Tiredsheep commited on
Commit
13b12a8
·
verified ·
1 Parent(s): 3570e68

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/env.csv +0 -0
  2. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/env_sv.csv +0 -0
  3. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/eval.csv +11 -0
  4. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/eval_sv.csv +11 -0
  5. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/online_agent.csv +101 -0
  6. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/online_agent_sv.csv +101 -0
  7. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_1000000.pkl +3 -0
  8. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_1050000.pkl +3 -0
  9. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_1100000.pkl +3 -0
  10. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_1150000.pkl +3 -0
  11. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_1200000.pkl +3 -0
  12. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_750000.pkl +3 -0
  13. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_800000.pkl +3 -0
  14. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_850000.pkl +3 -0
  15. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_900000.pkl +3 -0
  16. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_950000.pkl +3 -0
  17. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/progress.tk +1 -0
  18. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/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/fql/20260319_042005/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/fql/20260319_042005/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,-0.004882098896260248,-0.005528406076571861,-0.0049823607232727,-0.004383469691917239,35.02083178128393,11.133999999999688,0.94,5805.02,-0.1,-314.36,220.68,0.9816713523864746,750000
3
+ 0.0,0.0,-0.027874189308911678,0.006648363410476426,-0.02748231344618688,0.005155436080273987,35.11975938772481,8.30999999999959,0.98,15683.72,-0.02,-235.16,164.2,0.7481156587600708,800000
4
+ 0.0,0.0,-0.04080858751058136,-0.00876325785015429,-0.04114663761472107,-0.008380085005582663,35.30216814693548,8.027999999999691,1.0,23839.12,0.0,-220.64,158.56,0.6998658847808837,850000
5
+ 0.0,0.0,-0.03248990832652773,-0.003815350444479703,-0.03253281317043858,-0.005824547127093108,35.178484168489675,6.669999999999577,1.0,31471.66,0.0,-180.18,131.4,0.612697401046753,900000
6
+ 0.0,0.0,-0.030666900387986695,0.016946232052092898,-0.030129353377400542,0.0067829752646814505,35.6040803710672,5.952999999999579,1.0,37939.24,0.0,-160.04,117.06,0.501396541595459,950000
7
+ 0.0,0.0,-0.04596053125410605,0.028809261249851933,-0.04427654056143076,0.023053813989674557,35.71326331839106,5.5519999999996195,1.0,43809.44,0.0,-148.34,109.04,0.4688024854660034,1000000
8
+ 0.0,0.0,-0.05422195939474866,0.031494602083330915,-0.05236401455605379,0.014525740252197663,35.708668420628655,6.401999999999671,0.98,49752.32,-0.02,-169.78,126.04,0.5667866086959839,1050000
9
+ 0.0,0.0,-0.050854398553464,0.04598848582881174,-0.048659580832044955,0.03869568372476293,35.759158015156295,5.784999999999709,1.0,56101.74,0.0,-163.34,113.7,0.5067185020446777,1100000
10
+ 0.0,0.0,-0.04848722178642217,0.06670306756250363,-0.045824693761980666,0.04630188521996996,35.77387695094843,4.935999999999678,1.0,61592.3,0.0,-131.62,96.72,0.44848653316497805,1150000
11
+ 0.0,0.0,-0.05799140475281896,0.07045919947774752,-0.054488109248965404,0.06331869588571747,35.78383099949881,5.150999999999665,1.0,66746.12,0.0,-141.62,101.02,0.4531517839431763,1200000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/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,-0.004882098896260248,-0.005528406076571861,-0.0049823607232727,-0.004383469691917239,35.02083178128393,11.133999999999688,0.94,5805.02,-0.1,-314.36,220.68,0.9816713523864746,750000
3
+ 0.0,0.0,-0.027874189308911678,0.006648363410476426,-0.02748231344618688,0.005155436080273987,35.11975938772481,8.30999999999959,0.98,15683.72,-0.02,-235.16,164.2,0.7481156587600708,800000
4
+ 0.0,0.0,-0.04080858751058136,-0.00876325785015429,-0.04114663761472107,-0.008380085005582663,35.30216814693548,8.027999999999691,1.0,23839.12,0.0,-220.64,158.56,0.6998658847808837,850000
5
+ 0.0,0.0,-0.03248990832652773,-0.003815350444479703,-0.03253281317043858,-0.005824547127093108,35.178484168489675,6.669999999999577,1.0,31471.66,0.0,-180.18,131.4,0.612697401046753,900000
6
+ 0.0,0.0,-0.030666900387986695,0.016946232052092898,-0.030129353377400542,0.0067829752646814505,35.6040803710672,5.952999999999579,1.0,37939.24,0.0,-160.04,117.06,0.501396541595459,950000
7
+ 0.0,0.0,-0.04596053125410605,0.028809261249851933,-0.04427654056143076,0.023053813989674557,35.71326331839106,5.5519999999996195,1.0,43809.44,0.0,-148.34,109.04,0.4688024854660034,1000000
8
+ 0.0,0.0,-0.05422195939474866,0.031494602083330915,-0.05236401455605379,0.014525740252197663,35.708668420628655,6.401999999999671,0.98,49752.32,-0.02,-169.78,126.04,0.5667866086959839,1050000
9
+ 0.0,0.0,-0.050854398553464,0.04598848582881174,-0.048659580832044955,0.03869568372476293,35.759158015156295,5.784999999999709,1.0,56101.74,0.0,-163.34,113.7,0.5067185020446777,1100000
10
+ 0.0,0.0,-0.04848722178642217,0.06670306756250363,-0.045824693761980666,0.04630188521996996,35.77387695094843,4.935999999999678,1.0,61592.3,0.0,-131.62,96.72,0.44848653316497805,1150000
11
+ 0.0,0.0,-0.05799140475281896,0.07045919947774752,-0.054488109248965404,0.06331869588571747,35.78383099949881,5.150999999999665,1.0,66746.12,0.0,-141.62,101.02,0.4531517839431763,1200000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/online_agent.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,actor/bc_flow_loss,actor/distill_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 164.46767,0.19750284,0.007848839,3.702964,-46.72951,-164.78995,-203.79692,1.00816,-0.97249997,45.422787,705000
3
+ 161.06966,0.186201,0.006464591,5.0034575,-54.52866,-161.02351,-203.44492,1.378935,-1.6115404,61.10961,710000
4
+ 160.61992,0.18170998,0.0069390927,4.200953,-51.891624,-160.89656,-204.70007,0.91480106,-0.9219294,48.422134,715000
5
+ 158.4268,0.17832083,0.0071834773,5.4078217,-38.868584,-159.01787,-204.28134,0.9060328,-0.93530566,62.383537,720000
6
+ 155.94414,0.16764194,0.008502991,6.859752,-51.729805,-155.69774,-204.91882,2.1800327,-2.6309032,98.35358,725000
7
+ 152.25934,0.17897505,0.0069819284,6.87779,-51.693325,-152.7924,-203.83134,0.99955404,-1.2529114,65.25076,730000
8
+ 151.32483,0.17195082,0.009388868,7.818526,-43.915226,-151.8146,-204.17696,1.6466272,-1.6906303,70.4741,735000
9
+ 153.00163,0.16501552,0.011550352,6.902963,-43.271397,-153.22798,-205.01889,1.6515753,-1.7354158,90.91683,740000
10
+ 153.13095,0.16220616,0.007835762,7.089699,-56.824455,-153.28601,-204.97649,0.7533942,-1.2428764,59.0097,745000
11
+ 150.72142,0.1580747,0.009430587,9.286769,-25.584576,-151.00317,-204.62013,0.7684355,-0.75678647,70.1933,750000
12
+ 143.98886,0.18782127,0.007514107,8.819175,-36.245865,-144.34483,-204.37769,1.7062224,-0.98327065,60.671425,755000
13
+ 142.8925,0.2160869,0.009091468,8.186172,-3.2123108,-143.24596,-205.6944,1.8084899,-2.0803275,72.04745,760000
14
+ 142.66206,0.18826956,0.0066946554,5.841409,-24.559654,-143.15442,-204.30574,1.0815414,-1.9178455,62.042267,765000
15
+ 138.45448,0.18659793,0.007819948,6.7250924,-24.37523,-138.8398,-205.41801,0.75258374,-0.7470975,75.26626,770000
16
+ 142.1774,0.18959774,0.00971917,9.764687,-19.596554,-142.83838,-205.91153,1.7930188,-1.7751842,86.39441,775000
17
+ 144.91734,0.17339762,0.01063462,7.3269396,-15.455487,-144.94324,-205.06523,0.8359695,-1.4796692,72.71236,780000
18
+ 141.44415,0.19058642,0.0073161838,6.116914,-7.5757384,-141.39749,-204.19028,1.0902071,-1.2464408,72.84818,785000
19
+ 139.39813,0.19336446,0.008763104,6.8792796,-3.9558299,-139.82872,-205.70798,0.7940436,-0.59193134,60.049713,790000
20
+ 138.27592,0.16303617,0.00904776,7.386917,-3.9776812,-138.86438,-205.17441,1.4148654,-1.3379786,76.6575,795000
21
+ 133.26944,0.19405851,0.008278025,6.4142413,-12.282207,-133.60478,-205.06303,1.0394033,-0.987326,68.894325,800000
22
+ 138.15935,0.19729708,0.009311272,4.997583,-2.2462704,-138.90393,-205.46422,1.3941367,-1.8280864,63.377945,805000
23
+ 135.24388,0.1748997,0.008092487,6.77548,-16.851273,-135.83379,-205.4722,1.0530279,-0.97531104,79.9117,810000
24
+ 130.85068,0.1890715,0.010581822,10.665431,1.0687656,-131.40923,-205.56908,0.9875339,-1.0222018,70.02703,815000
25
+ 133.19719,0.16667563,0.0074774018,4.718349,-12.799075,-133.50528,-204.84631,0.7383493,-0.8237966,48.01096,820000
26
+ 136.9514,0.17887272,0.008515681,8.272271,-13.706109,-136.96695,-205.37225,3.176972,-3.604363,103.106026,825000
27
+ 134.74242,0.17781034,0.007983804,5.5714197,-18.271536,-135.53264,-204.36818,1.3767879,-1.3076116,84.37468,830000
28
+ 133.08495,0.18314897,0.009273208,7.136295,1.2803917,-134.56242,-206.06512,1.9803966,-2.1189973,73.12325,835000
29
+ 127.48154,0.18837348,0.010188282,7.2412715,-2.059922,-128.83345,-205.35954,1.1275405,-1.1221768,67.32153,840000
30
+ 131.61845,0.17020223,0.008226026,5.112383,-2.4723213,-132.30916,-206.15677,1.2811444,-1.3183589,56.10105,845000
31
+ 131.45421,0.15858783,0.007684029,4.9037833,0.06328325,-132.25801,-204.61055,1.5718124,-1.4478722,55.754414,850000
32
+ 129.26068,0.17187089,0.007780165,7.6377854,-4.6601667,-130.3586,-204.72614,0.853925,-0.99287796,69.13497,855000
33
+ 132.4772,0.18786329,0.0072823083,6.454489,-2.5873063,-133.15625,-204.92267,0.881243,-1.3038439,52.280186,860000
34
+ 128.15178,0.17379457,0.009308132,5.1445646,-0.90021455,-128.72388,-204.65857,1.037845,-1.1370687,54.09508,865000
35
+ 130.78076,0.16245314,0.00795669,5.8292675,-3.0805311,-131.0305,-205.4424,0.6626429,-0.6516529,73.03783,870000
36
+ 132.05507,0.18287072,0.008328643,6.335674,-7.122273,-132.10321,-205.81871,1.2903217,-1.2582817,68.3503,875000
37
+ 132.5723,0.18071008,0.008192819,11.445406,2.224225,-132.39616,-204.89717,0.6834783,-0.8497388,77.06786,880000
38
+ 127.68432,0.13913232,0.007941361,5.7487226,-4.676732,-128.15356,-205.69377,0.582042,-0.5212905,58.002266,885000
39
+ 125.12814,0.1745165,0.008398682,7.384332,-3.1122284,-126.10506,-205.11397,0.7426407,-0.7589073,63.128185,890000
40
+ 126.3462,0.15910837,0.008070624,6.1322913,-2.7192311,-126.92639,-203.97842,0.70035243,-0.5844671,55.682972,895000
41
+ 125.97045,0.185188,0.008118796,6.78069,1.380229,-127.07835,-205.15009,1.7698011,-1.3827764,65.030594,900000
42
+ 126.54714,0.1858087,0.008116424,4.5015335,1.4608111,-126.99099,-205.1959,1.344293,-1.1797527,47.20058,905000
43
+ 124.87779,0.16790533,0.009358228,6.8395257,-7.5106087,-125.211586,-205.13759,1.2333634,-1.9762592,63.985714,910000
44
+ 126.526794,0.19480062,0.008811769,6.065003,-0.08480689,-127.02647,-204.67746,1.6295142,-1.951397,73.31648,915000
45
+ 125.73273,0.180256,0.007617006,6.555875,-0.20458789,-126.096695,-205.11769,1.581487,-0.9342154,69.00429,920000
46
+ 119.78861,0.1727244,0.006765791,5.1650395,-9.959052,-120.04915,-203.60902,0.794416,-0.7623451,61.768303,925000
47
+ 125.765274,0.18008809,0.008382903,5.0934687,-0.71044457,-126.17224,-204.08899,0.8405822,-0.8655844,55.46598,930000
48
+ 121.66758,0.20216827,0.0070189023,4.737472,-2.651074,-121.80963,-204.40096,0.9126118,-0.83679795,46.102306,935000
49
+ 119.773834,0.219196,0.00615167,5.153209,1.3287672,-120.459816,-204.258,0.93358177,-0.8331305,56.69139,940000
50
+ 124.022835,0.18707362,0.009377404,7.0360904,-7.0238147,-124.561844,-206.19589,1.2252339,-0.919848,73.89371,945000
51
+ 113.75993,0.19112816,0.008057775,6.7320724,1.9612464,-114.54598,-205.5836,1.9314951,-1.703124,74.55836,950000
52
+ 123.82799,0.17798671,0.0076639554,5.620212,1.6291203,-124.811966,-204.40128,0.6279033,-0.5546749,52.48468,955000
53
+ 120.342545,0.16124555,0.008284608,8.373077,3.2110808,-121.459404,-205.89444,4.172345,-4.111476,147.22633,960000
54
+ 120.25611,0.18452601,0.009120566,5.82998,-5.4214945,-120.5426,-204.4184,2.4523242,-2.1654248,58.472443,965000
55
+ 119.92786,0.17740333,0.0082613565,5.7817297,-4.059332,-120.48733,-203.88084,1.6762794,-2.187871,57.63932,970000
56
+ 118.521736,0.1682422,0.008388954,10.422676,-2.2523232,-118.92224,-205.81229,2.50652,-2.5114205,139.79198,975000
57
+ 122.19589,0.17688103,0.009443209,5.373117,-3.2205245,-122.784645,-205.27272,1.7157899,-1.3797596,69.092834,980000
58
+ 116.87861,0.166918,0.009557361,3.914416,-2.3164752,-117.17098,-203.3465,0.9879238,-0.8555012,67.4073,985000
59
+ 111.88613,0.17116016,0.00826056,6.490758,-0.19741878,-112.73495,-203.79552,1.4187975,-1.2903366,60.526062,990000
60
+ 115.81669,0.1865702,0.0072950404,4.5488825,2.918242,-116.57983,-205.94296,1.0751731,-1.0089108,48.18328,995000
61
+ 118.21511,0.14058462,0.008302457,7.1303873,-4.164439,-118.397865,-204.21469,0.96237195,-1.0755332,77.32739,1000000
62
+ 119.37607,0.15852353,0.007465651,4.154873,-6.135511,-120.975,-205.8851,1.1319185,-1.1179802,68.38727,1005000
63
+ 116.33203,0.14804351,0.0071398104,6.217628,1.8925488,-117.188,-207.12515,0.81947106,-0.8609822,65.498474,1010000
64
+ 117.099655,0.15909386,0.0058505354,4.3195586,-1.5294638,-117.71316,-203.89287,1.6253989,-1.6422474,62.781975,1015000
65
+ 116.59919,0.1857456,0.008149042,7.4299827,4.827311,-117.51035,-204.131,0.9137905,-0.9840506,72.87636,1020000
66
+ 118.93263,0.18976444,0.007580802,5.3209243,-3.7455351,-119.73543,-205.32915,1.2175515,-1.1088737,71.596466,1025000
67
+ 115.31658,0.16769129,0.009185464,9.004993,-3.4572268,-115.66498,-204.23024,1.1748593,-1.1287395,73.57542,1030000
68
+ 115.05547,0.1830498,0.009559326,6.5246797,-3.0145032,-115.80682,-204.24348,1.0400212,-0.95938444,77.555084,1035000
69
+ 117.47124,0.12783952,0.006607903,3.3067994,-3.8830802,-117.84185,-203.2193,0.59068316,-0.7456771,44.325714,1040000
70
+ 120.52972,0.16661042,0.0065466617,6.4414186,-0.77659,-121.776794,-204.22748,1.2150116,-1.4081515,76.083405,1045000
71
+ 111.01364,0.17193422,0.0076102656,4.2477593,-5.5701036,-111.73342,-205.36401,1.6146413,-0.7496912,45.908676,1050000
72
+ 116.27297,0.15699697,0.007895902,5.559896,-3.8641467,-116.27123,-202.96947,0.6705674,-0.73124784,64.358475,1055000
73
+ 110.41717,0.15063088,0.007198992,4.399961,0.29383618,-111.20296,-205.49396,1.0160946,-1.1422272,58.653645,1060000
74
+ 116.78329,0.17646995,0.009398053,5.771059,-11.084978,-116.934875,-204.87529,2.0926313,-1.3069043,67.809135,1065000
75
+ 116.381195,0.17090386,0.0072581694,7.0175567,-2.6913314,-117.04717,-204.09244,0.72063446,-0.7980316,63.900887,1070000
76
+ 109.03105,0.16932568,0.008381098,5.2000237,0.7686693,-110.7156,-204.1561,1.2910379,-1.6911734,78.09993,1075000
77
+ 111.03682,0.17429395,0.008261144,4.315414,-1.9757901,-112.08402,-204.028,4.4712577,-4.3825126,92.5847,1080000
78
+ 113.72152,0.16027081,0.0070624826,6.7255754,-1.23669,-114.74163,-204.541,0.9030102,-1.8224462,62.72799,1085000
79
+ 113.48656,0.147243,0.0072327754,7.4502215,-2.3473167,-114.24048,-204.15092,2.7628033,-3.2262943,69.59822,1090000
80
+ 113.02996,0.16348335,0.0075752735,4.296561,0.20527963,-114.01741,-203.75327,0.8191738,-0.81687474,52.517784,1095000
81
+ 108.875694,0.17337298,0.0069814613,5.459606,0.025934428,-109.671265,-202.05257,1.7338418,-2.4568672,88.88837,1100000
82
+ 110.194244,0.17458354,0.0060094954,7.0346346,-0.71756184,-110.40855,-204.54071,1.6771334,-1.5829782,56.23833,1105000
83
+ 117.126976,0.14762518,0.0066159437,5.071898,-6.629565,-117.34214,-201.37357,0.83481526,-0.79793835,48.821014,1110000
84
+ 109.38428,0.13141197,0.0079182,4.7362185,3.1622622,-110.30098,-204.7312,0.49672917,-0.7057499,51.68799,1115000
85
+ 113.20177,0.16154134,0.008009182,5.3806405,-0.6329559,-114.28865,-203.9079,0.65270483,-0.7539405,55.12653,1120000
86
+ 107.423584,0.18083507,0.0071046897,6.31658,1.3632792,-108.66406,-206.38028,0.6506114,-0.9989732,59.597244,1125000
87
+ 108.94887,0.15254831,0.007234061,3.7659535,-4.4714847,-109.59412,-204.79031,0.8184762,-0.839598,51.47072,1130000
88
+ 114.894455,0.17425133,0.00823997,4.4491878,-4.0517664,-114.82198,-205.30176,1.5618898,-1.4971818,63.79975,1135000
89
+ 107.24571,0.18441892,0.0073837745,4.9540305,-2.61219,-107.9397,-205.86565,1.2492225,-1.1140094,65.63453,1140000
90
+ 110.2875,0.18552792,0.007412205,5.2969894,-6.0151424,-111.04419,-203.92178,1.9419625,-1.9797187,58.054787,1145000
91
+ 109.160095,0.1524603,0.0061386772,6.1301045,3.9091403,-110.186035,-204.43546,1.0498697,-0.95681614,58.78545,1150000
92
+ 107.92546,0.16815475,0.006588653,4.374219,2.1844118,-108.4126,-202.11876,0.5453002,-0.54291993,42.96575,1155000
93
+ 105.88848,0.17370361,0.0062000863,7.009952,9.325735,-106.878784,-204.59375,1.4627106,-1.3540566,85.81352,1160000
94
+ 108.55725,0.18158008,0.007982843,5.531221,0.43892246,-108.94927,-205.24721,4.6941485,-5.6852174,86.8138,1165000
95
+ 110.43191,0.12864473,0.00704508,8.701892,1.2470024,-110.82827,-200.92162,1.8462037,-1.8769753,102.740364,1170000
96
+ 106.20629,0.1501727,0.007635716,5.3964667,1.3313936,-106.93245,-204.05396,1.1380854,-1.4165986,55.018845,1175000
97
+ 108.247856,0.18934391,0.008083877,4.752317,16.04313,-108.610596,-203.96892,0.8938473,-0.6838271,63.51959,1180000
98
+ 106.39112,0.1547153,0.0072209197,6.2954683,1.2930094,-107.2485,-204.84842,0.95097435,-1.1735638,70.80474,1185000
99
+ 107.29465,0.15341961,0.0068927286,5.514774,1.415102,-108.32896,-203.79156,0.97347385,-0.87979513,57.290474,1190000
100
+ 101.09695,0.13516659,0.0060413224,4.2358613,0.15006343,-102.7666,-203.74365,0.7372116,-0.7309707,52.721703,1195000
101
+ 100.59953,0.14280409,0.0068115476,4.2021227,-1.5133352,-101.48498,-205.7008,0.80881494,-0.8284002,48.78897,1200000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/online_agent_sv.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,actor/bc_flow_loss,actor/distill_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 164.46767,0.19750284,0.007848839,3.702964,-46.72951,-164.78995,-203.79692,1.00816,-0.97249997,45.422787,705000
3
+ 161.06966,0.186201,0.006464591,5.0034575,-54.52866,-161.02351,-203.44492,1.378935,-1.6115404,61.10961,710000
4
+ 160.61992,0.18170998,0.0069390927,4.200953,-51.891624,-160.89656,-204.70007,0.91480106,-0.9219294,48.422134,715000
5
+ 158.4268,0.17832083,0.0071834773,5.4078217,-38.868584,-159.01787,-204.28134,0.9060328,-0.93530566,62.383537,720000
6
+ 155.94414,0.16764194,0.008502991,6.859752,-51.729805,-155.69774,-204.91882,2.1800327,-2.6309032,98.35358,725000
7
+ 152.25934,0.17897505,0.0069819284,6.87779,-51.693325,-152.7924,-203.83134,0.99955404,-1.2529114,65.25076,730000
8
+ 151.32483,0.17195082,0.009388868,7.818526,-43.915226,-151.8146,-204.17696,1.6466272,-1.6906303,70.4741,735000
9
+ 153.00163,0.16501552,0.011550352,6.902963,-43.271397,-153.22798,-205.01889,1.6515753,-1.7354158,90.91683,740000
10
+ 153.13095,0.16220616,0.007835762,7.089699,-56.824455,-153.28601,-204.97649,0.7533942,-1.2428764,59.0097,745000
11
+ 150.72142,0.1580747,0.009430587,9.286769,-25.584576,-151.00317,-204.62013,0.7684355,-0.75678647,70.1933,750000
12
+ 143.98886,0.18782127,0.007514107,8.819175,-36.245865,-144.34483,-204.37769,1.7062224,-0.98327065,60.671425,755000
13
+ 142.8925,0.2160869,0.009091468,8.186172,-3.2123108,-143.24596,-205.6944,1.8084899,-2.0803275,72.04745,760000
14
+ 142.66206,0.18826956,0.0066946554,5.841409,-24.559654,-143.15442,-204.30574,1.0815414,-1.9178455,62.042267,765000
15
+ 138.45448,0.18659793,0.007819948,6.7250924,-24.37523,-138.8398,-205.41801,0.75258374,-0.7470975,75.26626,770000
16
+ 142.1774,0.18959774,0.00971917,9.764687,-19.596554,-142.83838,-205.91153,1.7930188,-1.7751842,86.39441,775000
17
+ 144.91734,0.17339762,0.01063462,7.3269396,-15.455487,-144.94324,-205.06523,0.8359695,-1.4796692,72.71236,780000
18
+ 141.44415,0.19058642,0.0073161838,6.116914,-7.5757384,-141.39749,-204.19028,1.0902071,-1.2464408,72.84818,785000
19
+ 139.39813,0.19336446,0.008763104,6.8792796,-3.9558299,-139.82872,-205.70798,0.7940436,-0.59193134,60.049713,790000
20
+ 138.27592,0.16303617,0.00904776,7.386917,-3.9776812,-138.86438,-205.17441,1.4148654,-1.3379786,76.6575,795000
21
+ 133.26944,0.19405851,0.008278025,6.4142413,-12.282207,-133.60478,-205.06303,1.0394033,-0.987326,68.894325,800000
22
+ 138.15935,0.19729708,0.009311272,4.997583,-2.2462704,-138.90393,-205.46422,1.3941367,-1.8280864,63.377945,805000
23
+ 135.24388,0.1748997,0.008092487,6.77548,-16.851273,-135.83379,-205.4722,1.0530279,-0.97531104,79.9117,810000
24
+ 130.85068,0.1890715,0.010581822,10.665431,1.0687656,-131.40923,-205.56908,0.9875339,-1.0222018,70.02703,815000
25
+ 133.19719,0.16667563,0.0074774018,4.718349,-12.799075,-133.50528,-204.84631,0.7383493,-0.8237966,48.01096,820000
26
+ 136.9514,0.17887272,0.008515681,8.272271,-13.706109,-136.96695,-205.37225,3.176972,-3.604363,103.106026,825000
27
+ 134.74242,0.17781034,0.007983804,5.5714197,-18.271536,-135.53264,-204.36818,1.3767879,-1.3076116,84.37468,830000
28
+ 133.08495,0.18314897,0.009273208,7.136295,1.2803917,-134.56242,-206.06512,1.9803966,-2.1189973,73.12325,835000
29
+ 127.48154,0.18837348,0.010188282,7.2412715,-2.059922,-128.83345,-205.35954,1.1275405,-1.1221768,67.32153,840000
30
+ 131.61845,0.17020223,0.008226026,5.112383,-2.4723213,-132.30916,-206.15677,1.2811444,-1.3183589,56.10105,845000
31
+ 131.45421,0.15858783,0.007684029,4.9037833,0.06328325,-132.25801,-204.61055,1.5718124,-1.4478722,55.754414,850000
32
+ 129.26068,0.17187089,0.007780165,7.6377854,-4.6601667,-130.3586,-204.72614,0.853925,-0.99287796,69.13497,855000
33
+ 132.4772,0.18786329,0.0072823083,6.454489,-2.5873063,-133.15625,-204.92267,0.881243,-1.3038439,52.280186,860000
34
+ 128.15178,0.17379457,0.009308132,5.1445646,-0.90021455,-128.72388,-204.65857,1.037845,-1.1370687,54.09508,865000
35
+ 130.78076,0.16245314,0.00795669,5.8292675,-3.0805311,-131.0305,-205.4424,0.6626429,-0.6516529,73.03783,870000
36
+ 132.05507,0.18287072,0.008328643,6.335674,-7.122273,-132.10321,-205.81871,1.2903217,-1.2582817,68.3503,875000
37
+ 132.5723,0.18071008,0.008192819,11.445406,2.224225,-132.39616,-204.89717,0.6834783,-0.8497388,77.06786,880000
38
+ 127.68432,0.13913232,0.007941361,5.7487226,-4.676732,-128.15356,-205.69377,0.582042,-0.5212905,58.002266,885000
39
+ 125.12814,0.1745165,0.008398682,7.384332,-3.1122284,-126.10506,-205.11397,0.7426407,-0.7589073,63.128185,890000
40
+ 126.3462,0.15910837,0.008070624,6.1322913,-2.7192311,-126.92639,-203.97842,0.70035243,-0.5844671,55.682972,895000
41
+ 125.97045,0.185188,0.008118796,6.78069,1.380229,-127.07835,-205.15009,1.7698011,-1.3827764,65.030594,900000
42
+ 126.54714,0.1858087,0.008116424,4.5015335,1.4608111,-126.99099,-205.1959,1.344293,-1.1797527,47.20058,905000
43
+ 124.87779,0.16790533,0.009358228,6.8395257,-7.5106087,-125.211586,-205.13759,1.2333634,-1.9762592,63.985714,910000
44
+ 126.526794,0.19480062,0.008811769,6.065003,-0.08480689,-127.02647,-204.67746,1.6295142,-1.951397,73.31648,915000
45
+ 125.73273,0.180256,0.007617006,6.555875,-0.20458789,-126.096695,-205.11769,1.581487,-0.9342154,69.00429,920000
46
+ 119.78861,0.1727244,0.006765791,5.1650395,-9.959052,-120.04915,-203.60902,0.794416,-0.7623451,61.768303,925000
47
+ 125.765274,0.18008809,0.008382903,5.0934687,-0.71044457,-126.17224,-204.08899,0.8405822,-0.8655844,55.46598,930000
48
+ 121.66758,0.20216827,0.0070189023,4.737472,-2.651074,-121.80963,-204.40096,0.9126118,-0.83679795,46.102306,935000
49
+ 119.773834,0.219196,0.00615167,5.153209,1.3287672,-120.459816,-204.258,0.93358177,-0.8331305,56.69139,940000
50
+ 124.022835,0.18707362,0.009377404,7.0360904,-7.0238147,-124.561844,-206.19589,1.2252339,-0.919848,73.89371,945000
51
+ 113.75993,0.19112816,0.008057775,6.7320724,1.9612464,-114.54598,-205.5836,1.9314951,-1.703124,74.55836,950000
52
+ 123.82799,0.17798671,0.0076639554,5.620212,1.6291203,-124.811966,-204.40128,0.6279033,-0.5546749,52.48468,955000
53
+ 120.342545,0.16124555,0.008284608,8.373077,3.2110808,-121.459404,-205.89444,4.172345,-4.111476,147.22633,960000
54
+ 120.25611,0.18452601,0.009120566,5.82998,-5.4214945,-120.5426,-204.4184,2.4523242,-2.1654248,58.472443,965000
55
+ 119.92786,0.17740333,0.0082613565,5.7817297,-4.059332,-120.48733,-203.88084,1.6762794,-2.187871,57.63932,970000
56
+ 118.521736,0.1682422,0.008388954,10.422676,-2.2523232,-118.92224,-205.81229,2.50652,-2.5114205,139.79198,975000
57
+ 122.19589,0.17688103,0.009443209,5.373117,-3.2205245,-122.784645,-205.27272,1.7157899,-1.3797596,69.092834,980000
58
+ 116.87861,0.166918,0.009557361,3.914416,-2.3164752,-117.17098,-203.3465,0.9879238,-0.8555012,67.4073,985000
59
+ 111.88613,0.17116016,0.00826056,6.490758,-0.19741878,-112.73495,-203.79552,1.4187975,-1.2903366,60.526062,990000
60
+ 115.81669,0.1865702,0.0072950404,4.5488825,2.918242,-116.57983,-205.94296,1.0751731,-1.0089108,48.18328,995000
61
+ 118.21511,0.14058462,0.008302457,7.1303873,-4.164439,-118.397865,-204.21469,0.96237195,-1.0755332,77.32739,1000000
62
+ 119.37607,0.15852353,0.007465651,4.154873,-6.135511,-120.975,-205.8851,1.1319185,-1.1179802,68.38727,1005000
63
+ 116.33203,0.14804351,0.0071398104,6.217628,1.8925488,-117.188,-207.12515,0.81947106,-0.8609822,65.498474,1010000
64
+ 117.099655,0.15909386,0.0058505354,4.3195586,-1.5294638,-117.71316,-203.89287,1.6253989,-1.6422474,62.781975,1015000
65
+ 116.59919,0.1857456,0.008149042,7.4299827,4.827311,-117.51035,-204.131,0.9137905,-0.9840506,72.87636,1020000
66
+ 118.93263,0.18976444,0.007580802,5.3209243,-3.7455351,-119.73543,-205.32915,1.2175515,-1.1088737,71.596466,1025000
67
+ 115.31658,0.16769129,0.009185464,9.004993,-3.4572268,-115.66498,-204.23024,1.1748593,-1.1287395,73.57542,1030000
68
+ 115.05547,0.1830498,0.009559326,6.5246797,-3.0145032,-115.80682,-204.24348,1.0400212,-0.95938444,77.555084,1035000
69
+ 117.47124,0.12783952,0.006607903,3.3067994,-3.8830802,-117.84185,-203.2193,0.59068316,-0.7456771,44.325714,1040000
70
+ 120.52972,0.16661042,0.0065466617,6.4414186,-0.77659,-121.776794,-204.22748,1.2150116,-1.4081515,76.083405,1045000
71
+ 111.01364,0.17193422,0.0076102656,4.2477593,-5.5701036,-111.73342,-205.36401,1.6146413,-0.7496912,45.908676,1050000
72
+ 116.27297,0.15699697,0.007895902,5.559896,-3.8641467,-116.27123,-202.96947,0.6705674,-0.73124784,64.358475,1055000
73
+ 110.41717,0.15063088,0.007198992,4.399961,0.29383618,-111.20296,-205.49396,1.0160946,-1.1422272,58.653645,1060000
74
+ 116.78329,0.17646995,0.009398053,5.771059,-11.084978,-116.934875,-204.87529,2.0926313,-1.3069043,67.809135,1065000
75
+ 116.381195,0.17090386,0.0072581694,7.0175567,-2.6913314,-117.04717,-204.09244,0.72063446,-0.7980316,63.900887,1070000
76
+ 109.03105,0.16932568,0.008381098,5.2000237,0.7686693,-110.7156,-204.1561,1.2910379,-1.6911734,78.09993,1075000
77
+ 111.03682,0.17429395,0.008261144,4.315414,-1.9757901,-112.08402,-204.028,4.4712577,-4.3825126,92.5847,1080000
78
+ 113.72152,0.16027081,0.0070624826,6.7255754,-1.23669,-114.74163,-204.541,0.9030102,-1.8224462,62.72799,1085000
79
+ 113.48656,0.147243,0.0072327754,7.4502215,-2.3473167,-114.24048,-204.15092,2.7628033,-3.2262943,69.59822,1090000
80
+ 113.02996,0.16348335,0.0075752735,4.296561,0.20527963,-114.01741,-203.75327,0.8191738,-0.81687474,52.517784,1095000
81
+ 108.875694,0.17337298,0.0069814613,5.459606,0.025934428,-109.671265,-202.05257,1.7338418,-2.4568672,88.88837,1100000
82
+ 110.194244,0.17458354,0.0060094954,7.0346346,-0.71756184,-110.40855,-204.54071,1.6771334,-1.5829782,56.23833,1105000
83
+ 117.126976,0.14762518,0.0066159437,5.071898,-6.629565,-117.34214,-201.37357,0.83481526,-0.79793835,48.821014,1110000
84
+ 109.38428,0.13141197,0.0079182,4.7362185,3.1622622,-110.30098,-204.7312,0.49672917,-0.7057499,51.68799,1115000
85
+ 113.20177,0.16154134,0.008009182,5.3806405,-0.6329559,-114.28865,-203.9079,0.65270483,-0.7539405,55.12653,1120000
86
+ 107.423584,0.18083507,0.0071046897,6.31658,1.3632792,-108.66406,-206.38028,0.6506114,-0.9989732,59.597244,1125000
87
+ 108.94887,0.15254831,0.007234061,3.7659535,-4.4714847,-109.59412,-204.79031,0.8184762,-0.839598,51.47072,1130000
88
+ 114.894455,0.17425133,0.00823997,4.4491878,-4.0517664,-114.82198,-205.30176,1.5618898,-1.4971818,63.79975,1135000
89
+ 107.24571,0.18441892,0.0073837745,4.9540305,-2.61219,-107.9397,-205.86565,1.2492225,-1.1140094,65.63453,1140000
90
+ 110.2875,0.18552792,0.007412205,5.2969894,-6.0151424,-111.04419,-203.92178,1.9419625,-1.9797187,58.054787,1145000
91
+ 109.160095,0.1524603,0.0061386772,6.1301045,3.9091403,-110.186035,-204.43546,1.0498697,-0.95681614,58.78545,1150000
92
+ 107.92546,0.16815475,0.006588653,4.374219,2.1844118,-108.4126,-202.11876,0.5453002,-0.54291993,42.96575,1155000
93
+ 105.88848,0.17370361,0.0062000863,7.009952,9.325735,-106.878784,-204.59375,1.4627106,-1.3540566,85.81352,1160000
94
+ 108.55725,0.18158008,0.007982843,5.531221,0.43892246,-108.94927,-205.24721,4.6941485,-5.6852174,86.8138,1165000
95
+ 110.43191,0.12864473,0.00704508,8.701892,1.2470024,-110.82827,-200.92162,1.8462037,-1.8769753,102.740364,1170000
96
+ 106.20629,0.1501727,0.007635716,5.3964667,1.3313936,-106.93245,-204.05396,1.1380854,-1.4165986,55.018845,1175000
97
+ 108.247856,0.18934391,0.008083877,4.752317,16.04313,-108.610596,-203.96892,0.8938473,-0.6838271,63.51959,1180000
98
+ 106.39112,0.1547153,0.0072209197,6.2954683,1.2930094,-107.2485,-204.84842,0.95097435,-1.1735638,70.80474,1185000
99
+ 107.29465,0.15341961,0.0068927286,5.514774,1.415102,-108.32896,-203.79156,0.97347385,-0.87979513,57.290474,1190000
100
+ 101.09695,0.13516659,0.0060413224,4.2358613,0.15006343,-102.7666,-203.74365,0.7372116,-0.7309707,52.721703,1195000
101
+ 100.59953,0.14280409,0.0068115476,4.2021227,-1.5133352,-101.48498,-205.7008,0.80881494,-0.8284002,48.78897,1200000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3dee7a9f450b800887cbe4cbc646d30c675c554743f85f522e7853d8d5af5a
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_1050000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00b285523b031503164927ecbfa872a378fb05bdf31cd14fd57b76663e13ebf4
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_1100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80de28e3c96b445cef051ed88eef90624e030268f8f002310d7ebe3006f5add0
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_1150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b371774d87274f2bc7386386c15e4f65d7d580ca011756e5356a16a715d92e9c
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_1200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c05cd010d4b4d62d85226b362eadf9fb90cb9e83fd7eceefd726462954cdda6
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_750000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020063f2952af58c331275f96c37576a48ecfb2133f4de64a6217b87373c0c40
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_800000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6abce8c6aa5a06dd27127f051c4c497cbaf0dcf7dd106cd5771dc0e8d53e0a0b
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_850000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9018cd401ddeed0f952053c5e3f490927273c8365c75863347e81cf6f5a7a60
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_900000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43fc5b931cde823c7de60a268b4698d6c148fefe5a8378928ced02a92a7510c2
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aaec643958cc886bcfe7a105b9d5390cd7896573a63cec60308bfe2415e6c88
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_042005/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/dvhy5r4w