Tiredsheep commited on
Commit
94aacc9
·
verified ·
1 Parent(s): df7d515

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/env.csv +0 -0
  2. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/env_sv.csv +0 -0
  3. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/eval.csv +11 -0
  4. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/eval_sv.csv +11 -0
  5. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/online_agent.csv +101 -0
  6. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/online_agent_sv.csv +101 -0
  7. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1000000.pkl +3 -0
  8. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1050000.pkl +3 -0
  9. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1100000.pkl +3 -0
  10. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1150000.pkl +3 -0
  11. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1200000.pkl +3 -0
  12. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1250000.pkl +3 -0
  13. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1300000.pkl +3 -0
  14. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1350000.pkl +3 -0
  15. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1400000.pkl +3 -0
  16. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_950000.pkl +3 -0
  17. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/progress.tk +1 -0
  18. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/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/rebrac/20260311_194404/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/rebrac/20260311_194404/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,-0.05967335700788261,-0.0049353502764335755,-0.05935818971373815,0.001695502476297367,23.982281059232154,10.90399999999893,0.72,5238.6,-0.4,-333.94,216.08,0.6593766164779663,950000
3
+ 0.0,0.0,-0.04812572470802136,0.010032701104894534,-0.046359428499435,0.0078178802436984,31.820621304914717,7.3299999999993375,0.84,14470.84,-0.2,-195.7,144.6,0.45266730308532716,1000000
4
+ 0.0,0.0,-0.06054254964299117,0.032830875904550125,-0.05780611319959042,0.03036941475726282,32.77833836482121,4.773999999999667,0.94,20653.06,-0.1,-140.46,93.48,0.3092236614227295,1050000
5
+ 0.0,0.0,-0.05524949623476959,0.027447558232621093,-0.05247436362227619,0.02657218540032321,32.163185027409874,5.343999999999635,0.92,26046.22,-0.14,-163.3,104.88,0.3324254465103149,1100000
6
+ 0.0,0.0,-0.07013980480930365,0.05007449135755534,-0.06619826403179384,0.05257512583812557,34.986064759429524,3.5969999999998343,0.98,30698.9,-0.04,-105.44,69.94,0.22526371002197265,1150000
7
+ 0.0,0.0,-0.06481693728971324,0.0489598456905101,-0.06111458748242891,0.049996679889589134,35.758350619848265,3.615999999999835,0.98,34465.82,-0.02,-99.36,70.32,0.22881999969482422,1200000
8
+ 0.0,0.0,-0.051133212852400425,0.05427313061177244,-0.047848046892029594,0.04990348640652459,34.83994441907248,4.264999999999727,0.94,38492.74,-0.1,-129.46,83.3,0.26736644744873045,1250000
9
+ 0.0,0.0,-0.05914142006085859,0.05043591091237345,-0.055663277814024234,0.059864196113554716,34.53418455498867,3.2649999999998793,0.98,42000.9,-0.04,-96.52,63.3,0.2080231761932373,1300000
10
+ 0.0,0.0,-0.07299001771309167,0.05226363178193275,-0.06895035232861017,0.04443283449425898,34.58504286826392,2.954999999999887,0.98,45297.68,-0.02,-79.14,57.1,0.18609286308288575,1350000
11
+ 0.0,0.0,-0.0637244740658056,0.05733832025335124,-0.060272258440724064,0.05667743627354632,34.23003492394361,3.3439999999999,0.98,48567.24,-0.02,-96.64,64.88,0.21305737018585205,1400000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/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,-0.05967335700788261,-0.0049353502764335755,-0.05935818971373815,0.001695502476297367,23.982281059232154,10.90399999999893,0.72,5238.6,-0.4,-333.94,216.08,0.6593766164779663,950000
3
+ 0.0,0.0,-0.04812572470802136,0.010032701104894534,-0.046359428499435,0.0078178802436984,31.820621304914717,7.3299999999993375,0.84,14470.84,-0.2,-195.7,144.6,0.45266730308532716,1000000
4
+ 0.0,0.0,-0.06054254964299117,0.032830875904550125,-0.05780611319959042,0.03036941475726282,32.77833836482121,4.773999999999667,0.94,20653.06,-0.1,-140.46,93.48,0.3092236614227295,1050000
5
+ 0.0,0.0,-0.05524949623476959,0.027447558232621093,-0.05247436362227619,0.02657218540032321,32.163185027409874,5.343999999999635,0.92,26046.22,-0.14,-163.3,104.88,0.3324254465103149,1100000
6
+ 0.0,0.0,-0.07013980480930365,0.05007449135755534,-0.06619826403179384,0.05257512583812557,34.986064759429524,3.5969999999998343,0.98,30698.9,-0.04,-105.44,69.94,0.22526371002197265,1150000
7
+ 0.0,0.0,-0.06481693728971324,0.0489598456905101,-0.06111458748242891,0.049996679889589134,35.758350619848265,3.615999999999835,0.98,34465.82,-0.02,-99.36,70.32,0.22881999969482422,1200000
8
+ 0.0,0.0,-0.051133212852400425,0.05427313061177244,-0.047848046892029594,0.04990348640652459,34.83994441907248,4.264999999999727,0.94,38492.74,-0.1,-129.46,83.3,0.26736644744873045,1250000
9
+ 0.0,0.0,-0.05914142006085859,0.05043591091237345,-0.055663277814024234,0.059864196113554716,34.53418455498867,3.2649999999998793,0.98,42000.9,-0.04,-96.52,63.3,0.2080231761932373,1300000
10
+ 0.0,0.0,-0.07299001771309167,0.05226363178193275,-0.06895035232861017,0.04443283449425898,34.58504286826392,2.954999999999887,0.98,45297.68,-0.02,-79.14,57.1,0.18609286308288575,1350000
11
+ 0.0,0.0,-0.0637244740658056,0.05733832025335124,-0.060272258440724064,0.05667743627354632,34.23003492394361,3.3439999999999,0.98,48567.24,-0.02,-96.64,64.88,0.21305737018585205,1400000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/online_agent.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/action_std,actor/actor_loss,actor/bc_loss,actor/mse,actor/total_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 1.0,1.0,0.023560852,2.3560853,1.0235609,0.31703743,-25.178127,-105.33588,-181.2821,0.08052961,-0.15774749,6.0324054,905000
3
+ 1.0,1.0,0.02311986,2.3119862,1.0231198,0.62824684,-20.893965,-104.65154,-178.88803,0.2258584,-0.24425155,12.404209,910000
4
+ 1.0,1.0,0.020508535,2.0508535,1.0205085,0.66236156,-29.039959,-109.51105,-183.90642,0.11848141,-0.098490834,7.566047,915000
5
+ 1.0,1.0000001,0.020753004,2.0753007,1.0207531,0.7667503,-20.87578,-110.2694,-194.69402,0.13338831,-0.07537955,8.389747,920000
6
+ 1.0,1.0,0.020509914,2.0509913,1.02051,0.69008064,-40.04085,-109.65625,-190.55026,0.14630505,-0.12321436,8.08724,925000
7
+ 1.0,1.0,0.02135421,2.1354208,1.0213542,1.0170301,-39.43192,-107.8558,-195.32678,0.21945381,-0.18218093,13.533354,930000
8
+ 1.0,0.99999994,0.022840451,2.2840455,1.0228404,0.86826706,-27.558994,-107.06917,-193.41415,0.63439494,-0.6345502,20.088379,935000
9
+ 1.0,1.0,0.022012016,2.2012017,1.022012,3.1172645,-43.415783,-108.34039,-189.99084,0.33992308,-0.37691897,24.632988,940000
10
+ 1.0,1.0,0.021952396,2.1952395,1.0219524,1.2163088,-35.05275,-108.146805,-203.54276,0.21237072,-0.25211418,15.5218525,945000
11
+ 1.0,0.99999994,0.025138024,2.5138025,1.025138,1.3993076,-4.122537,-103.01269,-182.08968,0.43950593,-0.33581102,24.115522,950000
12
+ 1.0,0.99999994,0.025774805,2.5774806,1.0257747,1.1939907,-23.202791,-101.69356,-197.87021,0.16416268,-0.29150382,14.398701,955000
13
+ 1.0,1.0,0.024396896,2.4396896,1.0243969,4.471864,-20.534378,-99.12582,-197.0369,1.5570945,-1.6755924,47.77545,960000
14
+ 1.0,0.99999994,0.023665618,2.3665621,1.0236655,1.260393,-11.161547,-98.00982,-193.40596,0.15254523,-0.31519607,15.328273,965000
15
+ 1.0,1.0,0.02383258,2.3832583,1.0238326,1.3901417,-9.713713,-96.82385,-204.01282,0.3988276,-0.19760232,16.625374,970000
16
+ 1.0,1.0,0.025206458,2.520646,1.0252064,1.69611,-12.675197,-100.7822,-196.37042,0.37972084,-0.47286457,23.29624,975000
17
+ 1.0,0.99999994,0.02561602,2.561602,1.0256159,1.1379102,-0.14009318,-100.24312,-196.27682,0.3019352,-0.14584547,16.482956,980000
18
+ 1.0,1.0,0.025439732,2.5439732,1.0254397,0.94367,-6.357076,-100.34606,-197.71095,0.14400947,-0.1091304,10.1026745,985000
19
+ 1.0,1.0,0.025521263,2.5521264,1.0255213,1.1939133,-7.3256493,-96.91784,-193.96501,0.18991974,-0.18121374,12.072575,990000
20
+ 1.0,1.0,0.025559768,2.5559769,1.0255598,1.3603232,-0.29382634,-97.941574,-196.24161,0.16269358,-0.21853858,12.945818,995000
21
+ 1.0,1.0000001,0.023907539,2.390754,1.0239077,1.2130722,-23.883173,-93.146255,-183.08025,0.3230013,-0.1918295,16.135971,1000000
22
+ 1.0,1.0000001,0.026250029,2.625003,1.0262501,0.9683628,-2.8114064,-94.78903,-193.83925,0.16752295,-0.1461365,11.847147,1005000
23
+ 1.0,1.0,0.025700238,2.5700238,1.0257002,1.0980316,-9.43659,-95.25644,-173.72652,0.12885162,-0.13781044,11.83244,1010000
24
+ 1.0,0.99991643,0.025353406,2.5353408,1.0252699,1.7616326,2.176464,-90.608315,-173.59421,0.34567994,-0.32575628,24.453527,1015000
25
+ 1.0,1.0,0.026701972,2.670197,1.0267019,1.2045561,-5.5979614,-91.24599,-172.58987,0.20836699,-0.2396235,13.808342,1020000
26
+ 1.0,1.0,0.02650131,2.6501312,1.0265013,1.5630977,-21.395302,-94.88977,-181.28043,0.25159734,-0.22893932,18.254614,1025000
27
+ 1.0,0.9999853,0.027090434,2.7090435,1.0270758,1.0119377,1.8283923,-93.40084,-183.48251,0.328048,-0.1677851,14.508221,1030000
28
+ 1.0,0.99994564,0.02732284,2.732284,1.0272685,1.5237851,1.642109,-92.942314,-176.86732,0.6397866,-0.72205013,25.70871,1035000
29
+ 1.0,1.0,0.028140236,2.8140235,1.0281402,1.038299,-0.9555733,-87.13744,-190.59993,0.23208562,-0.171862,13.978234,1040000
30
+ 1.0,1.0,0.02780741,2.7807412,1.0278074,1.0427754,-2.1087565,-91.168106,-201.78435,0.20869182,-0.14912832,12.081525,1045000
31
+ 1.0,1.0,0.027505223,2.7505221,1.0275053,0.9342165,-3.009866,-89.668945,-198.52211,0.18523125,-0.20289513,12.98115,1050000
32
+ 1.0,1.0,0.025187135,2.5187135,1.0251871,1.0378637,-1.968296,-91.57815,-184.69717,0.18983287,-0.27242547,12.338209,1055000
33
+ 1.0,0.9999947,0.027220944,2.7220945,1.0272156,1.2453102,2.4631095,-89.170525,-195.83473,0.2714184,-0.2882011,19.006277,1060000
34
+ 1.0,1.0,0.026645243,2.6645246,1.0266452,0.89755964,-1.8689119,-87.99859,-188.5126,0.14893094,-0.17923275,11.319877,1065000
35
+ 1.0,1.0,0.029571708,2.957171,1.0295717,1.7733822,-2.896296,-86.01094,-178.92784,0.23309465,-0.21779932,18.73283,1070000
36
+ 1.0,0.99999994,0.029243745,2.9243743,1.0292437,1.1416644,-6.1310463,-91.30948,-193.75772,0.310988,-0.15424284,13.052547,1075000
37
+ 1.0,0.9999583,0.027019897,2.70199,1.0269781,1.2801129,2.0074217,-88.64112,-194.41235,0.1160923,-0.19620262,15.507796,1080000
38
+ 1.0,1.0,0.028567499,2.8567498,1.0285676,1.0770521,-4.309614,-87.029655,-167.23907,0.18007454,-0.15643263,12.71722,1085000
39
+ 1.0,0.99999994,0.026109792,2.6109793,1.0261097,2.4219666,-4.7393017,-85.91838,-188.03975,0.71544814,-0.7117937,35.90501,1090000
40
+ 1.0,0.99999994,0.027568538,2.7568536,1.0275685,1.1220247,-8.222528,-87.67018,-196.57138,0.18932706,-0.3318026,15.912117,1095000
41
+ 1.0,0.9999999,0.027365815,2.7365818,1.0273657,1.0473275,-1.9037862,-86.26454,-196.08412,0.1070808,-0.21778932,12.871006,1100000
42
+ 1.0,0.99999994,0.026740123,2.6740122,1.0267401,1.9886407,-1.3909761,-86.88832,-167.98166,0.5935469,-1.0216299,33.25441,1105000
43
+ 1.0,1.0,0.02816212,2.8162122,1.0281621,0.93562764,-5.8516135,-86.41833,-184.07768,0.17156258,-0.08552337,10.8085375,1110000
44
+ 1.0,1.0,0.028574705,2.8574705,1.0285747,1.4597193,-2.266429,-86.22613,-194.51,0.15183538,-0.2660482,15.574472,1115000
45
+ 1.0,1.0,0.027451428,2.7451427,1.0274514,3.3572698,-0.7116668,-84.93219,-199.71349,0.42164883,-0.6077612,29.251667,1120000
46
+ 1.0,0.9999996,0.02864112,2.8641124,1.0286407,1.9944944,-5.719705,-83.6867,-164.77179,0.22461633,-0.36987156,21.08537,1125000
47
+ 1.0,0.99999994,0.028707504,2.8707504,1.0287075,5.0704412,0.101175666,-85.21126,-183.37729,0.9574064,-0.86672467,37.917656,1130000
48
+ 1.0,1.0,0.026824055,2.6824055,1.026824,1.0435574,-3.3623374,-81.97908,-173.04944,0.1972935,-0.34747654,11.707766,1135000
49
+ 1.0,0.9999472,0.028177004,2.8177004,1.0281242,1.2381729,2.0875747,-84.014915,-200.82948,0.23062298,-0.36132312,16.116007,1140000
50
+ 1.0,0.99999994,0.030739468,3.0739465,1.0307394,1.1379626,-3.102193,-85.76052,-183.31958,0.26464856,-0.30618578,16.696083,1145000
51
+ 1.0,1.0000001,0.026608583,2.6608584,1.0266087,1.5630172,-5.2428308,-77.30064,-197.94829,1.3816454,-1.4016742,31.04306,1150000
52
+ 1.0,0.99999994,0.028601598,2.8601599,1.0286015,1.2067604,-8.305926,-85.66723,-192.30235,0.15247226,-0.30881658,14.917528,1155000
53
+ 1.0,1.0,0.027730552,2.7730553,1.0277306,1.2100285,1.5486658,-84.775894,-187.52283,0.19525658,-0.2130683,13.438185,1160000
54
+ 1.0,0.99999994,0.030234134,3.0234132,1.0302341,1.9247525,-2.231932,-82.900536,-203.25027,0.3343602,-0.5255017,25.568615,1165000
55
+ 1.0,1.0,0.029333238,2.9333239,1.0293332,3.214651,-4.978823,-84.132065,-168.7561,0.7555856,-0.5240155,34.27971,1170000
56
+ 1.0,0.99999994,0.026571466,2.6571465,1.0265714,9.010109,-2.597143,-82.03487,-202.71384,1.3037263,-1.3917344,66.74686,1175000
57
+ 1.0,1.0,0.028228283,2.8228283,1.0282283,0.98285526,-4.916829,-83.498024,-164.46071,0.3241868,-0.12517382,13.446921,1180000
58
+ 1.0,0.9999999,0.027618969,2.7618968,1.0276189,1.0414747,-2.7659104,-79.24111,-169.5334,0.28159875,-0.13623811,14.665682,1185000
59
+ 1.0,0.99999994,0.028225007,2.8225007,1.028225,1.3152599,-2.678369,-78.46537,-200.70288,0.20576479,-0.24606535,17.855694,1190000
60
+ 1.0,1.0,0.02711659,2.7116592,1.0271165,1.4706349,0.36656433,-80.29763,-181.56882,0.29066527,-0.24045637,18.584057,1195000
61
+ 1.0,1.0,0.026951516,2.6951518,1.0269516,0.94928676,-3.7228186,-81.81735,-164.7382,0.20838371,-0.19114566,12.983607,1200000
62
+ 1.0,1.0,0.03139618,3.1396184,1.0313962,1.3127297,-0.8315287,-82.08982,-183.21342,0.24974258,-0.31796193,17.036703,1205000
63
+ 1.0,0.99999994,0.029804923,2.9804924,1.0298048,2.4433773,-4.051466,-80.32904,-188.3796,0.63187367,-0.7085147,34.983303,1210000
64
+ 1.0,0.99999994,0.02791384,2.7913842,1.0279138,1.024804,0.8167348,-78.57224,-157.89821,0.25830424,-0.26376027,15.553793,1215000
65
+ 1.0,0.99999994,0.029500565,2.9500566,1.0295005,1.3349024,-5.820112,-80.75002,-172.56682,0.26681584,-0.2636851,15.496218,1220000
66
+ 1.0,1.0000001,0.029223073,2.9223075,1.0292232,0.9090977,-3.293055,-80.81467,-184.7794,0.16814318,-0.22270262,12.011722,1225000
67
+ 1.0,1.0,0.028913036,2.8913035,1.028913,1.859127,-3.7516217,-77.540794,-188.82686,0.430294,-0.2223491,20.199364,1230000
68
+ 1.0,1.0,0.028785903,2.8785906,1.028786,1.0773613,-1.9983146,-79.71222,-202.04149,0.27059162,-0.2556342,14.837778,1235000
69
+ 1.0,1.0,0.029793505,2.9793506,1.0297935,0.8958626,-4.7826033,-80.96465,-167.61488,0.14616752,-0.3116796,12.185198,1240000
70
+ 1.0,1.0,0.028746825,2.8746824,1.0287468,1.1145933,0.43620056,-83.30967,-196.66508,0.36132383,-0.2876523,18.547264,1245000
71
+ 1.0,1.0,0.026743228,2.6743226,1.0267432,1.2905113,-1.9251771,-77.74054,-192.59384,0.5373203,-0.61268014,21.319454,1250000
72
+ 1.0,1.0,0.028281126,2.8281126,1.0282811,3.0538056,0.014931917,-82.04868,-176.16594,1.1892562,-0.7709799,66.87318,1255000
73
+ 1.0,1.0000001,0.028110914,2.8110914,1.028111,1.5377945,-0.2971983,-79.02608,-201.7635,0.51195395,-0.471603,24.971016,1260000
74
+ 1.0,0.99999994,0.028460978,2.846098,1.0284609,0.7904707,-2.925911,-78.41892,-188.12566,0.114033975,-0.4123639,12.115517,1265000
75
+ 1.0,0.99999994,0.027354915,2.7354915,1.0273548,1.4379128,0.28550562,-76.72317,-183.14207,0.20621975,-0.2535996,15.047097,1270000
76
+ 1.0,1.0,0.028524064,2.8524065,1.028524,0.84561807,1.0294863,-77.349396,-201.02394,0.1385741,-0.13816977,11.57492,1275000
77
+ 1.0,1.0000001,0.0275786,2.7578602,1.0275787,1.415048,-3.8571825,-78.5584,-181.06924,0.1850233,-0.42610422,20.08408,1280000
78
+ 1.0,1.0,0.02980528,2.980528,1.0298053,1.1383162,-2.8606791,-77.84904,-187.25366,0.19075656,-0.19589296,13.955799,1285000
79
+ 1.0,1.0,0.029901486,2.9901485,1.0299015,1.2638752,0.943194,-78.70779,-184.5411,0.4109637,-0.6259148,26.411556,1290000
80
+ 1.0,1.0,0.029329473,2.9329472,1.0293294,1.3011326,6.526713,-80.41529,-162.09027,0.38391218,-0.55301976,14.758926,1295000
81
+ 1.0,1.0000001,0.02846408,2.846408,1.0284642,1.3934034,-2.1306474,-75.349846,-165.9608,0.34779346,-0.25506634,17.013273,1300000
82
+ 1.0,1.0,0.029871311,2.987131,1.0298713,1.4905754,-1.6062323,-77.98921,-181.79216,0.40857217,-0.22106129,20.591362,1305000
83
+ 1.0,0.99999994,0.030010791,3.0010793,1.0300107,0.95384425,-0.5266844,-77.16654,-153.92555,0.20173113,-0.23947498,12.545654,1310000
84
+ 1.0,0.9999999,0.026237216,2.6237216,1.0262371,1.4329952,-2.477703,-75.56842,-157.56221,0.51096934,-0.46920708,17.93782,1315000
85
+ 1.0,1.0,0.030138211,3.0138214,1.0301383,0.8076052,-3.9851255,-73.53954,-171.60512,0.45445016,-0.46856308,12.3631,1320000
86
+ 1.0,1.0,0.027940266,2.7940264,1.0279403,1.1584053,-0.07167959,-74.60439,-197.28653,0.36894947,-0.44055378,21.240337,1325000
87
+ 1.0,1.0,0.030116037,3.0116038,1.0301161,1.1903017,-1.3039125,-75.06168,-167.99774,0.31829566,-0.21028537,15.890092,1330000
88
+ 1.0,1.0,0.031060662,3.1060667,1.0310607,0.97415733,-1.5535127,-76.94234,-200.04031,0.4276281,-0.15933095,17.696495,1335000
89
+ 1.0,0.9999999,0.03111158,3.1111581,1.0311115,2.1323586,-0.25353643,-75.35097,-182.87444,0.5926424,-0.19350505,23.667484,1340000
90
+ 1.0,0.9999999,0.029570527,2.9570527,1.0295705,1.1654218,-1.8433166,-77.53863,-160.60576,0.34727174,-0.30091202,16.252516,1345000
91
+ 1.0,1.0,0.028332973,2.8332973,1.028333,1.5124791,1.1933526,-73.47881,-162.33363,1.772752,-2.0131493,40.953243,1350000
92
+ 1.0,1.0,0.03007796,3.0077963,1.0300779,1.0116196,-0.49753708,-75.11541,-168.14825,0.20203005,-0.25363898,11.83728,1355000
93
+ 1.0,1.0,0.027256796,2.7256794,1.0272568,0.9287359,-1.2451317,-72.788635,-168.56929,0.17578976,-0.27870446,13.096105,1360000
94
+ 1.0,1.0,0.030417904,3.0417905,1.0304179,1.1437315,-2.358684,-74.5594,-170.42339,0.53443897,-0.49766615,15.305337,1365000
95
+ 1.0,1.0,0.028267685,2.8267689,1.0282677,1.5121464,-1.8089867,-69.44217,-154.34149,0.34207103,-0.18506536,17.252632,1370000
96
+ 1.0,0.99999994,0.02879256,2.879256,1.0287925,0.98702335,-1.7762525,-74.319016,-183.70457,0.27320552,-0.28506896,14.940676,1375000
97
+ 1.0,0.9999999,0.030325929,3.0325928,1.0303258,1.232828,1.353568,-72.44436,-185.58101,0.20255044,-0.33325806,13.22139,1380000
98
+ 1.0,0.9999999,0.030503355,3.0503356,1.0305033,1.2561748,-1.7564313,-74.32138,-197.5193,0.45278478,-0.13881958,15.886172,1385000
99
+ 1.0,1.0,0.028314553,2.8314555,1.0283146,0.98733515,-4.062499,-73.7098,-172.99748,0.21143943,-0.5229739,15.399714,1390000
100
+ 1.0,1.0,0.028110597,2.8110597,1.0281106,1.367649,4.672265,-70.001366,-175.627,0.4869478,-0.4364121,20.140583,1395000
101
+ 1.0,1.0,0.029480577,2.948058,1.0294806,1.2452204,-1.1892135,-69.23844,-177.48293,0.49569583,-0.41975626,21.073853,1400000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/online_agent_sv.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/action_std,actor/actor_loss,actor/bc_loss,actor/mse,actor/total_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 1.0,1.0,0.023560852,2.3560853,1.0235609,0.31703743,-25.178127,-105.33588,-181.2821,0.08052961,-0.15774749,6.0324054,905000
3
+ 1.0,1.0,0.02311986,2.3119862,1.0231198,0.62824684,-20.893965,-104.65154,-178.88803,0.2258584,-0.24425155,12.404209,910000
4
+ 1.0,1.0,0.020508535,2.0508535,1.0205085,0.66236156,-29.039959,-109.51105,-183.90642,0.11848141,-0.098490834,7.566047,915000
5
+ 1.0,1.0000001,0.020753004,2.0753007,1.0207531,0.7667503,-20.87578,-110.2694,-194.69402,0.13338831,-0.07537955,8.389747,920000
6
+ 1.0,1.0,0.020509914,2.0509913,1.02051,0.69008064,-40.04085,-109.65625,-190.55026,0.14630505,-0.12321436,8.08724,925000
7
+ 1.0,1.0,0.02135421,2.1354208,1.0213542,1.0170301,-39.43192,-107.8558,-195.32678,0.21945381,-0.18218093,13.533354,930000
8
+ 1.0,0.99999994,0.022840451,2.2840455,1.0228404,0.86826706,-27.558994,-107.06917,-193.41415,0.63439494,-0.6345502,20.088379,935000
9
+ 1.0,1.0,0.022012016,2.2012017,1.022012,3.1172645,-43.415783,-108.34039,-189.99084,0.33992308,-0.37691897,24.632988,940000
10
+ 1.0,1.0,0.021952396,2.1952395,1.0219524,1.2163088,-35.05275,-108.146805,-203.54276,0.21237072,-0.25211418,15.5218525,945000
11
+ 1.0,0.99999994,0.025138024,2.5138025,1.025138,1.3993076,-4.122537,-103.01269,-182.08968,0.43950593,-0.33581102,24.115522,950000
12
+ 1.0,0.99999994,0.025774805,2.5774806,1.0257747,1.1939907,-23.202791,-101.69356,-197.87021,0.16416268,-0.29150382,14.398701,955000
13
+ 1.0,1.0,0.024396896,2.4396896,1.0243969,4.471864,-20.534378,-99.12582,-197.0369,1.5570945,-1.6755924,47.77545,960000
14
+ 1.0,0.99999994,0.023665618,2.3665621,1.0236655,1.260393,-11.161547,-98.00982,-193.40596,0.15254523,-0.31519607,15.328273,965000
15
+ 1.0,1.0,0.02383258,2.3832583,1.0238326,1.3901417,-9.713713,-96.82385,-204.01282,0.3988276,-0.19760232,16.625374,970000
16
+ 1.0,1.0,0.025206458,2.520646,1.0252064,1.69611,-12.675197,-100.7822,-196.37042,0.37972084,-0.47286457,23.29624,975000
17
+ 1.0,0.99999994,0.02561602,2.561602,1.0256159,1.1379102,-0.14009318,-100.24312,-196.27682,0.3019352,-0.14584547,16.482956,980000
18
+ 1.0,1.0,0.025439732,2.5439732,1.0254397,0.94367,-6.357076,-100.34606,-197.71095,0.14400947,-0.1091304,10.1026745,985000
19
+ 1.0,1.0,0.025521263,2.5521264,1.0255213,1.1939133,-7.3256493,-96.91784,-193.96501,0.18991974,-0.18121374,12.072575,990000
20
+ 1.0,1.0,0.025559768,2.5559769,1.0255598,1.3603232,-0.29382634,-97.941574,-196.24161,0.16269358,-0.21853858,12.945818,995000
21
+ 1.0,1.0000001,0.023907539,2.390754,1.0239077,1.2130722,-23.883173,-93.146255,-183.08025,0.3230013,-0.1918295,16.135971,1000000
22
+ 1.0,1.0000001,0.026250029,2.625003,1.0262501,0.9683628,-2.8114064,-94.78903,-193.83925,0.16752295,-0.1461365,11.847147,1005000
23
+ 1.0,1.0,0.025700238,2.5700238,1.0257002,1.0980316,-9.43659,-95.25644,-173.72652,0.12885162,-0.13781044,11.83244,1010000
24
+ 1.0,0.99991643,0.025353406,2.5353408,1.0252699,1.7616326,2.176464,-90.608315,-173.59421,0.34567994,-0.32575628,24.453527,1015000
25
+ 1.0,1.0,0.026701972,2.670197,1.0267019,1.2045561,-5.5979614,-91.24599,-172.58987,0.20836699,-0.2396235,13.808342,1020000
26
+ 1.0,1.0,0.02650131,2.6501312,1.0265013,1.5630977,-21.395302,-94.88977,-181.28043,0.25159734,-0.22893932,18.254614,1025000
27
+ 1.0,0.9999853,0.027090434,2.7090435,1.0270758,1.0119377,1.8283923,-93.40084,-183.48251,0.328048,-0.1677851,14.508221,1030000
28
+ 1.0,0.99994564,0.02732284,2.732284,1.0272685,1.5237851,1.642109,-92.942314,-176.86732,0.6397866,-0.72205013,25.70871,1035000
29
+ 1.0,1.0,0.028140236,2.8140235,1.0281402,1.038299,-0.9555733,-87.13744,-190.59993,0.23208562,-0.171862,13.978234,1040000
30
+ 1.0,1.0,0.02780741,2.7807412,1.0278074,1.0427754,-2.1087565,-91.168106,-201.78435,0.20869182,-0.14912832,12.081525,1045000
31
+ 1.0,1.0,0.027505223,2.7505221,1.0275053,0.9342165,-3.009866,-89.668945,-198.52211,0.18523125,-0.20289513,12.98115,1050000
32
+ 1.0,1.0,0.025187135,2.5187135,1.0251871,1.0378637,-1.968296,-91.57815,-184.69717,0.18983287,-0.27242547,12.338209,1055000
33
+ 1.0,0.9999947,0.027220944,2.7220945,1.0272156,1.2453102,2.4631095,-89.170525,-195.83473,0.2714184,-0.2882011,19.006277,1060000
34
+ 1.0,1.0,0.026645243,2.6645246,1.0266452,0.89755964,-1.8689119,-87.99859,-188.5126,0.14893094,-0.17923275,11.319877,1065000
35
+ 1.0,1.0,0.029571708,2.957171,1.0295717,1.7733822,-2.896296,-86.01094,-178.92784,0.23309465,-0.21779932,18.73283,1070000
36
+ 1.0,0.99999994,0.029243745,2.9243743,1.0292437,1.1416644,-6.1310463,-91.30948,-193.75772,0.310988,-0.15424284,13.052547,1075000
37
+ 1.0,0.9999583,0.027019897,2.70199,1.0269781,1.2801129,2.0074217,-88.64112,-194.41235,0.1160923,-0.19620262,15.507796,1080000
38
+ 1.0,1.0,0.028567499,2.8567498,1.0285676,1.0770521,-4.309614,-87.029655,-167.23907,0.18007454,-0.15643263,12.71722,1085000
39
+ 1.0,0.99999994,0.026109792,2.6109793,1.0261097,2.4219666,-4.7393017,-85.91838,-188.03975,0.71544814,-0.7117937,35.90501,1090000
40
+ 1.0,0.99999994,0.027568538,2.7568536,1.0275685,1.1220247,-8.222528,-87.67018,-196.57138,0.18932706,-0.3318026,15.912117,1095000
41
+ 1.0,0.9999999,0.027365815,2.7365818,1.0273657,1.0473275,-1.9037862,-86.26454,-196.08412,0.1070808,-0.21778932,12.871006,1100000
42
+ 1.0,0.99999994,0.026740123,2.6740122,1.0267401,1.9886407,-1.3909761,-86.88832,-167.98166,0.5935469,-1.0216299,33.25441,1105000
43
+ 1.0,1.0,0.02816212,2.8162122,1.0281621,0.93562764,-5.8516135,-86.41833,-184.07768,0.17156258,-0.08552337,10.8085375,1110000
44
+ 1.0,1.0,0.028574705,2.8574705,1.0285747,1.4597193,-2.266429,-86.22613,-194.51,0.15183538,-0.2660482,15.574472,1115000
45
+ 1.0,1.0,0.027451428,2.7451427,1.0274514,3.3572698,-0.7116668,-84.93219,-199.71349,0.42164883,-0.6077612,29.251667,1120000
46
+ 1.0,0.9999996,0.02864112,2.8641124,1.0286407,1.9944944,-5.719705,-83.6867,-164.77179,0.22461633,-0.36987156,21.08537,1125000
47
+ 1.0,0.99999994,0.028707504,2.8707504,1.0287075,5.0704412,0.101175666,-85.21126,-183.37729,0.9574064,-0.86672467,37.917656,1130000
48
+ 1.0,1.0,0.026824055,2.6824055,1.026824,1.0435574,-3.3623374,-81.97908,-173.04944,0.1972935,-0.34747654,11.707766,1135000
49
+ 1.0,0.9999472,0.028177004,2.8177004,1.0281242,1.2381729,2.0875747,-84.014915,-200.82948,0.23062298,-0.36132312,16.116007,1140000
50
+ 1.0,0.99999994,0.030739468,3.0739465,1.0307394,1.1379626,-3.102193,-85.76052,-183.31958,0.26464856,-0.30618578,16.696083,1145000
51
+ 1.0,1.0000001,0.026608583,2.6608584,1.0266087,1.5630172,-5.2428308,-77.30064,-197.94829,1.3816454,-1.4016742,31.04306,1150000
52
+ 1.0,0.99999994,0.028601598,2.8601599,1.0286015,1.2067604,-8.305926,-85.66723,-192.30235,0.15247226,-0.30881658,14.917528,1155000
53
+ 1.0,1.0,0.027730552,2.7730553,1.0277306,1.2100285,1.5486658,-84.775894,-187.52283,0.19525658,-0.2130683,13.438185,1160000
54
+ 1.0,0.99999994,0.030234134,3.0234132,1.0302341,1.9247525,-2.231932,-82.900536,-203.25027,0.3343602,-0.5255017,25.568615,1165000
55
+ 1.0,1.0,0.029333238,2.9333239,1.0293332,3.214651,-4.978823,-84.132065,-168.7561,0.7555856,-0.5240155,34.27971,1170000
56
+ 1.0,0.99999994,0.026571466,2.6571465,1.0265714,9.010109,-2.597143,-82.03487,-202.71384,1.3037263,-1.3917344,66.74686,1175000
57
+ 1.0,1.0,0.028228283,2.8228283,1.0282283,0.98285526,-4.916829,-83.498024,-164.46071,0.3241868,-0.12517382,13.446921,1180000
58
+ 1.0,0.9999999,0.027618969,2.7618968,1.0276189,1.0414747,-2.7659104,-79.24111,-169.5334,0.28159875,-0.13623811,14.665682,1185000
59
+ 1.0,0.99999994,0.028225007,2.8225007,1.028225,1.3152599,-2.678369,-78.46537,-200.70288,0.20576479,-0.24606535,17.855694,1190000
60
+ 1.0,1.0,0.02711659,2.7116592,1.0271165,1.4706349,0.36656433,-80.29763,-181.56882,0.29066527,-0.24045637,18.584057,1195000
61
+ 1.0,1.0,0.026951516,2.6951518,1.0269516,0.94928676,-3.7228186,-81.81735,-164.7382,0.20838371,-0.19114566,12.983607,1200000
62
+ 1.0,1.0,0.03139618,3.1396184,1.0313962,1.3127297,-0.8315287,-82.08982,-183.21342,0.24974258,-0.31796193,17.036703,1205000
63
+ 1.0,0.99999994,0.029804923,2.9804924,1.0298048,2.4433773,-4.051466,-80.32904,-188.3796,0.63187367,-0.7085147,34.983303,1210000
64
+ 1.0,0.99999994,0.02791384,2.7913842,1.0279138,1.024804,0.8167348,-78.57224,-157.89821,0.25830424,-0.26376027,15.553793,1215000
65
+ 1.0,0.99999994,0.029500565,2.9500566,1.0295005,1.3349024,-5.820112,-80.75002,-172.56682,0.26681584,-0.2636851,15.496218,1220000
66
+ 1.0,1.0000001,0.029223073,2.9223075,1.0292232,0.9090977,-3.293055,-80.81467,-184.7794,0.16814318,-0.22270262,12.011722,1225000
67
+ 1.0,1.0,0.028913036,2.8913035,1.028913,1.859127,-3.7516217,-77.540794,-188.82686,0.430294,-0.2223491,20.199364,1230000
68
+ 1.0,1.0,0.028785903,2.8785906,1.028786,1.0773613,-1.9983146,-79.71222,-202.04149,0.27059162,-0.2556342,14.837778,1235000
69
+ 1.0,1.0,0.029793505,2.9793506,1.0297935,0.8958626,-4.7826033,-80.96465,-167.61488,0.14616752,-0.3116796,12.185198,1240000
70
+ 1.0,1.0,0.028746825,2.8746824,1.0287468,1.1145933,0.43620056,-83.30967,-196.66508,0.36132383,-0.2876523,18.547264,1245000
71
+ 1.0,1.0,0.026743228,2.6743226,1.0267432,1.2905113,-1.9251771,-77.74054,-192.59384,0.5373203,-0.61268014,21.319454,1250000
72
+ 1.0,1.0,0.028281126,2.8281126,1.0282811,3.0538056,0.014931917,-82.04868,-176.16594,1.1892562,-0.7709799,66.87318,1255000
73
+ 1.0,1.0000001,0.028110914,2.8110914,1.028111,1.5377945,-0.2971983,-79.02608,-201.7635,0.51195395,-0.471603,24.971016,1260000
74
+ 1.0,0.99999994,0.028460978,2.846098,1.0284609,0.7904707,-2.925911,-78.41892,-188.12566,0.114033975,-0.4123639,12.115517,1265000
75
+ 1.0,0.99999994,0.027354915,2.7354915,1.0273548,1.4379128,0.28550562,-76.72317,-183.14207,0.20621975,-0.2535996,15.047097,1270000
76
+ 1.0,1.0,0.028524064,2.8524065,1.028524,0.84561807,1.0294863,-77.349396,-201.02394,0.1385741,-0.13816977,11.57492,1275000
77
+ 1.0,1.0000001,0.0275786,2.7578602,1.0275787,1.415048,-3.8571825,-78.5584,-181.06924,0.1850233,-0.42610422,20.08408,1280000
78
+ 1.0,1.0,0.02980528,2.980528,1.0298053,1.1383162,-2.8606791,-77.84904,-187.25366,0.19075656,-0.19589296,13.955799,1285000
79
+ 1.0,1.0,0.029901486,2.9901485,1.0299015,1.2638752,0.943194,-78.70779,-184.5411,0.4109637,-0.6259148,26.411556,1290000
80
+ 1.0,1.0,0.029329473,2.9329472,1.0293294,1.3011326,6.526713,-80.41529,-162.09027,0.38391218,-0.55301976,14.758926,1295000
81
+ 1.0,1.0000001,0.02846408,2.846408,1.0284642,1.3934034,-2.1306474,-75.349846,-165.9608,0.34779346,-0.25506634,17.013273,1300000
82
+ 1.0,1.0,0.029871311,2.987131,1.0298713,1.4905754,-1.6062323,-77.98921,-181.79216,0.40857217,-0.22106129,20.591362,1305000
83
+ 1.0,0.99999994,0.030010791,3.0010793,1.0300107,0.95384425,-0.5266844,-77.16654,-153.92555,0.20173113,-0.23947498,12.545654,1310000
84
+ 1.0,0.9999999,0.026237216,2.6237216,1.0262371,1.4329952,-2.477703,-75.56842,-157.56221,0.51096934,-0.46920708,17.93782,1315000
85
+ 1.0,1.0,0.030138211,3.0138214,1.0301383,0.8076052,-3.9851255,-73.53954,-171.60512,0.45445016,-0.46856308,12.3631,1320000
86
+ 1.0,1.0,0.027940266,2.7940264,1.0279403,1.1584053,-0.07167959,-74.60439,-197.28653,0.36894947,-0.44055378,21.240337,1325000
87
+ 1.0,1.0,0.030116037,3.0116038,1.0301161,1.1903017,-1.3039125,-75.06168,-167.99774,0.31829566,-0.21028537,15.890092,1330000
88
+ 1.0,1.0,0.031060662,3.1060667,1.0310607,0.97415733,-1.5535127,-76.94234,-200.04031,0.4276281,-0.15933095,17.696495,1335000
89
+ 1.0,0.9999999,0.03111158,3.1111581,1.0311115,2.1323586,-0.25353643,-75.35097,-182.87444,0.5926424,-0.19350505,23.667484,1340000
90
+ 1.0,0.9999999,0.029570527,2.9570527,1.0295705,1.1654218,-1.8433166,-77.53863,-160.60576,0.34727174,-0.30091202,16.252516,1345000
91
+ 1.0,1.0,0.028332973,2.8332973,1.028333,1.5124791,1.1933526,-73.47881,-162.33363,1.772752,-2.0131493,40.953243,1350000
92
+ 1.0,1.0,0.03007796,3.0077963,1.0300779,1.0116196,-0.49753708,-75.11541,-168.14825,0.20203005,-0.25363898,11.83728,1355000
93
+ 1.0,1.0,0.027256796,2.7256794,1.0272568,0.9287359,-1.2451317,-72.788635,-168.56929,0.17578976,-0.27870446,13.096105,1360000
94
+ 1.0,1.0,0.030417904,3.0417905,1.0304179,1.1437315,-2.358684,-74.5594,-170.42339,0.53443897,-0.49766615,15.305337,1365000
95
+ 1.0,1.0,0.028267685,2.8267689,1.0282677,1.5121464,-1.8089867,-69.44217,-154.34149,0.34207103,-0.18506536,17.252632,1370000
96
+ 1.0,0.99999994,0.02879256,2.879256,1.0287925,0.98702335,-1.7762525,-74.319016,-183.70457,0.27320552,-0.28506896,14.940676,1375000
97
+ 1.0,0.9999999,0.030325929,3.0325928,1.0303258,1.232828,1.353568,-72.44436,-185.58101,0.20255044,-0.33325806,13.22139,1380000
98
+ 1.0,0.9999999,0.030503355,3.0503356,1.0305033,1.2561748,-1.7564313,-74.32138,-197.5193,0.45278478,-0.13881958,15.886172,1385000
99
+ 1.0,1.0,0.028314553,2.8314555,1.0283146,0.98733515,-4.062499,-73.7098,-172.99748,0.21143943,-0.5229739,15.399714,1390000
100
+ 1.0,1.0,0.028110597,2.8110597,1.0281106,1.367649,4.672265,-70.001366,-175.627,0.4869478,-0.4364121,20.140583,1395000
101
+ 1.0,1.0,0.029480577,2.948058,1.0294806,1.2452204,-1.1892135,-69.23844,-177.48293,0.49569583,-0.41975626,21.073853,1400000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:492eb8d6b9bc4e40c368fbd230a8dfc4b5908a3fba00b8b5ac19f62d73d8a289
3
+ size 217655954
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1050000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d755f2ed51976a24809a29ae05dbbb6bfec8b341a61a37ed1990a6ff0582223
3
+ size 217655954
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466edd596c6de98b88291b0f98d73906a1aef7c36b01d53c1bf8e745ca5c10ed
3
+ size 217655954
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be91fe8e3dba677bfa6672b51727ae9d320d172db4709e0770db9d03679e4d4f
3
+ size 217655954
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd227e788fbafed7c495bd50ef74b3d0dc5dbb13142ad42f64fcf05ac81a8631
3
+ size 217655954
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1250000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a570f974022e674bae9001871ce0955ad9288cc14dcae509778f63af229f4618
3
+ size 217655954
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1300000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6969bf08d7ad2e2f75d7ce3631f2ff786c756a0ab1eae87186bc859457cf2bea
3
+ size 217655954
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1350000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ac5d88e22572dd931ed65cc810855a27cf449b5af9f74e6742cc549d8efcec5
3
+ size 217655954
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_1400000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c71dd9a25a8c0fc7ce15a754f7cfd8dc7f6641a29431d56cae8f8949a2864066
3
+ size 217655954
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ff10feb22fd789cb7a6dc136475dd671b09bb6deab35b6b8b58a660c75b1680
3
+ size 217655954
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/rebrac/20260311_194404/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/ioms1cgx