HumanoidStandup-v5/ero_trpo/seed_2/latest checkpoint epoch 1140
Browse files- HumanoidStandup-v5/ero_trpo/seed_2/latest/history.json +140 -0
- HumanoidStandup-v5/ero_trpo/seed_2/latest/metadata.json +11 -11
- HumanoidStandup-v5/ero_trpo/seed_2/latest/policy.pt +1 -1
- HumanoidStandup-v5/ero_trpo/seed_2/latest/progress.json +3 -3
- HumanoidStandup-v5/ero_trpo/seed_2/latest/value.pt +1 -1
HumanoidStandup-v5/ero_trpo/seed_2/latest/history.json
CHANGED
|
@@ -15818,5 +15818,145 @@
|
|
| 15818 |
"update_success": 1.0,
|
| 15819 |
"eval_return_mean": -79127.91247934656,
|
| 15820 |
"eval_return_std": 8463.752747853609
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15821 |
}
|
| 15822 |
]
|
|
|
|
| 15818 |
"update_success": 1.0,
|
| 15819 |
"eval_return_mean": -79127.91247934656,
|
| 15820 |
"eval_return_std": 8463.752747853609
|
| 15821 |
+
},
|
| 15822 |
+
{
|
| 15823 |
+
"epoch": 1130,
|
| 15824 |
+
"timesteps": 226200,
|
| 15825 |
+
"surrogate_improve": 6.542205483128782e-06,
|
| 15826 |
+
"surrogate": 6.542205483128782e-06,
|
| 15827 |
+
"kl": -4.76837147544984e-09,
|
| 15828 |
+
"entropy_mean": 15.621954917907715,
|
| 15829 |
+
"objective": 8.104400876618456e-06,
|
| 15830 |
+
"effective_kl": 4.76837147544984e-09,
|
| 15831 |
+
"line_search_backtracks": 0,
|
| 15832 |
+
"update_success": 1.0,
|
| 15833 |
+
"eval_return_mean": -83140.24162936097,
|
| 15834 |
+
"eval_return_std": 10081.370876849745
|
| 15835 |
+
},
|
| 15836 |
+
{
|
| 15837 |
+
"epoch": 1131,
|
| 15838 |
+
"timesteps": 226400,
|
| 15839 |
+
"surrogate_improve": 2.880096417356981e-06,
|
| 15840 |
+
"surrogate": 2.880096417356981e-06,
|
| 15841 |
+
"kl": -5.149840944795869e-07,
|
| 15842 |
+
"entropy_mean": 15.621954917907715,
|
| 15843 |
+
"objective": 4.442291810846655e-06,
|
| 15844 |
+
"effective_kl": 5.149840944795869e-07,
|
| 15845 |
+
"line_search_backtracks": 0,
|
| 15846 |
+
"update_success": 1.0,
|
| 15847 |
+
"eval_return_mean": -81898.22084145194,
|
| 15848 |
+
"eval_return_std": 11781.793600076642
|
| 15849 |
+
},
|
| 15850 |
+
{
|
| 15851 |
+
"epoch": 1132,
|
| 15852 |
+
"timesteps": 226600,
|
| 15853 |
+
"surrogate_improve": 4.253387487551663e-06,
|
| 15854 |
+
"surrogate": 4.253387487551663e-06,
|
| 15855 |
+
"kl": 5.722045557376987e-07,
|
| 15856 |
+
"entropy_mean": 15.621954917907715,
|
| 15857 |
+
"objective": 5.815582881041337e-06,
|
| 15858 |
+
"effective_kl": 5.722045557376987e-07,
|
| 15859 |
+
"line_search_backtracks": 0,
|
| 15860 |
+
"update_success": 1.0,
|
| 15861 |
+
"eval_return_mean": -72863.81887729406,
|
| 15862 |
+
"eval_return_std": 19970.693459598293
|
| 15863 |
+
},
|
| 15864 |
+
{
|
| 15865 |
+
"epoch": 1133,
|
| 15866 |
+
"timesteps": 226800,
|
| 15867 |
+
"surrogate_improve": 3.411769739614101e-06,
|
| 15868 |
+
"surrogate": 3.411769739614101e-06,
|
| 15869 |
+
"kl": -4.1007993445418833e-07,
|
| 15870 |
+
"entropy_mean": 15.621954917907715,
|
| 15871 |
+
"objective": 4.973965133103775e-06,
|
| 15872 |
+
"effective_kl": 4.1007993445418833e-07,
|
| 15873 |
+
"line_search_backtracks": 0,
|
| 15874 |
+
"update_success": 1.0,
|
| 15875 |
+
"eval_return_mean": -84768.61575005922,
|
| 15876 |
+
"eval_return_std": 15164.77523442776
|
| 15877 |
+
},
|
| 15878 |
+
{
|
| 15879 |
+
"epoch": 1134,
|
| 15880 |
+
"timesteps": 227000,
|
| 15881 |
+
"surrogate_improve": 2.0503996438492322e-06,
|
| 15882 |
+
"surrogate": 2.0503996438492322e-06,
|
| 15883 |
+
"kl": 6.484985419774603e-07,
|
| 15884 |
+
"entropy_mean": 15.621954917907715,
|
| 15885 |
+
"objective": 3.6125952647125814e-06,
|
| 15886 |
+
"effective_kl": 6.484985419774603e-07,
|
| 15887 |
+
"line_search_backtracks": 0,
|
| 15888 |
+
"update_success": 1.0,
|
| 15889 |
+
"eval_return_mean": -74471.49527755695,
|
| 15890 |
+
"eval_return_std": 17881.823592480614
|
| 15891 |
+
},
|
| 15892 |
+
{
|
| 15893 |
+
"epoch": 1135,
|
| 15894 |
+
"timesteps": 227200,
|
| 15895 |
+
"surrogate_improve": 3.952980023314012e-06,
|
| 15896 |
+
"surrogate": 3.952980023314012e-06,
|
| 15897 |
+
"kl": 1.163482693300466e-06,
|
| 15898 |
+
"entropy_mean": 15.621954917907715,
|
| 15899 |
+
"objective": 5.515175416803686e-06,
|
| 15900 |
+
"effective_kl": 1.163482693300466e-06,
|
| 15901 |
+
"line_search_backtracks": 0,
|
| 15902 |
+
"update_success": 1.0,
|
| 15903 |
+
"eval_return_mean": -84895.60154622355,
|
| 15904 |
+
"eval_return_std": 9237.29353957124
|
| 15905 |
+
},
|
| 15906 |
+
{
|
| 15907 |
+
"epoch": 1136,
|
| 15908 |
+
"timesteps": 227400,
|
| 15909 |
+
"surrogate_improve": 1.3685225894732866e-06,
|
| 15910 |
+
"surrogate": 1.3685225894732866e-06,
|
| 15911 |
+
"kl": -4.5299529460862686e-07,
|
| 15912 |
+
"entropy_mean": 15.621954917907715,
|
| 15913 |
+
"objective": 2.9307179829629604e-06,
|
| 15914 |
+
"effective_kl": 4.5299529460862686e-07,
|
| 15915 |
+
"line_search_backtracks": 0,
|
| 15916 |
+
"update_success": 1.0,
|
| 15917 |
+
"eval_return_mean": -74709.40194568908,
|
| 15918 |
+
"eval_return_std": 12406.761965225764
|
| 15919 |
+
},
|
| 15920 |
+
{
|
| 15921 |
+
"epoch": 1137,
|
| 15922 |
+
"timesteps": 227600,
|
| 15923 |
+
"surrogate_improve": 1.7738342421580455e-06,
|
| 15924 |
+
"surrogate": 1.7738342421580455e-06,
|
| 15925 |
+
"kl": -5.2452087118126656e-08,
|
| 15926 |
+
"entropy_mean": 15.621954917907715,
|
| 15927 |
+
"objective": 3.336029749334557e-06,
|
| 15928 |
+
"effective_kl": 5.2452087118126656e-08,
|
| 15929 |
+
"line_search_backtracks": 0,
|
| 15930 |
+
"update_success": 1.0,
|
| 15931 |
+
"eval_return_mean": -73646.26414769383,
|
| 15932 |
+
"eval_return_std": 13341.96808030034
|
| 15933 |
+
},
|
| 15934 |
+
{
|
| 15935 |
+
"epoch": 1138,
|
| 15936 |
+
"timesteps": 227800,
|
| 15937 |
+
"surrogate_improve": 4.2915343101412873e-07,
|
| 15938 |
+
"surrogate": 4.2915343101412873e-07,
|
| 15939 |
+
"kl": 1.76429750808893e-07,
|
| 15940 |
+
"entropy_mean": 15.621954917907715,
|
| 15941 |
+
"objective": 1.9913488813472213e-06,
|
| 15942 |
+
"effective_kl": 1.76429750808893e-07,
|
| 15943 |
+
"line_search_backtracks": 0,
|
| 15944 |
+
"update_success": 1.0,
|
| 15945 |
+
"eval_return_mean": -77031.51805269597,
|
| 15946 |
+
"eval_return_std": 18143.45991690911
|
| 15947 |
+
},
|
| 15948 |
+
{
|
| 15949 |
+
"epoch": 1139,
|
| 15950 |
+
"timesteps": 228000,
|
| 15951 |
+
"surrogate_improve": 5.102157501823967e-06,
|
| 15952 |
+
"surrogate": 5.102157501823967e-06,
|
| 15953 |
+
"kl": 9.059905892172537e-07,
|
| 15954 |
+
"entropy_mean": 15.621954917907715,
|
| 15955 |
+
"objective": 6.664352895313641e-06,
|
| 15956 |
+
"effective_kl": 9.059905892172537e-07,
|
| 15957 |
+
"line_search_backtracks": 0,
|
| 15958 |
+
"update_success": 1.0,
|
| 15959 |
+
"eval_return_mean": -76823.78209090098,
|
| 15960 |
+
"eval_return_std": 7799.7910229761355
|
| 15961 |
}
|
| 15962 |
]
|
HumanoidStandup-v5/ero_trpo/seed_2/latest/metadata.json
CHANGED
|
@@ -16,22 +16,22 @@
|
|
| 16 |
"batch_size": 200
|
| 17 |
},
|
| 18 |
"progress": {
|
| 19 |
-
"epoch":
|
| 20 |
-
"timesteps":
|
| 21 |
},
|
| 22 |
"metrics": {
|
| 23 |
-
"epoch":
|
| 24 |
-
"timesteps":
|
| 25 |
-
"surrogate_improve":
|
| 26 |
-
"surrogate":
|
| 27 |
-
"kl":
|
| 28 |
"entropy_mean": 15.621954917907715,
|
| 29 |
-
"objective":
|
| 30 |
-
"effective_kl":
|
| 31 |
"line_search_backtracks": 0,
|
| 32 |
"update_success": 1.0,
|
| 33 |
-
"eval_return_mean": -
|
| 34 |
-
"eval_return_std":
|
| 35 |
},
|
| 36 |
"variant": "ero_trpo",
|
| 37 |
"uses_entropy": true,
|
|
|
|
| 16 |
"batch_size": 200
|
| 17 |
},
|
| 18 |
"progress": {
|
| 19 |
+
"epoch": 1140,
|
| 20 |
+
"timesteps": 228000
|
| 21 |
},
|
| 22 |
"metrics": {
|
| 23 |
+
"epoch": 1139,
|
| 24 |
+
"timesteps": 228000,
|
| 25 |
+
"surrogate_improve": 5.102157501823967e-06,
|
| 26 |
+
"surrogate": 5.102157501823967e-06,
|
| 27 |
+
"kl": 9.059905892172537e-07,
|
| 28 |
"entropy_mean": 15.621954917907715,
|
| 29 |
+
"objective": 6.664352895313641e-06,
|
| 30 |
+
"effective_kl": 9.059905892172537e-07,
|
| 31 |
"line_search_backtracks": 0,
|
| 32 |
"update_success": 1.0,
|
| 33 |
+
"eval_return_mean": -76823.78209090098,
|
| 34 |
+
"eval_return_std": 7799.7910229761355
|
| 35 |
},
|
| 36 |
"variant": "ero_trpo",
|
| 37 |
"uses_entropy": true,
|
HumanoidStandup-v5/ero_trpo/seed_2/latest/policy.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 189763
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c75d3cd579ad01fad0fecfeabb0aef7d07a99407457862ff4051712af640488e
|
| 3 |
size 189763
|
HumanoidStandup-v5/ero_trpo/seed_2/latest/progress.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"timesteps":
|
| 4 |
-
"history_len":
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1140,
|
| 3 |
+
"timesteps": 228000,
|
| 4 |
+
"history_len": 1140
|
| 5 |
}
|
HumanoidStandup-v5/ero_trpo/seed_2/latest/value.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 181184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc704d56dfef2dd548abeb92212f649750de191e3a28096a194882b96c0759f2
|
| 3 |
size 181184
|