Upload folder using huggingface_hub
Browse files- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/env.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/env_sv.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/eval.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/eval_sv.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/online_agent.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/online_agent_sv.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_1000000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_1050000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_1100000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_1150000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_1200000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_750000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_800000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_850000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_900000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_950000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/progress.tk +1 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/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/20260318_231719/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/20260318_231719/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,-0.01769064057726658,0.0021582588520755158,-0.017337941509766773,0.002161080459742589,27.874489750655798,15.821999999999107,0.72,8252.3,-0.34,-443.26,314.44,1.09254900932312,750000
|
| 3 |
+
0.0,0.0,-0.018395832912548506,-0.012589216348937029,-0.018784093713676484,-0.01831392264821251,33.23757015105626,12.750999999999726,0.86,22821.36,-0.16,-379.62,253.02,0.8697344303131104,800000
|
| 4 |
+
0.0,0.0,-0.005265256241206246,-0.024901392264038275,-0.006015797936625421,-0.022086675575120215,34.242215605974735,10.094999999999791,0.96,34038.82,-0.04,-298.72,199.9,0.725063910484314,850000
|
| 5 |
+
0.0,0.0,0.02127322073519765,-0.031096860721683835,0.02072354282236381,-0.031041994683609502,34.88017693578445,9.400999999999602,0.94,44460.74,-0.1,-280.88,186.02,0.80793212890625,900000
|
| 6 |
+
0.0,0.0,0.01638632743311394,-0.04182507297843233,0.014770835103256866,-0.04232622592207814,33.70004247485463,9.194999999999645,0.96,54248.38,-0.06,-268.34,181.9,0.7043047666549682,950000
|
| 7 |
+
0.0,0.0,0.03190229535712844,-0.04314824571506195,0.03022331731535237,-0.05062337912787518,34.82211376267022,9.054999999999646,0.96,64207.08,-0.06,-267.44,179.1,0.624876766204834,1000000
|
| 8 |
+
0.0,0.0,0.018814342310996404,-0.051439723415899787,0.017006961301741886,-0.056991636492978684,35.45806521200516,7.965999999999624,0.98,72674.32,-0.04,-233.14,157.32,0.5682600259780883,1050000
|
| 9 |
+
0.0,0.0,0.016454358558499006,-0.04839779269497177,0.014966900544332137,-0.05422411151519963,33.020786808383136,7.829999999999529,0.96,80538.82,-0.04,-228.9,154.6,0.9080002117156982,1100000
|
| 10 |
+
0.0,0.0,0.027493094504927592,-0.05130084884403798,0.025494050322531946,-0.0627999406473633,35.21801304032946,7.33199999999958,0.98,88601.64,-0.04,-209.86,144.64,0.7639012813568116,1150000
|
| 11 |
+
0.0,0.0,0.029292582356013834,-0.054875433647973454,0.02702536783278744,-0.05832465913059667,35.5408642193544,6.80199999999961,1.0,95869.46,0.0,-191.42,134.04,0.48296854972839354,1200000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/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,-0.01769064057726658,0.0021582588520755158,-0.017337941509766773,0.002161080459742589,27.874489750655798,15.821999999999107,0.72,8252.3,-0.34,-443.26,314.44,1.09254900932312,750000
|
| 3 |
+
0.0,0.0,-0.018395832912548506,-0.012589216348937029,-0.018784093713676484,-0.01831392264821251,33.23757015105626,12.750999999999726,0.86,22821.36,-0.16,-379.62,253.02,0.8697344303131104,800000
|
| 4 |
+
0.0,0.0,-0.005265256241206246,-0.024901392264038275,-0.006015797936625421,-0.022086675575120215,34.242215605974735,10.094999999999791,0.96,34038.82,-0.04,-298.72,199.9,0.725063910484314,850000
|
| 5 |
+
0.0,0.0,0.02127322073519765,-0.031096860721683835,0.02072354282236381,-0.031041994683609502,34.88017693578445,9.400999999999602,0.94,44460.74,-0.1,-280.88,186.02,0.80793212890625,900000
|
| 6 |
+
0.0,0.0,0.01638632743311394,-0.04182507297843233,0.014770835103256866,-0.04232622592207814,33.70004247485463,9.194999999999645,0.96,54248.38,-0.06,-268.34,181.9,0.7043047666549682,950000
|
| 7 |
+
0.0,0.0,0.03190229535712844,-0.04314824571506195,0.03022331731535237,-0.05062337912787518,34.82211376267022,9.054999999999646,0.96,64207.08,-0.06,-267.44,179.1,0.624876766204834,1000000
|
| 8 |
+
0.0,0.0,0.018814342310996404,-0.051439723415899787,0.017006961301741886,-0.056991636492978684,35.45806521200516,7.965999999999624,0.98,72674.32,-0.04,-233.14,157.32,0.5682600259780883,1050000
|
| 9 |
+
0.0,0.0,0.016454358558499006,-0.04839779269497177,0.014966900544332137,-0.05422411151519963,33.020786808383136,7.829999999999529,0.96,80538.82,-0.04,-228.9,154.6,0.9080002117156982,1100000
|
| 10 |
+
0.0,0.0,0.027493094504927592,-0.05130084884403798,0.025494050322531946,-0.0627999406473633,35.21801304032946,7.33199999999958,0.98,88601.64,-0.04,-209.86,144.64,0.7639012813568116,1150000
|
| 11 |
+
0.0,0.0,0.029292582356013834,-0.054875433647973454,0.02702536783278744,-0.05832465913059667,35.5408642193544,6.80199999999961,1.0,95869.46,0.0,-191.42,134.04,0.48296854972839354,1200000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/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 |
+
0.19734979,12.158076,-82.89527,-179.59836,-202.96623,0.278031,-0.28499767,25.035858,705000
|
| 3 |
+
0.1852695,11.618044,-66.675415,-175.34917,-202.97342,0.51197845,-0.4128598,35.898773,710000
|
| 4 |
+
0.18313277,11.644752,-57.274075,-174.17952,-202.67297,0.40690404,-0.39859676,33.72863,715000
|
| 5 |
+
0.17939295,24.8678,-58.616425,-171.00713,-203.2286,0.54949427,-0.3510325,49.306488,720000
|
| 6 |
+
0.16664076,14.367284,-64.67236,-171.56033,-203.43886,0.3044897,-0.4059464,37.278584,725000
|
| 7 |
+
0.17932072,12.902194,-74.28653,-171.6,-203.60844,0.9426574,-1.3317713,33.415688,730000
|
| 8 |
+
0.17362824,20.91267,-70.79747,-170.0105,-203.65671,0.7493851,-0.39160642,55.651237,735000
|
| 9 |
+
0.16412419,15.196652,-15.869219,-168.98079,-203.34488,1.7530789,-1.5437537,62.40531,740000
|
| 10 |
+
0.15811485,18.349861,-49.493793,-168.71954,-204.76578,0.60354334,-0.41941392,39.97914,745000
|
| 11 |
+
0.15477172,19.195707,-61.856533,-169.67902,-202.88521,0.9101194,-0.9771488,60.708946,750000
|
| 12 |
+
0.18666527,18.34709,-46.065063,-166.51929,-204.34549,0.50597245,-0.9651483,41.05211,755000
|
| 13 |
+
0.21959934,19.165289,-46.33205,-165.65994,-203.91354,0.6652424,-0.66404325,51.135223,760000
|
| 14 |
+
0.18746266,10.738433,-53.204456,-165.84476,-204.72414,0.64642024,-0.6095129,34.91669,765000
|
| 15 |
+
0.1894221,18.936403,-31.931658,-161.55591,-204.10118,2.097733,-2.265086,69.34618,770000
|
| 16 |
+
0.19033939,14.603607,-20.103714,-164.4762,-203.81183,0.87403023,-0.914203,46.71957,775000
|
| 17 |
+
0.17221588,23.689674,-14.781785,-164.75716,-203.8404,1.0618999,-1.0379771,45.220966,780000
|
| 18 |
+
0.19100416,21.99935,-6.7875185,-162.55876,-204.59833,0.58770907,-0.62456614,42.182064,785000
|
| 19 |
+
0.1934581,11.412819,-38.923985,-159.38937,-204.71434,0.44393533,-0.40238634,37.753845,790000
|
| 20 |
+
0.16224545,16.958462,-64.84124,-162.5749,-203.78778,0.74775106,-0.6932399,36.907867,795000
|
| 21 |
+
0.19623686,15.936576,-32.822094,-154.84354,-203.92636,1.6369544,-1.7699838,55.360718,800000
|
| 22 |
+
0.19743186,16.263968,-2.6504254,-158.47456,-204.03447,0.55890286,-0.36080492,39.62986,805000
|
| 23 |
+
0.17753986,25.930155,-18.512241,-156.22935,-203.91864,2.2388258,-2.7272708,85.78496,810000
|
| 24 |
+
0.18831806,17.362043,2.1293378,-152.54225,-203.96184,0.80720615,-0.94299006,58.142868,815000
|
| 25 |
+
0.1686388,20.312597,-2.296115,-155.22476,-203.30089,0.895463,-0.6531258,50.42764,820000
|
| 26 |
+
0.17810011,13.941251,-32.70702,-157.86278,-204.34656,0.3026883,-0.6852456,39.567955,825000
|
| 27 |
+
0.17763877,18.608892,-8.233587,-151.74117,-203.66884,0.6441805,-0.65345937,43.234375,830000
|
| 28 |
+
0.18384439,18.758818,2.5820441,-152.93706,-203.67894,0.5354126,-0.5106289,45.426056,835000
|
| 29 |
+
0.19278386,13.458667,-16.083511,-148.51445,-203.11081,1.3597246,-1.3707712,55.73405,840000
|
| 30 |
+
0.17248333,18.67421,-23.11421,-150.3443,-204.50337,0.98392254,-0.7614136,53.390423,845000
|
| 31 |
+
0.16403292,12.271911,-29.25567,-150.76163,-203.92276,0.5310791,-0.75392354,46.145267,850000
|
| 32 |
+
0.17459702,11.215972,-18.909088,-148.28172,-204.19917,2.6438384,-3.208866,77.40133,855000
|
| 33 |
+
0.18862906,23.254002,-6.561493,-150.2967,-204.44604,0.9530208,-1.5024422,67.0871,860000
|
| 34 |
+
0.17338906,13.765922,-0.07669397,-146.81943,-204.67154,0.45399266,-0.62716275,39.683502,865000
|
| 35 |
+
0.15905102,11.90585,-19.941618,-146.671,-204.53606,0.35442072,-0.38836238,36.658005,870000
|
| 36 |
+
0.18034741,22.783735,-14.198748,-149.3115,-205.72087,1.6740335,-1.4452091,65.10074,875000
|
| 37 |
+
0.18252783,13.008597,6.1564503,-147.2941,-203.43137,0.5988279,-0.7647277,53.987865,880000
|
| 38 |
+
0.1435834,17.460016,-8.057041,-144.58015,-204.33107,0.8543537,-1.0138888,55.814655,885000
|
| 39 |
+
0.17323996,16.30998,0.21934459,-142.44115,-203.1333,1.4539183,-1.8899843,60.423645,890000
|
| 40 |
+
0.15936488,18.683731,-5.604309,-141.43024,-205.2219,2.995109,-2.8591518,86.52049,895000
|
| 41 |
+
0.18954258,23.678373,-2.455367,-143.84195,-205.1903,1.3857644,-1.844979,79.01305,900000
|
| 42 |
+
0.18609118,17.199371,-1.8540422,-144.55446,-205.44958,1.3399328,-1.292887,51.6789,905000
|
| 43 |
+
0.1720098,18.902761,-3.7006242,-142.85623,-203.88338,0.52744985,-0.84586924,51.641003,910000
|
| 44 |
+
0.19384916,15.637293,-8.115197,-144.74223,-204.33583,0.6774129,-0.45576695,50.80797,915000
|
| 45 |
+
0.1788258,18.482878,-2.607226,-141.59375,-202.10895,0.5757939,-1.109723,52.83832,920000
|
| 46 |
+
0.17075652,19.74214,-1.1827828,-137.19777,-203.99048,0.9248617,-0.90003884,54.647224,925000
|
| 47 |
+
0.1838356,16.588224,-6.0791593,-140.03738,-204.8663,1.0801271,-0.97956526,64.20477,930000
|
| 48 |
+
0.19859543,11.767452,-3.147247,-137.52518,-203.18652,1.7149197,-1.6453171,57.57158,935000
|
| 49 |
+
0.21849173,16.195755,2.7960036,-139.67313,-203.47176,2.0241451,-2.4792135,66.88157,940000
|
| 50 |
+
0.18707311,14.920328,2.171465,-141.33028,-206.32945,1.6812749,-2.788498,62.44541,945000
|
| 51 |
+
0.18903717,22.202253,-9.046592,-131.62624,-203.23895,1.1225345,-2.0350575,71.93042,950000
|
| 52 |
+
0.17658487,14.780423,-6.775141,-142.946,-202.85603,2.1114259,-2.2847726,82.52771,955000
|
| 53 |
+
0.1658981,21.725815,4.49814,-138.65727,-203.776,2.712473,-3.0881028,94.3233,960000
|
| 54 |
+
0.18304056,26.055769,-23.18895,-144.58426,-203.97043,2.8877423,-3.1500926,80.53017,965000
|
| 55 |
+
0.18478402,16.602009,-11.756989,-139.01978,-201.0606,1.0263479,-1.4818804,87.75327,970000
|
| 56 |
+
0.17073059,19.906624,-13.872733,-136.14322,-204.64845,0.93792933,-0.9199364,61.0189,975000
|
| 57 |
+
0.17486563,21.428465,-12.61659,-143.46599,-204.25641,0.7541981,-0.8130538,62.658463,980000
|
| 58 |
+
0.17311868,24.954899,-6.0486,-137.51753,-204.56795,2.0219226,-1.0836605,103.508835,985000
|
| 59 |
+
0.17359114,18.066359,-10.711103,-133.62839,-203.77573,0.6749983,-0.5888466,54.835648,990000
|
| 60 |
+
0.18656671,19.390974,2.4258356,-135.39348,-205.22314,1.2218055,-1.5900109,55.49781,995000
|
| 61 |
+
0.1376231,13.009799,-1.5908175,-141.01302,-203.74765,0.5061458,-0.49616,40.286148,1000000
|
| 62 |
+
0.15174216,16.03082,-0.23986924,-137.00041,-203.86354,0.53993905,-1.1139041,59.22635,1005000
|
| 63 |
+
0.15084042,20.832264,-10.402132,-137.75566,-203.99422,1.7176234,-2.5455768,71.32066,1010000
|
| 64 |
+
0.1609165,16.465961,-6.9022927,-138.36234,-200.60849,0.93598956,-1.060102,60.994537,1015000
|
| 65 |
+
0.17946774,18.434582,-7.4991083,-135.81992,-201.59462,4.601385,-6.3677797,79.77505,1020000
|
| 66 |
+
0.19101697,16.154438,-5.0584846,-135.63188,-204.23737,1.6076388,-1.255946,70.38031,1025000
|
| 67 |
+
0.17135344,14.473366,3.5487704,-131.30627,-202.9273,1.3931215,-1.3210803,67.372826,1030000
|
| 68 |
+
0.17957938,17.924452,-5.30966,-137.52774,-205.15005,1.0588845,-0.97426564,65.08549,1035000
|
| 69 |
+
0.13770124,22.75214,-6.269922,-135.58272,-201.71138,1.1813507,-1.164555,71.7661,1040000
|
| 70 |
+
0.16653088,18.601297,2.4769402,-138.05806,-203.7631,0.8347115,-0.8559644,45.8627,1045000
|
| 71 |
+
0.17603779,19.455729,-12.351328,-127.71665,-204.86592,1.5396764,-1.5866649,52.043922,1050000
|
| 72 |
+
0.1520341,16.035559,-0.2820369,-135.25502,-204.20226,0.37848112,-0.40676644,39.35192,1055000
|
| 73 |
+
0.15511131,17.214489,-7.072416,-128.73262,-203.12605,2.1973903,-2.278127,66.01126,1060000
|
| 74 |
+
0.1769526,20.005325,-4.9426413,-136.61531,-205.62839,1.001062,-1.0397378,52.61699,1065000
|
| 75 |
+
0.16829047,14.805877,-3.2840812,-132.69061,-204.67679,0.8839877,-1.0027158,52.7827,1070000
|
| 76 |
+
0.16761425,15.661283,0.8193064,-132.56075,-204.73811,0.97390914,-1.690342,73.85674,1075000
|
| 77 |
+
0.17950681,18.83237,-6.9636626,-129.85716,-203.8824,2.6582687,-2.5578651,96.07347,1080000
|
| 78 |
+
0.14890297,18.657969,-4.486946,-133.99518,-204.16713,3.1826437,-3.6467426,105.448845,1085000
|
| 79 |
+
0.14781153,9.952979,-3.4108796,-135.19917,-203.27544,1.2524195,-1.1031663,42.179474,1090000
|
| 80 |
+
0.16825753,13.2256,0.5445114,-136.08138,-202.20879,1.1650411,-1.1647372,53.01453,1095000
|
| 81 |
+
0.1746628,15.710253,-4.9507337,-129.60799,-201.31873,1.0669502,-1.383244,59.031384,1100000
|
| 82 |
+
0.17454931,23.333387,0.66113544,-129.49904,-203.58145,1.1174343,-1.444205,68.71501,1105000
|
| 83 |
+
0.15460825,13.963043,-2.7687318,-135.45589,-201.51126,1.0187758,-0.97713166,47.047318,1110000
|
| 84 |
+
0.13320522,16.454123,-5.492003,-131.75542,-201.19115,0.5887687,-0.53543,41.271576,1115000
|
| 85 |
+
0.1655376,18.39648,-6.2188306,-134.20903,-204.27275,2.752608,-3.1231108,81.09111,1120000
|
| 86 |
+
0.19418845,19.967361,-0.34512067,-127.76428,-202.57652,12.186039,-10.839854,133.10553,1125000
|
| 87 |
+
0.14383505,33.643932,-8.07464,-127.84377,-202.4325,0.7431778,-0.98547286,58.08418,1130000
|
| 88 |
+
0.18386824,52.15211,-7.64565,-134.10083,-202.21684,1.8247362,-2.671495,101.54436,1135000
|
| 89 |
+
0.18760964,10.266864,-7.079901,-128.1521,-203.11722,1.4371517,-1.604984,48.316216,1140000
|
| 90 |
+
0.18143953,17.052597,-1.7461523,-131.32925,-202.11707,1.5930297,-1.4605196,83.96467,1145000
|
| 91 |
+
0.1509063,16.1646,0.11879122,-124.659645,-203.61932,1.4908592,-1.6148129,55.073868,1150000
|
| 92 |
+
0.17767088,21.214434,-6.9521227,-129.57259,-202.64516,0.7884594,-0.7969991,63.819954,1155000
|
| 93 |
+
0.1828727,19.876434,-4.093593,-128.91304,-201.36472,1.0249575,-0.5186011,52.534027,1160000
|
| 94 |
+
0.18906222,15.730594,-2.5641298,-129.5355,-203.60712,1.9351608,-5.292023,89.8143,1165000
|
| 95 |
+
0.13283783,15.937555,2.3151226,-127.42759,-202.6,5.970777,-6.058083,70.29212,1170000
|
| 96 |
+
0.15198585,19.152098,2.0313847,-128.45634,-203.4021,0.5275691,-0.46722838,39.429787,1175000
|
| 97 |
+
0.19559145,11.624591,0.43371844,-128.80309,-204.01424,2.518207,-1.6087058,62.528427,1180000
|
| 98 |
+
0.15267943,20.972244,4.0416026,-125.27628,-201.41339,0.9634304,-1.0245848,59.47374,1185000
|
| 99 |
+
0.16311596,16.243824,-7.684948,-130.69563,-203.72383,1.0877684,-0.65248144,57.727074,1190000
|
| 100 |
+
0.14355747,13.703717,5.48487,-120.58231,-203.50868,4.134886,-4.55221,103.99316,1195000
|
| 101 |
+
0.14957392,11.183851,-2.136448,-123.97534,-202.72292,1.3041357,-1.2399548,45.982445,1200000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/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 |
+
0.19734979,12.158076,-82.89527,-179.59836,-202.96623,0.278031,-0.28499767,25.035858,705000
|
| 3 |
+
0.1852695,11.618044,-66.675415,-175.34917,-202.97342,0.51197845,-0.4128598,35.898773,710000
|
| 4 |
+
0.18313277,11.644752,-57.274075,-174.17952,-202.67297,0.40690404,-0.39859676,33.72863,715000
|
| 5 |
+
0.17939295,24.8678,-58.616425,-171.00713,-203.2286,0.54949427,-0.3510325,49.306488,720000
|
| 6 |
+
0.16664076,14.367284,-64.67236,-171.56033,-203.43886,0.3044897,-0.4059464,37.278584,725000
|
| 7 |
+
0.17932072,12.902194,-74.28653,-171.6,-203.60844,0.9426574,-1.3317713,33.415688,730000
|
| 8 |
+
0.17362824,20.91267,-70.79747,-170.0105,-203.65671,0.7493851,-0.39160642,55.651237,735000
|
| 9 |
+
0.16412419,15.196652,-15.869219,-168.98079,-203.34488,1.7530789,-1.5437537,62.40531,740000
|
| 10 |
+
0.15811485,18.349861,-49.493793,-168.71954,-204.76578,0.60354334,-0.41941392,39.97914,745000
|
| 11 |
+
0.15477172,19.195707,-61.856533,-169.67902,-202.88521,0.9101194,-0.9771488,60.708946,750000
|
| 12 |
+
0.18666527,18.34709,-46.065063,-166.51929,-204.34549,0.50597245,-0.9651483,41.05211,755000
|
| 13 |
+
0.21959934,19.165289,-46.33205,-165.65994,-203.91354,0.6652424,-0.66404325,51.135223,760000
|
| 14 |
+
0.18746266,10.738433,-53.204456,-165.84476,-204.72414,0.64642024,-0.6095129,34.91669,765000
|
| 15 |
+
0.1894221,18.936403,-31.931658,-161.55591,-204.10118,2.097733,-2.265086,69.34618,770000
|
| 16 |
+
0.19033939,14.603607,-20.103714,-164.4762,-203.81183,0.87403023,-0.914203,46.71957,775000
|
| 17 |
+
0.17221588,23.689674,-14.781785,-164.75716,-203.8404,1.0618999,-1.0379771,45.220966,780000
|
| 18 |
+
0.19100416,21.99935,-6.7875185,-162.55876,-204.59833,0.58770907,-0.62456614,42.182064,785000
|
| 19 |
+
0.1934581,11.412819,-38.923985,-159.38937,-204.71434,0.44393533,-0.40238634,37.753845,790000
|
| 20 |
+
0.16224545,16.958462,-64.84124,-162.5749,-203.78778,0.74775106,-0.6932399,36.907867,795000
|
| 21 |
+
0.19623686,15.936576,-32.822094,-154.84354,-203.92636,1.6369544,-1.7699838,55.360718,800000
|
| 22 |
+
0.19743186,16.263968,-2.6504254,-158.47456,-204.03447,0.55890286,-0.36080492,39.62986,805000
|
| 23 |
+
0.17753986,25.930155,-18.512241,-156.22935,-203.91864,2.2388258,-2.7272708,85.78496,810000
|
| 24 |
+
0.18831806,17.362043,2.1293378,-152.54225,-203.96184,0.80720615,-0.94299006,58.142868,815000
|
| 25 |
+
0.1686388,20.312597,-2.296115,-155.22476,-203.30089,0.895463,-0.6531258,50.42764,820000
|
| 26 |
+
0.17810011,13.941251,-32.70702,-157.86278,-204.34656,0.3026883,-0.6852456,39.567955,825000
|
| 27 |
+
0.17763877,18.608892,-8.233587,-151.74117,-203.66884,0.6441805,-0.65345937,43.234375,830000
|
| 28 |
+
0.18384439,18.758818,2.5820441,-152.93706,-203.67894,0.5354126,-0.5106289,45.426056,835000
|
| 29 |
+
0.19278386,13.458667,-16.083511,-148.51445,-203.11081,1.3597246,-1.3707712,55.73405,840000
|
| 30 |
+
0.17248333,18.67421,-23.11421,-150.3443,-204.50337,0.98392254,-0.7614136,53.390423,845000
|
| 31 |
+
0.16403292,12.271911,-29.25567,-150.76163,-203.92276,0.5310791,-0.75392354,46.145267,850000
|
| 32 |
+
0.17459702,11.215972,-18.909088,-148.28172,-204.19917,2.6438384,-3.208866,77.40133,855000
|
| 33 |
+
0.18862906,23.254002,-6.561493,-150.2967,-204.44604,0.9530208,-1.5024422,67.0871,860000
|
| 34 |
+
0.17338906,13.765922,-0.07669397,-146.81943,-204.67154,0.45399266,-0.62716275,39.683502,865000
|
| 35 |
+
0.15905102,11.90585,-19.941618,-146.671,-204.53606,0.35442072,-0.38836238,36.658005,870000
|
| 36 |
+
0.18034741,22.783735,-14.198748,-149.3115,-205.72087,1.6740335,-1.4452091,65.10074,875000
|
| 37 |
+
0.18252783,13.008597,6.1564503,-147.2941,-203.43137,0.5988279,-0.7647277,53.987865,880000
|
| 38 |
+
0.1435834,17.460016,-8.057041,-144.58015,-204.33107,0.8543537,-1.0138888,55.814655,885000
|
| 39 |
+
0.17323996,16.30998,0.21934459,-142.44115,-203.1333,1.4539183,-1.8899843,60.423645,890000
|
| 40 |
+
0.15936488,18.683731,-5.604309,-141.43024,-205.2219,2.995109,-2.8591518,86.52049,895000
|
| 41 |
+
0.18954258,23.678373,-2.455367,-143.84195,-205.1903,1.3857644,-1.844979,79.01305,900000
|
| 42 |
+
0.18609118,17.199371,-1.8540422,-144.55446,-205.44958,1.3399328,-1.292887,51.6789,905000
|
| 43 |
+
0.1720098,18.902761,-3.7006242,-142.85623,-203.88338,0.52744985,-0.84586924,51.641003,910000
|
| 44 |
+
0.19384916,15.637293,-8.115197,-144.74223,-204.33583,0.6774129,-0.45576695,50.80797,915000
|
| 45 |
+
0.1788258,18.482878,-2.607226,-141.59375,-202.10895,0.5757939,-1.109723,52.83832,920000
|
| 46 |
+
0.17075652,19.74214,-1.1827828,-137.19777,-203.99048,0.9248617,-0.90003884,54.647224,925000
|
| 47 |
+
0.1838356,16.588224,-6.0791593,-140.03738,-204.8663,1.0801271,-0.97956526,64.20477,930000
|
| 48 |
+
0.19859543,11.767452,-3.147247,-137.52518,-203.18652,1.7149197,-1.6453171,57.57158,935000
|
| 49 |
+
0.21849173,16.195755,2.7960036,-139.67313,-203.47176,2.0241451,-2.4792135,66.88157,940000
|
| 50 |
+
0.18707311,14.920328,2.171465,-141.33028,-206.32945,1.6812749,-2.788498,62.44541,945000
|
| 51 |
+
0.18903717,22.202253,-9.046592,-131.62624,-203.23895,1.1225345,-2.0350575,71.93042,950000
|
| 52 |
+
0.17658487,14.780423,-6.775141,-142.946,-202.85603,2.1114259,-2.2847726,82.52771,955000
|
| 53 |
+
0.1658981,21.725815,4.49814,-138.65727,-203.776,2.712473,-3.0881028,94.3233,960000
|
| 54 |
+
0.18304056,26.055769,-23.18895,-144.58426,-203.97043,2.8877423,-3.1500926,80.53017,965000
|
| 55 |
+
0.18478402,16.602009,-11.756989,-139.01978,-201.0606,1.0263479,-1.4818804,87.75327,970000
|
| 56 |
+
0.17073059,19.906624,-13.872733,-136.14322,-204.64845,0.93792933,-0.9199364,61.0189,975000
|
| 57 |
+
0.17486563,21.428465,-12.61659,-143.46599,-204.25641,0.7541981,-0.8130538,62.658463,980000
|
| 58 |
+
0.17311868,24.954899,-6.0486,-137.51753,-204.56795,2.0219226,-1.0836605,103.508835,985000
|
| 59 |
+
0.17359114,18.066359,-10.711103,-133.62839,-203.77573,0.6749983,-0.5888466,54.835648,990000
|
| 60 |
+
0.18656671,19.390974,2.4258356,-135.39348,-205.22314,1.2218055,-1.5900109,55.49781,995000
|
| 61 |
+
0.1376231,13.009799,-1.5908175,-141.01302,-203.74765,0.5061458,-0.49616,40.286148,1000000
|
| 62 |
+
0.15174216,16.03082,-0.23986924,-137.00041,-203.86354,0.53993905,-1.1139041,59.22635,1005000
|
| 63 |
+
0.15084042,20.832264,-10.402132,-137.75566,-203.99422,1.7176234,-2.5455768,71.32066,1010000
|
| 64 |
+
0.1609165,16.465961,-6.9022927,-138.36234,-200.60849,0.93598956,-1.060102,60.994537,1015000
|
| 65 |
+
0.17946774,18.434582,-7.4991083,-135.81992,-201.59462,4.601385,-6.3677797,79.77505,1020000
|
| 66 |
+
0.19101697,16.154438,-5.0584846,-135.63188,-204.23737,1.6076388,-1.255946,70.38031,1025000
|
| 67 |
+
0.17135344,14.473366,3.5487704,-131.30627,-202.9273,1.3931215,-1.3210803,67.372826,1030000
|
| 68 |
+
0.17957938,17.924452,-5.30966,-137.52774,-205.15005,1.0588845,-0.97426564,65.08549,1035000
|
| 69 |
+
0.13770124,22.75214,-6.269922,-135.58272,-201.71138,1.1813507,-1.164555,71.7661,1040000
|
| 70 |
+
0.16653088,18.601297,2.4769402,-138.05806,-203.7631,0.8347115,-0.8559644,45.8627,1045000
|
| 71 |
+
0.17603779,19.455729,-12.351328,-127.71665,-204.86592,1.5396764,-1.5866649,52.043922,1050000
|
| 72 |
+
0.1520341,16.035559,-0.2820369,-135.25502,-204.20226,0.37848112,-0.40676644,39.35192,1055000
|
| 73 |
+
0.15511131,17.214489,-7.072416,-128.73262,-203.12605,2.1973903,-2.278127,66.01126,1060000
|
| 74 |
+
0.1769526,20.005325,-4.9426413,-136.61531,-205.62839,1.001062,-1.0397378,52.61699,1065000
|
| 75 |
+
0.16829047,14.805877,-3.2840812,-132.69061,-204.67679,0.8839877,-1.0027158,52.7827,1070000
|
| 76 |
+
0.16761425,15.661283,0.8193064,-132.56075,-204.73811,0.97390914,-1.690342,73.85674,1075000
|
| 77 |
+
0.17950681,18.83237,-6.9636626,-129.85716,-203.8824,2.6582687,-2.5578651,96.07347,1080000
|
| 78 |
+
0.14890297,18.657969,-4.486946,-133.99518,-204.16713,3.1826437,-3.6467426,105.448845,1085000
|
| 79 |
+
0.14781153,9.952979,-3.4108796,-135.19917,-203.27544,1.2524195,-1.1031663,42.179474,1090000
|
| 80 |
+
0.16825753,13.2256,0.5445114,-136.08138,-202.20879,1.1650411,-1.1647372,53.01453,1095000
|
| 81 |
+
0.1746628,15.710253,-4.9507337,-129.60799,-201.31873,1.0669502,-1.383244,59.031384,1100000
|
| 82 |
+
0.17454931,23.333387,0.66113544,-129.49904,-203.58145,1.1174343,-1.444205,68.71501,1105000
|
| 83 |
+
0.15460825,13.963043,-2.7687318,-135.45589,-201.51126,1.0187758,-0.97713166,47.047318,1110000
|
| 84 |
+
0.13320522,16.454123,-5.492003,-131.75542,-201.19115,0.5887687,-0.53543,41.271576,1115000
|
| 85 |
+
0.1655376,18.39648,-6.2188306,-134.20903,-204.27275,2.752608,-3.1231108,81.09111,1120000
|
| 86 |
+
0.19418845,19.967361,-0.34512067,-127.76428,-202.57652,12.186039,-10.839854,133.10553,1125000
|
| 87 |
+
0.14383505,33.643932,-8.07464,-127.84377,-202.4325,0.7431778,-0.98547286,58.08418,1130000
|
| 88 |
+
0.18386824,52.15211,-7.64565,-134.10083,-202.21684,1.8247362,-2.671495,101.54436,1135000
|
| 89 |
+
0.18760964,10.266864,-7.079901,-128.1521,-203.11722,1.4371517,-1.604984,48.316216,1140000
|
| 90 |
+
0.18143953,17.052597,-1.7461523,-131.32925,-202.11707,1.5930297,-1.4605196,83.96467,1145000
|
| 91 |
+
0.1509063,16.1646,0.11879122,-124.659645,-203.61932,1.4908592,-1.6148129,55.073868,1150000
|
| 92 |
+
0.17767088,21.214434,-6.9521227,-129.57259,-202.64516,0.7884594,-0.7969991,63.819954,1155000
|
| 93 |
+
0.1828727,19.876434,-4.093593,-128.91304,-201.36472,1.0249575,-0.5186011,52.534027,1160000
|
| 94 |
+
0.18906222,15.730594,-2.5641298,-129.5355,-203.60712,1.9351608,-5.292023,89.8143,1165000
|
| 95 |
+
0.13283783,15.937555,2.3151226,-127.42759,-202.6,5.970777,-6.058083,70.29212,1170000
|
| 96 |
+
0.15198585,19.152098,2.0313847,-128.45634,-203.4021,0.5275691,-0.46722838,39.429787,1175000
|
| 97 |
+
0.19559145,11.624591,0.43371844,-128.80309,-204.01424,2.518207,-1.6087058,62.528427,1180000
|
| 98 |
+
0.15267943,20.972244,4.0416026,-125.27628,-201.41339,0.9634304,-1.0245848,59.47374,1185000
|
| 99 |
+
0.16311596,16.243824,-7.684948,-130.69563,-203.72383,1.0877684,-0.65248144,57.727074,1190000
|
| 100 |
+
0.14355747,13.703717,5.48487,-120.58231,-203.50868,4.134886,-4.55221,103.99316,1195000
|
| 101 |
+
0.14957392,11.183851,-2.136448,-123.97534,-202.72292,1.3041357,-1.2399548,45.982445,1200000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_1000000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc444e69d3a0d3c370aefca49e7deab3769da07b8ea36cc961444c883d42a58c
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_1050000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0fe5383974f2f1b10f2bc79fa4cffbdea8f014a56b193557177bdf771e8396e
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_1100000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca74be5f146e916ebf961690ecd147ed5dae2f10ed03c1de3fa914d1e3a35b33
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_1150000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd6b754aff9f08628f58d66a124205e7c63121458553bb9ad96b0e6012c891c8
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_1200000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:362cc82d1e19a17d60c73bbbd9ecfe0d5daf392aad13b2cf184ffca86486d67d
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_750000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1cf1272ef8168f471bb7461c6767bb66a93d1792a2e5ae6cc1825e98b7209b7
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_800000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:604b92deb25d2bccdbe77fcd2b93ac789e18f2d98fc05aa9f4dc7fe2e4b5ace8
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_850000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:362649aef89da8c16685744849e7bfd6f9c0acd970b0cab53f360657869d0d59
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_900000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6278369959870ee04dd8f8c366e5c3417c31cb03493456c54c415512f75a17e8
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/params_950000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:979540e0a58b20c584097ad61b2e27e474919fd675107fc2c5fb958c02703d1f
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_231719/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/0gtuwm64
|