Upload folder using huggingface_hub
Browse files- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/env.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/env_sv.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/eval.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/eval_sv.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/online_agent.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/online_agent_sv.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1050000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1100000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1150000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1200000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1250000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1300000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1350000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1400000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1450000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1500000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/progress.tk +1 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/env.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/env_sv.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/eval.csv
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
avg_gripper_contact_length,num_gripper_contacts,prev_qpos,prev_qvel,qpos,qvel,control,time,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
|
| 2 |
+
0.0,0.0,-0.056104481875626167,0.00965955659185523,-0.055577424105230734,0.032105493900867726,28.414927549922464,17.43999999999905,0.64,8817.84,-0.54,-534.5,346.8,1.1856263256072999,1050000
|
| 3 |
+
0.0,0.0,-0.028196353643132825,-0.006507045256664049,-0.027988648956679022,-0.01360665342827997,29.918348039561444,12.491999999999807,0.9,24381.6,-0.1,-352.84,247.84,0.8723200559616089,1100000
|
| 4 |
+
0.0,0.0,-0.01678806717901668,-0.016821665896033643,-0.017287196471491947,-0.0006340819555539893,30.82180825188973,11.17099999999969,0.92,36539.9,-0.14,-333.82,221.42,0.7761707878112794,1150000
|
| 5 |
+
0.0,0.0,-0.03492612038667972,-0.021291746111461195,-0.03577553838918914,-0.021230092945996027,32.31283365234904,10.727999999999545,0.92,47857.68,-0.12,-326.54,212.56,0.7491395950317383,1200000
|
| 6 |
+
0.0,0.0,-0.006861347154022058,-0.02914724662599161,-0.008053589108161301,-0.03725394149021834,34.29711691488962,8.268999999999762,1.0,57441.26,0.0,-239.24,163.38,0.5823695182800293,1250000
|
| 7 |
+
0.0,0.0,-0.007150882360410447,-0.030646396508609543,-0.008516127941315614,-0.03195985962179106,34.9596218394712,8.871999999999527,0.96,66530.52,-0.04,-264.88,175.44,0.6231310129165649,1300000
|
| 8 |
+
0.0,0.0,-0.020938824085340525,-0.03625045459667914,-0.022243098496830777,-0.04218146087052397,34.55468668502505,8.979999999999654,0.98,75711.9,-0.04,-261.68,177.6,0.6298216390609741,1350000
|
| 9 |
+
0.0,0.0,-0.005745538064453098,-0.03961718311199692,-0.007294498587848788,-0.049029397119080026,34.481886427374775,8.03899999999969,1.0,84539.62,0.0,-240.4,158.78,0.5687006950378418,1400000
|
| 10 |
+
0.0,0.0,0.0014078112485152532,-0.044224364508666174,-0.0003920537192802888,-0.045250874296894825,34.624086635337115,8.180999999999608,0.98,92455.18,-0.02,-239.04,161.62,0.5727093172073364,1450000
|
| 11 |
+
0.0,0.0,0.004625157062095984,-0.041136977839063345,0.0031428443647489733,-0.048765230993522195,35.40798848421698,8.286999999999797,1.0,101202.08,0.0,-243.92,163.74,0.5806734180450439,1500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/eval_sv.csv
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
avg_gripper_contact_length,num_gripper_contacts,prev_qpos,prev_qvel,qpos,qvel,control,time,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
|
| 2 |
+
0.0,0.0,-0.056104481875626167,0.00965955659185523,-0.055577424105230734,0.032105493900867726,28.414927549922464,17.43999999999905,0.64,8817.84,-0.54,-534.5,346.8,1.1856263256072999,1050000
|
| 3 |
+
0.0,0.0,-0.028196353643132825,-0.006507045256664049,-0.027988648956679022,-0.01360665342827997,29.918348039561444,12.491999999999807,0.9,24381.6,-0.1,-352.84,247.84,0.8723200559616089,1100000
|
| 4 |
+
0.0,0.0,-0.01678806717901668,-0.016821665896033643,-0.017287196471491947,-0.0006340819555539893,30.82180825188973,11.17099999999969,0.92,36539.9,-0.14,-333.82,221.42,0.7761707878112794,1150000
|
| 5 |
+
0.0,0.0,-0.03492612038667972,-0.021291746111461195,-0.03577553838918914,-0.021230092945996027,32.31283365234904,10.727999999999545,0.92,47857.68,-0.12,-326.54,212.56,0.7491395950317383,1200000
|
| 6 |
+
0.0,0.0,-0.006861347154022058,-0.02914724662599161,-0.008053589108161301,-0.03725394149021834,34.29711691488962,8.268999999999762,1.0,57441.26,0.0,-239.24,163.38,0.5823695182800293,1250000
|
| 7 |
+
0.0,0.0,-0.007150882360410447,-0.030646396508609543,-0.008516127941315614,-0.03195985962179106,34.9596218394712,8.871999999999527,0.96,66530.52,-0.04,-264.88,175.44,0.6231310129165649,1300000
|
| 8 |
+
0.0,0.0,-0.020938824085340525,-0.03625045459667914,-0.022243098496830777,-0.04218146087052397,34.55468668502505,8.979999999999654,0.98,75711.9,-0.04,-261.68,177.6,0.6298216390609741,1350000
|
| 9 |
+
0.0,0.0,-0.005745538064453098,-0.03961718311199692,-0.007294498587848788,-0.049029397119080026,34.481886427374775,8.03899999999969,1.0,84539.62,0.0,-240.4,158.78,0.5687006950378418,1400000
|
| 10 |
+
0.0,0.0,0.0014078112485152532,-0.044224364508666174,-0.0003920537192802888,-0.045250874296894825,34.624086635337115,8.180999999999608,0.98,92455.18,-0.02,-239.04,161.62,0.5727093172073364,1450000
|
| 11 |
+
0.0,0.0,0.004625157062095984,-0.041136977839063345,0.0031428443647489733,-0.048765230993522195,35.40798848421698,8.286999999999797,1.0,101202.08,0.0,-243.92,163.74,0.5806734180450439,1500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/online_agent.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
0.17347135,5.90093,-73.36169,-179.08669,-203.21951,1.9280142,-1.909731,31.355469,1005000
|
| 3 |
+
0.1684382,10.234735,-69.197586,-175.41783,-202.9411,1.3715338,-1.3187234,50.25828,1010000
|
| 4 |
+
0.18393531,14.585149,-60.574486,-175.24048,-202.8755,0.29196468,-0.44904202,26.025732,1015000
|
| 5 |
+
0.18991858,11.292845,-61.194885,-172.22453,-203.08769,0.2506041,-0.25699937,21.650875,1020000
|
| 6 |
+
0.2076874,8.784673,-69.846634,-172.90347,-204.0363,0.44502476,-0.5486853,30.130198,1025000
|
| 7 |
+
0.16656232,13.242296,-74.33708,-171.50676,-203.43088,0.49015757,-0.9767264,54.921032,1030000
|
| 8 |
+
0.18845105,14.604556,-27.456911,-171.29265,-203.21126,0.48652247,-0.34295225,27.038185,1035000
|
| 9 |
+
0.1413931,11.660407,-77.663376,-173.57117,-203.05383,0.6497879,-0.8626937,46.792267,1040000
|
| 10 |
+
0.17850752,13.480176,-22.139927,-172.30887,-203.0407,0.743928,-0.57930434,34.951385,1045000
|
| 11 |
+
0.18840505,12.892665,-25.147072,-172.01012,-203.50912,1.2132223,-1.3992286,62.029957,1050000
|
| 12 |
+
0.18530959,15.150882,-12.278787,-168.91234,-203.64256,0.8504161,-0.8691534,45.310593,1055000
|
| 13 |
+
0.18377176,17.924212,-41.02985,-166.534,-202.99442,0.801869,-0.8566096,37.93057,1060000
|
| 14 |
+
0.1758594,17.082483,-37.995117,-167.35413,-203.70247,0.565538,-0.56971973,35.816696,1065000
|
| 15 |
+
0.19697335,21.161345,-27.647785,-163.24486,-203.47195,0.59294116,-0.46152797,38.685875,1070000
|
| 16 |
+
0.19566488,15.383319,-11.2593975,-164.91624,-204.2385,0.5937203,-0.5586049,40.153,1075000
|
| 17 |
+
0.17804307,18.89899,-27.25436,-164.74112,-203.58965,1.2506992,-1.2588226,46.17302,1080000
|
| 18 |
+
0.1930997,14.208649,-35.89524,-161.08025,-203.8039,0.6595463,-0.5390871,47.36072,1085000
|
| 19 |
+
0.1657325,24.117147,-20.42089,-160.37846,-203.94133,0.82980025,-0.900913,53.524582,1090000
|
| 20 |
+
0.1590005,20.501593,-13.5274935,-159.20308,-203.2165,0.50724894,-0.5666389,46.672733,1095000
|
| 21 |
+
0.19034022,12.451739,-33.892307,-157.74379,-203.97652,3.3562782,-4.32677,87.119675,1100000
|
| 22 |
+
0.18436764,19.661573,-6.4743047,-159.56938,-204.74158,0.8012444,-0.82251436,61.006588,1105000
|
| 23 |
+
0.16871017,15.6916685,-29.800917,-158.72914,-204.33148,0.497647,-0.52789456,34.536964,1110000
|
| 24 |
+
0.13838843,19.468287,-3.779633,-155.81433,-203.00735,0.40689236,-0.5108659,39.83889,1115000
|
| 25 |
+
0.18675524,19.829262,-3.0764732,-157.27354,-204.48497,1.5369879,-1.3549589,72.93087,1120000
|
| 26 |
+
0.20588663,15.856033,-3.3475807,-157.73405,-204.74448,2.608074,-2.679611,97.42116,1125000
|
| 27 |
+
0.17124015,18.926558,-19.840965,-153.86609,-204.51595,0.5630286,-0.85666287,50.08359,1130000
|
| 28 |
+
0.18771128,13.961902,2.4664607,-155.10738,-204.30788,0.4932894,-0.48521554,38.661003,1135000
|
| 29 |
+
0.19530314,13.57979,-16.684574,-150.7271,-203.15118,0.5525311,-0.5837141,38.8601,1140000
|
| 30 |
+
0.17517184,20.662165,-15.511193,-151.67699,-204.50113,1.4436568,-1.7871329,70.246704,1145000
|
| 31 |
+
0.16341048,11.083537,-12.2842655,-150.58456,-203.2449,0.5224148,-0.5077268,37.286617,1150000
|
| 32 |
+
0.18711662,14.502008,-7.3756304,-150.56306,-203.71104,1.3305608,-1.3269451,47.438843,1155000
|
| 33 |
+
0.2005435,23.874102,-13.949791,-150.98494,-204.19875,1.775566,-1.9221264,79.352646,1160000
|
| 34 |
+
0.20879522,20.563532,-2.6318905,-149.20087,-205.1381,3.3909247,-3.6429086,131.20895,1165000
|
| 35 |
+
0.14771947,15.919011,-17.257467,-149.46948,-204.40788,0.49116018,-0.44995254,40.19165,1170000
|
| 36 |
+
0.17669177,20.832869,-3.2997007,-150.55089,-204.61473,0.5028119,-0.45507672,41.880924,1175000
|
| 37 |
+
0.18829209,19.782545,1.615823,-148.31999,-204.72113,0.8368521,-0.8827328,63.9953,1180000
|
| 38 |
+
0.17796779,17.340815,-35.801796,-149.77544,-203.8866,1.8903836,-2.282413,80.99191,1185000
|
| 39 |
+
0.15722519,14.880928,-2.7760699,-145.57033,-203.58699,0.85264647,-0.7629517,44.609615,1190000
|
| 40 |
+
0.18215705,15.194045,-20.813896,-146.25415,-204.49821,0.72790873,-0.7989139,51.927048,1195000
|
| 41 |
+
0.15934269,11.398469,-10.78726,-148.12263,-205.14568,1.150866,-1.0785217,48.578163,1200000
|
| 42 |
+
0.1430189,21.530018,-5.9747906,-148.25069,-203.78513,0.7327659,-0.40782252,59.50761,1205000
|
| 43 |
+
0.1775859,19.677702,-4.573077,-149.66629,-204.68636,2.489573,-2.8405676,95.57449,1210000
|
| 44 |
+
0.19677727,20.98797,0.76228976,-148.17784,-204.71411,1.6459457,-0.5709649,72.86674,1215000
|
| 45 |
+
0.20992976,16.509668,-17.916906,-149.2191,-203.64809,0.8425442,-0.8232444,45.63152,1220000
|
| 46 |
+
0.19260186,31.638538,1.047735,-140.91911,-203.13278,2.1886091,-1.5795873,88.497986,1225000
|
| 47 |
+
0.20734048,26.57873,-7.381989,-145.37149,-204.08194,1.0307533,-1.0432678,61.91202,1230000
|
| 48 |
+
0.20752443,24.381441,-5.8234053,-141.99455,-203.59557,5.833566,-5.8711786,155.80026,1235000
|
| 49 |
+
0.1791884,14.725853,1.3933246,-144.68481,-204.42464,0.58520484,-0.49292713,42.527527,1240000
|
| 50 |
+
0.18859875,34.258858,-28.10347,-145.20227,-205.0646,2.1217792,-4.2397366,119.284645,1245000
|
| 51 |
+
0.16767886,24.67575,-2.1549063,-135.9595,-203.95326,1.0241538,-0.9772309,61.584805,1250000
|
| 52 |
+
0.19823465,15.931147,-0.41753033,-145.75641,-203.64697,0.47809333,-0.54923105,45.472874,1255000
|
| 53 |
+
0.18131897,15.185756,2.9867337,-141.20512,-204.15305,0.7808598,-0.7457425,44.52932,1260000
|
| 54 |
+
0.16445923,15.247437,-5.129197,-143.31279,-204.67435,0.66128325,-0.75198185,57.277245,1265000
|
| 55 |
+
0.1710063,14.530258,-12.173882,-144.12175,-203.30118,0.6128733,-0.564872,42.13812,1270000
|
| 56 |
+
0.22520666,21.857603,-15.627126,-139.36266,-204.60455,1.2132444,-1.1797484,67.15738,1275000
|
| 57 |
+
0.20025478,21.458933,-20.291637,-144.17467,-204.5708,2.2411954,-1.7913172,66.10466,1280000
|
| 58 |
+
0.17653911,19.623327,0.59746253,-136.90376,-203.45563,0.4938349,-0.63966155,48.35077,1285000
|
| 59 |
+
0.17596956,17.36694,-16.416658,-137.21513,-203.45995,0.93809825,-0.72578526,53.071987,1290000
|
| 60 |
+
0.19730109,15.1301775,3.7830098,-139.30473,-204.0617,0.9055414,-0.9800283,56.421448,1295000
|
| 61 |
+
0.18807319,21.533535,-4.9764686,-141.67757,-203.65569,1.1770113,-1.1154628,69.975494,1300000
|
| 62 |
+
0.16627881,14.754695,2.0705369,-141.0601,-203.17741,0.5096346,-0.43510684,40.934998,1305000
|
| 63 |
+
0.18606938,41.85948,-8.1286125,-136.82019,-203.86797,2.9409778,-2.915147,100.67944,1310000
|
| 64 |
+
0.16950507,11.668364,-8.010771,-141.70427,-201.44995,1.1233683,-1.3120242,56.333885,1315000
|
| 65 |
+
0.15312657,27.933569,-5.4203687,-143.14598,-203.64255,1.3888525,-1.2660265,59.809975,1320000
|
| 66 |
+
0.17390591,14.895856,-2.1154015,-138.39346,-205.02998,1.4534568,-1.4738996,68.31671,1325000
|
| 67 |
+
0.18662472,16.10967,-6.2913876,-137.56267,-204.02786,1.0013145,-0.97190094,52.051937,1330000
|
| 68 |
+
0.20083326,15.703827,-4.20464,-138.23453,-204.79303,0.5401385,-0.4103782,41.126637,1335000
|
| 69 |
+
0.17990401,14.278346,-6.2494044,-140.72635,-203.84032,0.93524396,-1.016164,67.548546,1340000
|
| 70 |
+
0.18437509,22.243002,3.0148747,-146.01276,-204.85497,4.1568313,-4.7844033,150.30264,1345000
|
| 71 |
+
0.19171828,17.629652,0.056771442,-135.45335,-204.13948,0.7501701,-0.6431722,50.22384,1350000
|
| 72 |
+
0.20723288,21.064322,2.3590698,-138.51968,-203.11644,0.9174427,-0.9627235,59.48101,1355000
|
| 73 |
+
0.1648527,12.175722,-3.8985507,-136.67671,-203.29143,0.581145,-0.9434085,49.035915,1360000
|
| 74 |
+
0.16593677,24.584873,-7.368161,-136.31482,-202.91542,0.910726,-0.7824561,59.709698,1365000
|
| 75 |
+
0.19401443,16.026514,-6.7290807,-136.93192,-203.9829,1.2898574,-1.0641137,53.938652,1370000
|
| 76 |
+
0.15752685,13.374867,2.320611,-133.85425,-203.65514,0.7061252,-0.59026754,45.821247,1375000
|
| 77 |
+
0.13456401,13.229395,-4.504763,-137.66512,-203.09229,0.7078867,-0.82086813,49.93144,1380000
|
| 78 |
+
0.15629621,19.04971,-5.094702,-136.8813,-203.40761,0.618274,-0.6237644,49.761242,1385000
|
| 79 |
+
0.14455473,21.026987,-7.464626,-137.15399,-201.79703,0.987266,-1.259927,67.61774,1390000
|
| 80 |
+
0.16485238,29.59235,-6.230971,-137.02649,-202.01201,1.3533604,-1.3554226,59.98937,1395000
|
| 81 |
+
0.14502184,26.625044,1.7255473,-133.44788,-201.67038,0.7869268,-0.8601907,66.08336,1400000
|
| 82 |
+
0.1524814,21.739033,5.471513,-134.97363,-202.81725,1.2232579,-1.254671,54.09939,1405000
|
| 83 |
+
0.1827285,31.349033,-1.2902807,-137.38239,-203.29189,1.7833909,-2.040348,78.70475,1410000
|
| 84 |
+
0.17831473,35.660698,-4.684113,-133.45555,-201.59387,2.477486,-3.1883352,114.198975,1415000
|
| 85 |
+
0.17096226,17.411623,-9.509316,-136.953,-204.18854,0.7123256,-0.70010215,54.589836,1420000
|
| 86 |
+
0.17622453,20.815022,-2.2840714,-130.97375,-205.51173,1.4956614,-2.0207248,98.40172,1425000
|
| 87 |
+
0.15064326,18.520739,0.68866634,-130.11058,-203.42993,1.6312219,-1.8588307,70.44023,1430000
|
| 88 |
+
0.1695524,27.074884,-3.9812627,-135.76462,-205.79048,2.2057667,-2.3080122,84.32126,1435000
|
| 89 |
+
0.18064612,12.291417,-7.7252474,-129.1617,-204.52321,1.2823055,-1.3797349,60.723442,1440000
|
| 90 |
+
0.16974798,13.704808,-13.379714,-133.88066,-201.62999,1.0292861,-1.4036586,62.238792,1445000
|
| 91 |
+
0.16084614,18.41121,-1.4383522,-129.3461,-204.3147,3.2667108,-3.740526,76.81115,1450000
|
| 92 |
+
0.16577034,19.969267,-0.6981807,-130.99966,-204.035,1.672792,-1.7062078,88.94693,1455000
|
| 93 |
+
0.16098559,17.935255,4.203195,-133.94824,-203.07578,1.6724178,-1.5099832,73.31316,1460000
|
| 94 |
+
0.14341368,13.867284,-2.7225268,-133.63231,-204.04726,0.73275965,-0.49028686,48.502213,1465000
|
| 95 |
+
0.14827153,39.60275,-2.6852324,-129.66031,-200.90984,1.0235975,-1.1347495,69.48524,1470000
|
| 96 |
+
0.15477385,15.374255,0.24809808,-129.84802,-204.13777,0.7879417,-0.79512775,47.051144,1475000
|
| 97 |
+
0.15100372,13.952624,0.17277473,-132.45917,-202.859,0.35179487,-0.6224945,36.718513,1480000
|
| 98 |
+
0.14250559,17.76924,-4.0517817,-130.15233,-204.22585,0.69648993,-1.0320195,48.578327,1485000
|
| 99 |
+
0.1602141,18.916563,-2.0683088,-128.29634,-204.84654,0.64884186,-0.6293367,53.363773,1490000
|
| 100 |
+
0.122909784,26.366339,-1.6565945,-127.661865,-203.37157,0.6830265,-0.72842866,55.120346,1495000
|
| 101 |
+
0.1905185,11.91043,2.6787522,-127.86437,-204.56232,0.49235925,-0.911269,45.14097,1500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/online_agent_sv.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
0.17347135,5.90093,-73.36169,-179.08669,-203.21951,1.9280142,-1.909731,31.355469,1005000
|
| 3 |
+
0.1684382,10.234735,-69.197586,-175.41783,-202.9411,1.3715338,-1.3187234,50.25828,1010000
|
| 4 |
+
0.18393531,14.585149,-60.574486,-175.24048,-202.8755,0.29196468,-0.44904202,26.025732,1015000
|
| 5 |
+
0.18991858,11.292845,-61.194885,-172.22453,-203.08769,0.2506041,-0.25699937,21.650875,1020000
|
| 6 |
+
0.2076874,8.784673,-69.846634,-172.90347,-204.0363,0.44502476,-0.5486853,30.130198,1025000
|
| 7 |
+
0.16656232,13.242296,-74.33708,-171.50676,-203.43088,0.49015757,-0.9767264,54.921032,1030000
|
| 8 |
+
0.18845105,14.604556,-27.456911,-171.29265,-203.21126,0.48652247,-0.34295225,27.038185,1035000
|
| 9 |
+
0.1413931,11.660407,-77.663376,-173.57117,-203.05383,0.6497879,-0.8626937,46.792267,1040000
|
| 10 |
+
0.17850752,13.480176,-22.139927,-172.30887,-203.0407,0.743928,-0.57930434,34.951385,1045000
|
| 11 |
+
0.18840505,12.892665,-25.147072,-172.01012,-203.50912,1.2132223,-1.3992286,62.029957,1050000
|
| 12 |
+
0.18530959,15.150882,-12.278787,-168.91234,-203.64256,0.8504161,-0.8691534,45.310593,1055000
|
| 13 |
+
0.18377176,17.924212,-41.02985,-166.534,-202.99442,0.801869,-0.8566096,37.93057,1060000
|
| 14 |
+
0.1758594,17.082483,-37.995117,-167.35413,-203.70247,0.565538,-0.56971973,35.816696,1065000
|
| 15 |
+
0.19697335,21.161345,-27.647785,-163.24486,-203.47195,0.59294116,-0.46152797,38.685875,1070000
|
| 16 |
+
0.19566488,15.383319,-11.2593975,-164.91624,-204.2385,0.5937203,-0.5586049,40.153,1075000
|
| 17 |
+
0.17804307,18.89899,-27.25436,-164.74112,-203.58965,1.2506992,-1.2588226,46.17302,1080000
|
| 18 |
+
0.1930997,14.208649,-35.89524,-161.08025,-203.8039,0.6595463,-0.5390871,47.36072,1085000
|
| 19 |
+
0.1657325,24.117147,-20.42089,-160.37846,-203.94133,0.82980025,-0.900913,53.524582,1090000
|
| 20 |
+
0.1590005,20.501593,-13.5274935,-159.20308,-203.2165,0.50724894,-0.5666389,46.672733,1095000
|
| 21 |
+
0.19034022,12.451739,-33.892307,-157.74379,-203.97652,3.3562782,-4.32677,87.119675,1100000
|
| 22 |
+
0.18436764,19.661573,-6.4743047,-159.56938,-204.74158,0.8012444,-0.82251436,61.006588,1105000
|
| 23 |
+
0.16871017,15.6916685,-29.800917,-158.72914,-204.33148,0.497647,-0.52789456,34.536964,1110000
|
| 24 |
+
0.13838843,19.468287,-3.779633,-155.81433,-203.00735,0.40689236,-0.5108659,39.83889,1115000
|
| 25 |
+
0.18675524,19.829262,-3.0764732,-157.27354,-204.48497,1.5369879,-1.3549589,72.93087,1120000
|
| 26 |
+
0.20588663,15.856033,-3.3475807,-157.73405,-204.74448,2.608074,-2.679611,97.42116,1125000
|
| 27 |
+
0.17124015,18.926558,-19.840965,-153.86609,-204.51595,0.5630286,-0.85666287,50.08359,1130000
|
| 28 |
+
0.18771128,13.961902,2.4664607,-155.10738,-204.30788,0.4932894,-0.48521554,38.661003,1135000
|
| 29 |
+
0.19530314,13.57979,-16.684574,-150.7271,-203.15118,0.5525311,-0.5837141,38.8601,1140000
|
| 30 |
+
0.17517184,20.662165,-15.511193,-151.67699,-204.50113,1.4436568,-1.7871329,70.246704,1145000
|
| 31 |
+
0.16341048,11.083537,-12.2842655,-150.58456,-203.2449,0.5224148,-0.5077268,37.286617,1150000
|
| 32 |
+
0.18711662,14.502008,-7.3756304,-150.56306,-203.71104,1.3305608,-1.3269451,47.438843,1155000
|
| 33 |
+
0.2005435,23.874102,-13.949791,-150.98494,-204.19875,1.775566,-1.9221264,79.352646,1160000
|
| 34 |
+
0.20879522,20.563532,-2.6318905,-149.20087,-205.1381,3.3909247,-3.6429086,131.20895,1165000
|
| 35 |
+
0.14771947,15.919011,-17.257467,-149.46948,-204.40788,0.49116018,-0.44995254,40.19165,1170000
|
| 36 |
+
0.17669177,20.832869,-3.2997007,-150.55089,-204.61473,0.5028119,-0.45507672,41.880924,1175000
|
| 37 |
+
0.18829209,19.782545,1.615823,-148.31999,-204.72113,0.8368521,-0.8827328,63.9953,1180000
|
| 38 |
+
0.17796779,17.340815,-35.801796,-149.77544,-203.8866,1.8903836,-2.282413,80.99191,1185000
|
| 39 |
+
0.15722519,14.880928,-2.7760699,-145.57033,-203.58699,0.85264647,-0.7629517,44.609615,1190000
|
| 40 |
+
0.18215705,15.194045,-20.813896,-146.25415,-204.49821,0.72790873,-0.7989139,51.927048,1195000
|
| 41 |
+
0.15934269,11.398469,-10.78726,-148.12263,-205.14568,1.150866,-1.0785217,48.578163,1200000
|
| 42 |
+
0.1430189,21.530018,-5.9747906,-148.25069,-203.78513,0.7327659,-0.40782252,59.50761,1205000
|
| 43 |
+
0.1775859,19.677702,-4.573077,-149.66629,-204.68636,2.489573,-2.8405676,95.57449,1210000
|
| 44 |
+
0.19677727,20.98797,0.76228976,-148.17784,-204.71411,1.6459457,-0.5709649,72.86674,1215000
|
| 45 |
+
0.20992976,16.509668,-17.916906,-149.2191,-203.64809,0.8425442,-0.8232444,45.63152,1220000
|
| 46 |
+
0.19260186,31.638538,1.047735,-140.91911,-203.13278,2.1886091,-1.5795873,88.497986,1225000
|
| 47 |
+
0.20734048,26.57873,-7.381989,-145.37149,-204.08194,1.0307533,-1.0432678,61.91202,1230000
|
| 48 |
+
0.20752443,24.381441,-5.8234053,-141.99455,-203.59557,5.833566,-5.8711786,155.80026,1235000
|
| 49 |
+
0.1791884,14.725853,1.3933246,-144.68481,-204.42464,0.58520484,-0.49292713,42.527527,1240000
|
| 50 |
+
0.18859875,34.258858,-28.10347,-145.20227,-205.0646,2.1217792,-4.2397366,119.284645,1245000
|
| 51 |
+
0.16767886,24.67575,-2.1549063,-135.9595,-203.95326,1.0241538,-0.9772309,61.584805,1250000
|
| 52 |
+
0.19823465,15.931147,-0.41753033,-145.75641,-203.64697,0.47809333,-0.54923105,45.472874,1255000
|
| 53 |
+
0.18131897,15.185756,2.9867337,-141.20512,-204.15305,0.7808598,-0.7457425,44.52932,1260000
|
| 54 |
+
0.16445923,15.247437,-5.129197,-143.31279,-204.67435,0.66128325,-0.75198185,57.277245,1265000
|
| 55 |
+
0.1710063,14.530258,-12.173882,-144.12175,-203.30118,0.6128733,-0.564872,42.13812,1270000
|
| 56 |
+
0.22520666,21.857603,-15.627126,-139.36266,-204.60455,1.2132444,-1.1797484,67.15738,1275000
|
| 57 |
+
0.20025478,21.458933,-20.291637,-144.17467,-204.5708,2.2411954,-1.7913172,66.10466,1280000
|
| 58 |
+
0.17653911,19.623327,0.59746253,-136.90376,-203.45563,0.4938349,-0.63966155,48.35077,1285000
|
| 59 |
+
0.17596956,17.36694,-16.416658,-137.21513,-203.45995,0.93809825,-0.72578526,53.071987,1290000
|
| 60 |
+
0.19730109,15.1301775,3.7830098,-139.30473,-204.0617,0.9055414,-0.9800283,56.421448,1295000
|
| 61 |
+
0.18807319,21.533535,-4.9764686,-141.67757,-203.65569,1.1770113,-1.1154628,69.975494,1300000
|
| 62 |
+
0.16627881,14.754695,2.0705369,-141.0601,-203.17741,0.5096346,-0.43510684,40.934998,1305000
|
| 63 |
+
0.18606938,41.85948,-8.1286125,-136.82019,-203.86797,2.9409778,-2.915147,100.67944,1310000
|
| 64 |
+
0.16950507,11.668364,-8.010771,-141.70427,-201.44995,1.1233683,-1.3120242,56.333885,1315000
|
| 65 |
+
0.15312657,27.933569,-5.4203687,-143.14598,-203.64255,1.3888525,-1.2660265,59.809975,1320000
|
| 66 |
+
0.17390591,14.895856,-2.1154015,-138.39346,-205.02998,1.4534568,-1.4738996,68.31671,1325000
|
| 67 |
+
0.18662472,16.10967,-6.2913876,-137.56267,-204.02786,1.0013145,-0.97190094,52.051937,1330000
|
| 68 |
+
0.20083326,15.703827,-4.20464,-138.23453,-204.79303,0.5401385,-0.4103782,41.126637,1335000
|
| 69 |
+
0.17990401,14.278346,-6.2494044,-140.72635,-203.84032,0.93524396,-1.016164,67.548546,1340000
|
| 70 |
+
0.18437509,22.243002,3.0148747,-146.01276,-204.85497,4.1568313,-4.7844033,150.30264,1345000
|
| 71 |
+
0.19171828,17.629652,0.056771442,-135.45335,-204.13948,0.7501701,-0.6431722,50.22384,1350000
|
| 72 |
+
0.20723288,21.064322,2.3590698,-138.51968,-203.11644,0.9174427,-0.9627235,59.48101,1355000
|
| 73 |
+
0.1648527,12.175722,-3.8985507,-136.67671,-203.29143,0.581145,-0.9434085,49.035915,1360000
|
| 74 |
+
0.16593677,24.584873,-7.368161,-136.31482,-202.91542,0.910726,-0.7824561,59.709698,1365000
|
| 75 |
+
0.19401443,16.026514,-6.7290807,-136.93192,-203.9829,1.2898574,-1.0641137,53.938652,1370000
|
| 76 |
+
0.15752685,13.374867,2.320611,-133.85425,-203.65514,0.7061252,-0.59026754,45.821247,1375000
|
| 77 |
+
0.13456401,13.229395,-4.504763,-137.66512,-203.09229,0.7078867,-0.82086813,49.93144,1380000
|
| 78 |
+
0.15629621,19.04971,-5.094702,-136.8813,-203.40761,0.618274,-0.6237644,49.761242,1385000
|
| 79 |
+
0.14455473,21.026987,-7.464626,-137.15399,-201.79703,0.987266,-1.259927,67.61774,1390000
|
| 80 |
+
0.16485238,29.59235,-6.230971,-137.02649,-202.01201,1.3533604,-1.3554226,59.98937,1395000
|
| 81 |
+
0.14502184,26.625044,1.7255473,-133.44788,-201.67038,0.7869268,-0.8601907,66.08336,1400000
|
| 82 |
+
0.1524814,21.739033,5.471513,-134.97363,-202.81725,1.2232579,-1.254671,54.09939,1405000
|
| 83 |
+
0.1827285,31.349033,-1.2902807,-137.38239,-203.29189,1.7833909,-2.040348,78.70475,1410000
|
| 84 |
+
0.17831473,35.660698,-4.684113,-133.45555,-201.59387,2.477486,-3.1883352,114.198975,1415000
|
| 85 |
+
0.17096226,17.411623,-9.509316,-136.953,-204.18854,0.7123256,-0.70010215,54.589836,1420000
|
| 86 |
+
0.17622453,20.815022,-2.2840714,-130.97375,-205.51173,1.4956614,-2.0207248,98.40172,1425000
|
| 87 |
+
0.15064326,18.520739,0.68866634,-130.11058,-203.42993,1.6312219,-1.8588307,70.44023,1430000
|
| 88 |
+
0.1695524,27.074884,-3.9812627,-135.76462,-205.79048,2.2057667,-2.3080122,84.32126,1435000
|
| 89 |
+
0.18064612,12.291417,-7.7252474,-129.1617,-204.52321,1.2823055,-1.3797349,60.723442,1440000
|
| 90 |
+
0.16974798,13.704808,-13.379714,-133.88066,-201.62999,1.0292861,-1.4036586,62.238792,1445000
|
| 91 |
+
0.16084614,18.41121,-1.4383522,-129.3461,-204.3147,3.2667108,-3.740526,76.81115,1450000
|
| 92 |
+
0.16577034,19.969267,-0.6981807,-130.99966,-204.035,1.672792,-1.7062078,88.94693,1455000
|
| 93 |
+
0.16098559,17.935255,4.203195,-133.94824,-203.07578,1.6724178,-1.5099832,73.31316,1460000
|
| 94 |
+
0.14341368,13.867284,-2.7225268,-133.63231,-204.04726,0.73275965,-0.49028686,48.502213,1465000
|
| 95 |
+
0.14827153,39.60275,-2.6852324,-129.66031,-200.90984,1.0235975,-1.1347495,69.48524,1470000
|
| 96 |
+
0.15477385,15.374255,0.24809808,-129.84802,-204.13777,0.7879417,-0.79512775,47.051144,1475000
|
| 97 |
+
0.15100372,13.952624,0.17277473,-132.45917,-202.859,0.35179487,-0.6224945,36.718513,1480000
|
| 98 |
+
0.14250559,17.76924,-4.0517817,-130.15233,-204.22585,0.69648993,-1.0320195,48.578327,1485000
|
| 99 |
+
0.1602141,18.916563,-2.0683088,-128.29634,-204.84654,0.64884186,-0.6293367,53.363773,1490000
|
| 100 |
+
0.122909784,26.366339,-1.6565945,-127.661865,-203.37157,0.6830265,-0.72842866,55.120346,1495000
|
| 101 |
+
0.1905185,11.91043,2.6787522,-127.86437,-204.56232,0.49235925,-0.911269,45.14097,1500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1050000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e372beb59ba257842357ae910b50632af3f9d356f4156df5b4ea03a2d41abfbc
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1100000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2fc31b91cb73969fc07c6444eb5ae9c319421911fbe845477c1bbba106a68aa
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1150000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c9009b0867e606cc48d05f87e8ab09895150f5948f7ac7098bbe2fda5d5adcc
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1200000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4497cc332c2d87ea0d2da5440c0b182259e489616d3db0c851ad10720f843e9a
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1250000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b6540cd065a55a11a7cb5c11ea8f20e162883a22fa1423c3f183b2cf6261cfd
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1300000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b0e9b3a160b40e9d6fcb687b1b1e52e2ab2f6d6b96c78a7928065834da942f7
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1350000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:208304166a7418cbd78ec171cfa235959ef1dae225e7c6e9ee0c9641eea410e2
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1400000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cb34d0400f455442997da82ddf14847425c3f981b8bbd6cc3691f7f0e39e084
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1450000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ce9063a2e89dfbe33fb5b684a50444a5d590910c2dc0e774bd6831c799a39a6
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/params_1500000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f49bf298f7bc1b031b2ee4adc7259f73577c8ba7e1007458d360047fd8745edc
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_220533/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/a77nfv68
|