Hugging Face's logo

ezipe
/
reward_learning

Model card Files
xet
Community
ezipe commited on
Commit
ee0745d
·
verified ·
1 Parent(s): bd80f1e

Upload folder using huggingface_hub

Browse files
Files changed (30) hide show
  1. ce_rmabppo_test_n21b7.0dcounterexamplersample_randomp0/ce_rmabppo_test_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  2. ce_rmabppo_test_n21b7.0dcounterexamplersample_randomp0/ce_rmabppo_test_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  3. ce_rmabppo_test_n21b7.0dcounterexamplersample_randomp0/ce_rmabppo_test_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  4. reward_2024-01-24---18-46-38_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---18-46-38_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  5. reward_2024-01-24---18-46-38_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---18-46-38_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  6. reward_2024-01-24---18-46-38_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---18-46-38_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  7. reward_2024-01-24---19-12-17_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-12-17_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  8. reward_2024-01-24---19-12-17_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-12-17_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  9. reward_2024-01-24---19-12-17_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-12-17_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  10. reward_2024-01-24---19-24-22_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-24-22_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  11. reward_2024-01-24---19-24-22_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-24-22_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  12. reward_2024-01-24---19-24-22_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-24-22_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  13. reward_2024-01-24---19-26-03_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-26-03_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  14. reward_2024-01-24---19-26-03_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-26-03_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  15. reward_2024-01-24---19-26-03_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-26-03_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  16. reward_2024-01-24---19-26-58_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-26-58_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  17. reward_2024-01-24---19-26-58_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-26-58_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  18. reward_2024-01-24---19-26-58_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-26-58_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  19. reward_2024-01-24---19-39-07_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-39-07_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  20. reward_2024-01-24---19-39-07_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-39-07_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  21. reward_2024-01-24---19-39-07_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-39-07_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  22. reward_2024-01-24---20-01-07_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-01-07_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  23. reward_2024-01-24---20-01-07_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-01-07_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  24. reward_2024-01-24---20-01-07_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-01-07_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
  25. reward_2024-01-24---20-02-13_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-02-13_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +0 -0
  26. reward_2024-01-24---20-04-15_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-04-15_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +0 -0
  27. reward_2024-01-24---20-06-33_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-06-33_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +0 -0
  28. reward_2024-01-24---20-07-28_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-07-28_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt +2 -0
  29. reward_2024-01-24---20-07-28_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-07-28_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt +3 -0
  30. reward_2024-01-24---20-07-28_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-07-28_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl +3 -0
ce_rmabppo_test_n21b7.0dcounterexamplersample_randomp0/ce_rmabppo_test_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 6848.739 0.0 6848.739 6848.739 6526.2256 0.0 6526.2256 6526.2256 -0.005310931 0.043766547 0.059458897 -0.074559785 0.33877438 1.8149731159210205
ce_rmabppo_test_n21b7.0dcounterexamplersample_randomp0/ce_rmabppo_test_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7854d215a44f255e8f27e96ef34bc69d0d5907fdef40d74962b064af519d090
3
+ size 26198
ce_rmabppo_test_n21b7.0dcounterexamplersample_randomp0/ce_rmabppo_test_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df1c40996c6813a4f09638829048f776da40ea44c35fafe443934da8e17b679
3
+ size 14076
reward_2024-01-24---18-46-38_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---18-46-38_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 262.0 0.0 262.0 262.0 -22.218044 0.0 -22.218044 -22.218044 -0.0011059602 0.045040186 0.060568523 -0.07351168 0.32151362 1.7601103782653809
reward_2024-01-24---18-46-38_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---18-46-38_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76427b2c4d4c512a3746fe59ff759c65e8b042383dd805a3c957dfab4a170207
3
+ size 26198
reward_2024-01-24---18-46-38_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---18-46-38_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df1c40996c6813a4f09638829048f776da40ea44c35fafe443934da8e17b679
3
+ size 14076
reward_2024-01-24---19-12-17_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-12-17_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 1492.0 0.0 1492.0 1492.0 1186.5498 0.0 1186.5498 1186.5498 -0.0022845499 0.044902034 0.059248008 -0.07475856 0.34204945 1.8139305114746094
reward_2024-01-24---19-12-17_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-12-17_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9078d25a6d842a0e0ee5fe4982621b00e209fcb7c7beb284aa2b0453f26e2d6
3
+ size 26198
reward_2024-01-24---19-12-17_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-12-17_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df1c40996c6813a4f09638829048f776da40ea44c35fafe443934da8e17b679
3
+ size 14076
reward_2024-01-24---19-24-22_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-24-22_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 48.0 0.0 48.0 48.0 -278.14178 0.0 -278.14178 -278.14178 -0.007816804 0.04234601 0.04392085 -0.07385238 0.32712317 1.8424572944641113
reward_2024-01-24---19-24-22_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-24-22_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0a503e3b6e76f425f1eff390bcf222d809bf14f75f84719554ff6f43fb624cf
3
+ size 26198
reward_2024-01-24---19-24-22_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-24-22_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df1c40996c6813a4f09638829048f776da40ea44c35fafe443934da8e17b679
3
+ size 14076
reward_2024-01-24---19-26-03_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-26-03_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 24.0 0.0 24.0 24.0 -298.5132 0.0 -298.5132 -298.5132 -0.005310931 0.043766547 0.059458897 -0.074559785 0.33877438 1.7777719497680664
reward_2024-01-24---19-26-03_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-26-03_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8237a0addd8039a7c732e480f9c81cfee3daaf5eacb92d8497fbdd63893b3c31
3
+ size 26198
reward_2024-01-24---19-26-03_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-26-03_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df1c40996c6813a4f09638829048f776da40ea44c35fafe443934da8e17b679
3
+ size 14076
reward_2024-01-24---19-26-58_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-26-58_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 325.2 0.0 325.2 325.2 58.953186 0.0 58.953186 58.953186 -0.00016120703 0.044984415 0.061915003 -0.07223507 0.3005043 1.7492702007293701
reward_2024-01-24---19-26-58_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-26-58_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ae08f1f99ba745071d42b164cca3d6298540b37e209f1cdcd0783ecdd07f039
3
+ size 26198
reward_2024-01-24---19-26-58_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-26-58_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df1c40996c6813a4f09638829048f776da40ea44c35fafe443934da8e17b679
3
+ size 14076
reward_2024-01-24---19-39-07_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-39-07_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 1924.0 0.0 1924.0 1924.0 1597.8579 0.0 1597.8579 1597.8579 -0.007816804 0.04234601 0.04392085 -0.07385238 0.32712317 1.8682904243469238
reward_2024-01-24---19-39-07_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-39-07_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfffc219e8222a6a83f0eac9f74f44d1c9081e9b7474b79307a17d8ccab983e6
3
+ size 26198
reward_2024-01-24---19-39-07_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---19-39-07_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df1c40996c6813a4f09638829048f776da40ea44c35fafe443934da8e17b679
3
+ size 14076
reward_2024-01-24---20-01-07_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-01-07_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 970.8 0.0 970.8 970.8 722.1742 0.0 722.1742 722.1742 0.009028936 0.046654265 0.060317256 -0.07374935 0.32542643 1.8202075958251953
reward_2024-01-24---20-01-07_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-01-07_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec8e1465d61ddc027320eb6399ef2f5462657a917f2ebb6ec53f82cb5a0059e7
3
+ size 26198
reward_2024-01-24---20-01-07_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-01-07_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df1c40996c6813a4f09638829048f776da40ea44c35fafe443934da8e17b679
3
+ size 14076
reward_2024-01-24---20-02-13_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-02-13_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
File without changes
reward_2024-01-24---20-04-15_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-04-15_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
File without changes
reward_2024-01-24---20-06-33_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-06-33_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
File without changes
reward_2024-01-24---20-07-28_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-07-28_n21b7.0dcounterexamplersample_randomp0_s0/progress.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Epoch AverageEpActualRet StdEpActualRet MaxEpActualRet MinEpActualRet AverageEpLambAdjRet StdEpLambAdjRet MaxEpLambAdjRet MinEpLambAdjRet AverageVVals StdVVals MaxVVals MinVVals Lamb Time
2
+ 0 872.0 0.0 872.0 872.0 589.22046 0.0 589.22046 589.22046 -0.0002368875 0.04474328 0.06064972 -0.07343485 0.32024878 1.8865466117858887
reward_2024-01-24---20-07-28_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-07-28_n21b7.0dcounterexamplersample_randomp0_s0/pyt_save/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:342a70df71f953934c3c171db8e1a474adb50b090f54f66539183f6e4d14ef63
3
+ size 26198
reward_2024-01-24---20-07-28_n21b7.0dcounterexamplersample_randomp0/reward_2024-01-24---20-07-28_n21b7.0dcounterexamplersample_randomp0_s0/vars.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed698a663774dd4dfead09d56034b3ff9fc31d932a94ff9346352e8b942a6dd3
3
+ size 13916