0.0,,,,0.002457476888701101,0.001416694384168644,0.004826911259442568,0.00020686438074335456,6.25e-05,0.0,6.25e-05,6.25e-05,0.009877314,0.0036330753999999996,0.016690083,0.0060720159999999995,,,,
20,760.0,0.0,4098.0,4098.0,337.0,4098.0,0.9969894100000654,5.0,75.0,0.0,,,,0.0024319054032925385,0.0013263558155535164,0.005569641478359699,0.00018588016973808408,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.009379297,0.0030807509999999996,0.019846683,0.0054414636,0.04652569,0.016040854,0.06404913,0.015960556
21,791.0,0.0,4222.0,4222.0,124.0,4222.0,0.9968666500000679,1.0,30.0,0.0,,,,0.0021794731803839247,0.0011718290688936287,0.005569073371589185,0.0001716011029202491,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.00873512,0.0021913913,0.016666776,0.0058183987,,,,
22,812.0,0.0,4304.0,4304.0,82.0,4304.0,0.9967854700000698,1.0,5.0,0.0,,,,0.0019065574230071867,0.0011469396393949038,0.003925406374037266,0.00020020424562972042,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.008078746500000001,0.0020175315,0.012820823,0.006058481,,,,
23,858.0,0.0,4488.0,4488.0,184.0,4488.0,0.9966033100000736,3.0,40.0,0.0,,,,0.00237545639222093,0.0014159762842297016,0.0052749416790902615,0.00012829533079639077,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.009339779,0.0036552486,0.02111213,0.0047810297,0.058359805,0.02419141,0.09481566,0.03411417
24,877.0,0.0,4563.0,4563.0,75.0,4563.0,0.9965290600000754,2.0,35.0,0.0,,,,0.0018037814221124313,0.000942041831796274,0.0039741676300764075,0.00020381834474392235,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.007797141600000001,0.0016731704999999998,0.012402746000000001,0.0055578630000000006,0.069268644,0.030192586,0.1046643,0.008713403
25,903.0,0.0,4669.0,4669.0,106.0,4669.0,0.9964241200000776,0.0,0.0,0.0,,,,0.0022410110227960665,0.0010767211744821578,0.0042915213853120795,0.0001786778011592105,6.25e-05,0.0,6.25e-05,6.25e-05,0.008801429,0.0023838158,0.014880427,0.005826161,,,,
26,949.0,0.0,4853.0,4853.0,184.0,4853.0,0.9962419600000816,0.0,0.0,0.0,,,,0.0024887697854074245,0.0014360504525598654,0.00585534330457449,0.00016110201249830425,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.009557521,0.0031522116999999996,0.01680403,0.005234984,0.053540934000000005,0.0246497,0.09204285599999999,0.013581572
27,966.0,0.0,4920.0,4920.0,67.0,4920.0,0.996175630000083,1.0,5.0,0.0,,,,0.002170577046105309,0.0011411493600190698,0.00466995220631361,0.0002499166294001043,6.25e-05,0.0,6.25e-05,6.25e-05,0.008650793,0.0019061747,0.012208687,0.005993179,,,,
28,1047.0,0.0,5245.0,5245.0,325.0,5245.0,0.99585388000009,4.0,40.0,0.0,,,,0.0024006758916427463,0.0012690461042417142,0.005421573296189308,0.0001969042932614684,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.009089955,0.0023783583,0.015432458000000001,0.0056008375,0.058892712,0.021359037999999997,0.10233389,0.030309968
29,1096.0,0.0,5442.0,5442.0,197.0,5442.0,0.9956588500000942,0.0,0.0,0.0,,,,0.0019011555625035484,0.0011534560731979529,0.005133558064699173,0.00018047218327410516,6.25e-05,0.0,6.25e-05,6.25e-05,0.008425966,0.002764765,0.017151356,0.0056821685,0.06334073,0.02206539,0.102514274,0.027491631000000002
30,1222.0,0.0,5946.0,5946.0,504.0,5946.0,0.9951598900001052,10.0,155.0,0.0,,,,0.002289209580339957,0.001271651628931315,0.006031029857695103,0.0001688292104518041,6.250000000000003e-05,2.7105054312137605e-20,6.25e-05,6.25e-05,0.008890314,0.0025685276,0.01631673,0.004984512,0.04618715,0.025464163999999997,0.0957826,-0.0035402263
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 0.9998000200000045 3.0 35.0 0.0 0.0034466183491281745 0.003340898543875149 0.01218117494136095 2.661944745341316e-05 6.25e-05 0.0 6.25e-05 6.25e-05 0.011219176 0.007470515600000001 0.02738716 0.0017668923
7 6 81.0 0.0 1382.0 1382.0 123.0 1382.0 0.9996782500000072 4.0 55.0 0.0 0.011165372235700487 0.004458774445701718 0.021819429472088814 0.005195816047489643 6.250000000000001e-05 1.3552527156068802e-20 6.25e-05 6.25e-05 0.027822528 0.007687265 0.04223389599999999 0.016463846
8 7 152.0 0.0 1665.0 1665.0 283.0 1665.0 0.9993980800000132 2.0 45.0 0.0 0.00623855225964856 0.0030330486680636712 0.013224589638412 0.0007156636565923692 6.25e-05 0.0 6.25e-05 6.25e-05 0.018865645 0.005285673 0.033977974 0.010334366999999999
9 8 208.0 0.0 1887.0 1887.0 222.0 1887.0 0.9991783000000178 1.0 20.0 0.0 0.0038385935840778975 0.0021158033238458662 0.00906903576105833 0.0003513850388117134 6.25e-05 0.0 6.25e-05 6.25e-05 0.013778427 0.0030470558 0.021373875 0.008706516
10 9 220.0 0.0 1938.0 1938.0 51.0 1938.0 0.9991278100000188 0.0 0.0 0.0 0.003801035270347105 0.0018785112794797772 0.006776161491870879 0.0003781157138291746 6.250000000000001e-05 1.3552527156068802e-20 6.25e-05 6.25e-05 0.012194245 0.0018602667000000002 0.01696095 0.01006682
11 10 269.0 0.0 2131.0 2131.0 193.0 2131.0 0.9989367400000232 1.0 5.0 0.0 0.003452837460066135 0.0021161494549021354 0.010810058563947678 0.0002755867608357221 6.25e-05 0.0 6.25e-05 6.25e-05 0.012883931999999999 0.0038414826 0.026179705 0.007717976999999999
12 11 363.0 0.0 2509.0 2509.0 378.0 2509.0 0.9985625200000312 8.0 105.0 0.0 0.0038385342929185312 0.002197450802281801 0.013560933992266657 0.000329795788275078 6.250000000000001e-05 1.3552527156068802e-20 6.25e-05 6.25e-05 0.013579085 0.0045603695000000005 0.035137113 0.0076442054 0.060884252 0.008807714 0.07398923 0.044078137999999996
13 12 403.0 0.0 2667.0 2667.0 158.0 2667.0 0.9984061000000346 1.0 20.0 0.0 0.0039893238288641435 0.0021892620525771848 0.009860016405582428 0.0002942612045444548 6.25e-05 0.0 6.25e-05 6.25e-05 0.013888638 0.0039621494 0.028397342000000002 0.008886355
14 13 424.0 0.0 2753.0 2753.0 86.0 2753.0 0.9983209600000365 1.0 25.0 0.0 0.003456612211829495 0.0020587698243105523 0.008297181688249111 0.00038015557220205675 6.250000000000001e-05 1.3552527156068802e-20 6.25e-05 6.25e-05 0.012752383999999999 0.0027827478 0.020799935 0.009112617
15 14 487.0 0.0 3003.0 3003.0 250.0 3003.0 0.9980734600000418 4.0 35.0 0.0 0.0035351967242258117 0.0021189242929216105 0.009568667039275171 0.00023944152053445575 6.25e-05 0.0 6.25e-05 6.25e-05 0.013402411000000001 0.0034090402000000004 0.022448676 0.008539663000000001
16 15 559.0 0.0 3292.0 3292.0 289.0 3292.0 0.997787350000048 3.0 45.0 0.0 0.0035738618094506404 0.0020785595659065575 0.009401696734130384 0.0003029023064300418 6.25e-05 0.0 6.25e-05 6.25e-05 0.013828838999999999 0.004127528 0.024494877 0.008980279
17 16 591.0 0.0 3421.0 3421.0 129.0 3421.0 0.9976596400000508 1.0 20.0 0.0 0.002270541154302918 0.0013220278591834814 0.005336767993867397 0.00015750376041978598 6.25e-05 0.0 6.25e-05 6.25e-05 0.008640400999999999 0.0027808861 0.015539816000000001 0.0048837294
18 17 641.0 0.0 3619.0 3619.0 198.0 3619.0 0.9974636200000552 4.0 50.0 0.0 0.0023200249412911947 0.001272970510092554 0.005772919394075871 0.00016006443183869123 6.25e-05 0.0 6.25e-05 6.25e-05 0.008547546999999999 0.0024141644 0.014635223999999999 0.00513471
19 18 659.0 0.0 3694.0 3694.0 75.0 3694.0 0.9973893700000568 2.0 15.0 0.0 0.00222514630392349 0.0012230397213823035 0.0049801948480308065 0.00019548021373339 6.25e-05 0.0 6.25e-05 6.25e-05 0.008170923 0.0017159204 0.012074826 0.0055588847
20 19 676.0 0.0 3761.0 3761.0 67.0 3761.0 0.997323040000058 0.0 0.0 0.0 0.002457476888701101 0.001416694384168644 0.004826911259442568 0.00020686438074335456 6.25e-05 0.0 6.25e-05 6.25e-05 0.009877314 0.0036330753999999996 0.016690083 0.0060720159999999995
21 20 760.0 0.0 4098.0 4098.0 337.0 4098.0 0.9969894100000654 5.0 75.0 0.0 0.0024319054032925385 0.0013263558155535164 0.005569641478359699 0.00018588016973808408 6.250000000000001e-05 1.3552527156068802e-20 6.25e-05 6.25e-05 0.009379297 0.0030807509999999996 0.019846683 0.0054414636 0.04652569 0.016040854 0.06404913 0.015960556
22 21 791.0 0.0 4222.0 4222.0 124.0 4222.0 0.9968666500000679 1.0 30.0 0.0 0.0021794731803839247 0.0011718290688936287 0.005569073371589185 0.0001716011029202491 6.250000000000001e-05 1.3552527156068802e-20 6.25e-05 6.25e-05 0.00873512 0.0021913913 0.016666776 0.0058183987
23 22 812.0 0.0 4304.0 4304.0 82.0 4304.0 0.9967854700000698 1.0 5.0 0.0 0.0019065574230071867 0.0011469396393949038 0.003925406374037266 0.00020020424562972042 6.250000000000001e-05 1.3552527156068802e-20 6.25e-05 6.25e-05 0.008078746500000001 0.0020175315 0.012820823 0.006058481
24 23 858.0 0.0 4488.0 4488.0 184.0 4488.0 0.9966033100000736 3.0 40.0 0.0 0.00237545639222093 0.0014159762842297016 0.0052749416790902615 0.00012829533079639077 6.250000000000001e-05 1.3552527156068802e-20 6.25e-05 6.25e-05 0.009339779 0.0036552486 0.02111213 0.0047810297 0.058359805 0.02419141 0.09481566 0.03411417
25 24 877.0 0.0 4563.0 4563.0 75.0 4563.0 0.9965290600000754 2.0 35.0 0.0 0.0018037814221124313 0.000942041831796274 0.0039741676300764075 0.00020381834474392235 6.250000000000001e-05 1.3552527156068802e-20 6.25e-05 6.25e-05 0.007797141600000001 0.0016731704999999998 0.012402746000000001 0.0055578630000000006 0.069268644 0.030192586 0.1046643 0.008713403
26 25 903.0 0.0 4669.0 4669.0 106.0 4669.0 0.9964241200000776 0.0 0.0 0.0 0.0022410110227960665 0.0010767211744821578 0.0042915213853120795 0.0001786778011592105 6.25e-05 0.0 6.25e-05 6.25e-05 0.008801429 0.0023838158 0.014880427 0.005826161
27 26 949.0 0.0 4853.0 4853.0 184.0 4853.0 0.9962419600000816 0.0 0.0 0.0 0.0024887697854074245 0.0014360504525598654 0.00585534330457449 0.00016110201249830425 6.250000000000001e-05 1.3552527156068802e-20 6.25e-05 6.25e-05 0.009557521 0.0031522116999999996 0.01680403 0.005234984 0.053540934000000005 0.0246497 0.09204285599999999 0.013581572
28 27 966.0 0.0 4920.0 4920.0 67.0 4920.0 0.996175630000083 1.0 5.0 0.0 0.002170577046105309 0.0011411493600190698 0.00466995220631361 0.0002499166294001043 6.25e-05 0.0 6.25e-05 6.25e-05 0.008650793 0.0019061747 0.012208687 0.005993179
29 28 1047.0 0.0 5245.0 5245.0 325.0 5245.0 0.99585388000009 4.0 40.0 0.0 0.0024006758916427463 0.0012690461042417142 0.005421573296189308 0.0001969042932614684 6.250000000000001e-05 1.3552527156068802e-20 6.25e-05 6.25e-05 0.009089955 0.0023783583 0.015432458000000001 0.0056008375 0.058892712 0.021359037999999997 0.10233389 0.030309968
30 29 1096.0 0.0 5442.0 5442.0 197.0 5442.0 0.9956588500000942 0.0 0.0 0.0 0.0019011555625035484 0.0011534560731979529 0.005133558064699173 0.00018047218327410516 6.25e-05 0.0 6.25e-05 6.25e-05 0.008425966 0.002764765 0.017151356 0.0056821685 0.06334073 0.02206539 0.102514274 0.027491631000000002
31 30 1222.0 0.0 5946.0 5946.0 504.0 5946.0 0.9951598900001052 10.0 155.0 0.0 0.002289209580339957 0.001271651628931315 0.006031029857695103 0.0001688292104518041 6.250000000000003e-05 2.7105054312137605e-20 6.25e-05 6.25e-05 0.008890314 0.0025685276 0.01631673 0.004984512 0.04618715 0.025464163999999997 0.0957826 -0.0035402263