gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-03-13 04:55:47 +01:00
Code Issues Projects Releases Wiki Activity

new traces

Browse Source
This commit is contained in:
itaicaspi-intel
2018-09-12 15:29:42 +03:00
parent 673911ff7f
commit fa4895f840
76 changed files with 12786 additions and 12606 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
rl_coach/traces/ControlSuite_DDPG_cartpole_swingup/trace.csv
View File

@@ -1,6 +1,6 @@
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,Entropy/Mean,Entropy/Stdev,Entropy/Max,Entropy/Min,Advantages/Mean,Advantages/Stdev,Advantages/Max,Advantages/Min,Values/Mean,Values/Stdev,Values/Max,Values/Min,Value Loss/Mean,Value Loss/Stdev,Value Loss/Max,Value Loss/Min,Policy Loss/Mean,Policy Loss/Stdev,Policy Loss/Max,Policy Loss/Min,Q/Mean,Q/Stdev,Q/Max,Q/Min,TD targets/Mean,TD targets/Stdev,TD targets/Max,TD targets/Min,actions/Mean,actions/Stdev,actions/Max,actions/Min
1,0.0,1.0,1001.0,1.0,1001.0,1001.0,0.0,,,0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
2,0.0,1.0,2002.0,2.0,1001.0,2002.0,0.0,,,1.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
3,1000.0,0.0,3003.0,3.0,1001.0,3003.0,-0.1185302492771778,12.73546386992824,127.3546386992823,1.0,,,,1.4965620654038504e-05,3.650858260133972e-05,0.0007415295694954692,1.510996071374393e-06,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.0049991608,0.004320714,0.029555712,0.00052324863,,,,,,,,,,,,,,,,,,,,,-0.02509604,0.12253879,0.19679643,-0.25691667,0.002979598431912616,0.042334642053058036,0.09477341320020807,-0.1277348208010601,0.7574106673312205,0.2820158065549947,1.3628734977284602,-0.13561528749852786
4,2001.0,0.0,4004.0,4.0,1001.0,4004.0,-0.2048510260598676,7.629510433822026,76.29510433822016,1.0,,,,9.294460378555413e-05,0.00018001446184314637,0.0014042556285858154,1.88643639376096e-06,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.018415965,0.019779565,0.19278607,0.0008359549000000001,,,,,,,,,,,,,,,,,,,,,-0.007871467,0.112213835,0.17972693,-0.23277566,0.002690244749371092,0.08247475995739656,0.20102381350942625,-0.2633941138081878,0.8866818175665385,0.1980599181751808,1.3750565774684147,0.4541525586846937
5,3002.0,0.0,5005.0,5.0,1001.0,5005.0,-0.02134772535498328,7.612595851248884,76.12595851248874,0.0,,,,4.2167748756014586e-05,0.00010527586086637082,0.001020723837427795,1.4967686183808837e-06,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.009330036,0.0073557219999999994,0.04758695,0.00048721785000000004,,,,,,,,,,,,,,,,,,,,,-0.00076002936,0.12163509,0.17490079,-0.2400235,0.009237181711633144,0.09619469158143916,0.21206437128683006,-0.2783133662129137,1.0669116245649553,0.12577960072670955,1.400521073123623,0.7853534082159903
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,Discounted Return/Mean,Discounted Return/Stdev,Discounted Return/Max,Discounted Return/Min,Entropy/Mean,Entropy/Stdev,Entropy/Max,Entropy/Min,Advantages/Mean,Advantages/Stdev,Advantages/Max,Advantages/Min,Values/Mean,Values/Stdev,Values/Max,Values/Min,Value Loss/Mean,Value Loss/Stdev,Value Loss/Max,Value Loss/Min,Policy Loss/Mean,Policy Loss/Stdev,Policy Loss/Max,Policy Loss/Min,Q/Mean,Q/Stdev,Q/Max,Q/Min,TD targets/Mean,TD targets/Stdev,TD targets/Max,TD targets/Min,actions/Mean,actions/Stdev,actions/Max,actions/Min
1,0.0,1.0,1001.0,1.0,1001.0,1001.0,0.0,,,0.0,,,,,,,,,,,,,,,,0.1810549437584988,0.08342612458204374,0.3657155727590055,0.012114535848885052,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
2,0.0,1.0,2002.0,2.0,1001.0,2002.0,0.0,,,1.0,,,,,,,,,,,,,,,,0.10514369548395547,0.05043065738920054,0.21524430347618226,0.0011643643789458708,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
3,1000.0,0.0,3003.0,3.0,1001.0,3003.0,-0.1185302492771778,6.74600433432463,67.46004334324633,1.0,,,,1.0688050798876248e-05,1.766983092613708e-05,0.0002591642551124096,1.702799409031286e-06,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.0045520826,0.0030055756,0.023246742999999997,0.00061706273,0.6303898598111053,0.14191577052955434,0.8002050670805612,0.012917920234129009,,,,,,,,,,,,,,,,,,,,,0.00010149915000000001,0.17838655,0.24224899999999996,-0.3742638,0.031711048067017016,0.06663038905079713,0.16946774334467746,-0.1425395913783225,-1.1330065308041135,0.2760152561198482,-0.11754712369609001,-1.564363479104263
4,2001.0,0.0,4004.0,4.0,1001.0,4004.0,-0.2048510260598676,7.668551490997389,76.68551490997385,1.0,,,,3.408961573131819e-05,6.750553695485743e-05,0.0007010267581790687,1.4872452993586194e-06,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.010960271,0.013024458000000001,0.09523078,0.0007027931,0.6965929526733899,0.1622994335943064,0.9453308568504694,0.013324665458032537,,,,,,,,,,,,,,,,,,,,,0.0027730353,0.18788128,0.250535,-0.3431186,0.029557790599657345,0.11711363926377175,0.2386419371743873,-0.3346987397531008,-1.113269411960027,0.1980527596764508,-0.6249308459515377,-1.5458447591062914
5,3002.0,0.0,5005.0,5.0,1001.0,5005.0,-0.02134772535498328,7.368122753870011,73.6812275387001,0.0,,,,1.2014473524686764e-05,1.2546101794472948e-05,0.00015411879576276988,1.0827171763594379e-06,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.007843023000000001,0.0051095295,0.038092513,0.0006715836400000001,0.66996138932216,0.15703584718374808,0.8908932610369035,0.0060312519674541746,,,,,,,,,,,,,,,,,,,,,0.015175661000000002,0.18127811,0.24180134,-0.31560785,0.03080747100578105,0.13684940389057226,0.2399127439483701,-0.3243346170643305,-0.9330713833476759,0.12577776040520755,-0.5994658138545264,-1.21464647257472
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 Discounted Return/Mean Discounted Return/Stdev Discounted Return/Max Discounted Return/Min Entropy/Mean Entropy/Stdev Entropy/Max Entropy/Min Advantages/Mean Advantages/Stdev Advantages/Max Advantages/Min Values/Mean Values/Stdev Values/Max Values/Min Value Loss/Mean Value Loss/Stdev Value Loss/Max Value Loss/Min Policy Loss/Mean Policy Loss/Stdev Policy Loss/Max Policy Loss/Min Q/Mean Q/Stdev Q/Max Q/Min TD targets/Mean TD targets/Stdev TD targets/Max TD targets/Min actions/Mean actions/Stdev actions/Max actions/Min
2 1 0.0 1.0 1001.0 1.0 1001.0 1001.0 0.0 0.0 0.1810549437584988 0.08342612458204374 0.3657155727590055 0.012114535848885052
3 2 0.0 1.0 2002.0 2.0 1001.0 2002.0 0.0 1.0 0.10514369548395547 0.05043065738920054 0.21524430347618226 0.0011643643789458708
4 3 1000.0 0.0 3003.0 3.0 1001.0 3003.0 -0.1185302492771778 12.73546386992824 6.74600433432463 127.3546386992823 67.46004334324633 1.0 1.4965620654038504e-05 1.0688050798876248e-05 3.650858260133972e-05 1.766983092613708e-05 0.0007415295694954692 0.0002591642551124096 1.510996071374393e-06 1.702799409031286e-06 0.00010000000000000003 2.7105054312137605e-20 0.0001 0.0001 0.0049991608 0.0045520826 0.004320714 0.0030055756 0.029555712 0.023246742999999997 0.00052324863 0.00061706273 0.6303898598111053 0.14191577052955434 0.8002050670805612 0.012917920234129009 -0.02509604 0.00010149915000000001 0.12253879 0.17838655 0.19679643 0.24224899999999996 -0.25691667 -0.3742638 0.002979598431912616 0.031711048067017016 0.042334642053058036 0.06663038905079713 0.09477341320020807 0.16946774334467746 -0.1277348208010601 -0.1425395913783225 0.7574106673312205 -1.1330065308041135 0.2820158065549947 0.2760152561198482 1.3628734977284602 -0.11754712369609001 -0.13561528749852786 -1.564363479104263
5 4 2001.0 0.0 4004.0 4.0 1001.0 4004.0 -0.2048510260598676 7.629510433822026 7.668551490997389 76.29510433822016 76.68551490997385 1.0 9.294460378555413e-05 3.408961573131819e-05 0.00018001446184314637 6.750553695485743e-05 0.0014042556285858154 0.0007010267581790687 1.88643639376096e-06 1.4872452993586194e-06 0.00010000000000000003 2.7105054312137605e-20 0.0001 0.0001 0.018415965 0.010960271 0.019779565 0.013024458000000001 0.19278607 0.09523078 0.0008359549000000001 0.0007027931 0.6965929526733899 0.1622994335943064 0.9453308568504694 0.013324665458032537 -0.007871467 0.0027730353 0.112213835 0.18788128 0.17972693 0.250535 -0.23277566 -0.3431186 0.002690244749371092 0.029557790599657345 0.08247475995739656 0.11711363926377175 0.20102381350942625 0.2386419371743873 -0.2633941138081878 -0.3346987397531008 0.8866818175665385 -1.113269411960027 0.1980599181751808 0.1980527596764508 1.3750565774684147 -0.6249308459515377 0.4541525586846937 -1.5458447591062914
6 5 3002.0 0.0 5005.0 5.0 1001.0 5005.0 -0.02134772535498328 7.612595851248884 7.368122753870011 76.12595851248874 73.6812275387001 0.0 4.2167748756014586e-05 1.2014473524686764e-05 0.00010527586086637082 1.2546101794472948e-05 0.001020723837427795 0.00015411879576276988 1.4967686183808837e-06 1.0827171763594379e-06 0.00010000000000000003 2.7105054312137605e-20 0.0001 0.0001 0.009330036 0.007843023000000001 0.0073557219999999994 0.0051095295 0.04758695 0.038092513 0.00048721785000000004 0.0006715836400000001 0.66996138932216 0.15703584718374808 0.8908932610369035 0.0060312519674541746 -0.00076002936 0.015175661000000002 0.12163509 0.18127811 0.17490079 0.24180134 -0.2400235 -0.31560785 0.009237181711633144 0.03080747100578105 0.09619469158143916 0.13684940389057226 0.21206437128683006 0.2399127439483701 -0.2783133662129137 -0.3243346170643305 1.0669116245649553 -0.9330713833476759 0.12577960072670955 0.12577776040520755 1.400521073123623 -0.5994658138545264 0.7853534082159903 -1.21464647257472