Hugging Face's logo

RLinf
/
RLinf-OpenVLAOFT-GRPO-ManiSkill3-25ood

Reinforcement Learning
Safetensors
English
openvla
RLinf
custom_code
Eval Results
Model card Files
xet
Community
2
RLinf-OpenVLAOFT-GRPO-ManiSkill3-25ood
File size: 2,975 Bytes 
b9c622a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
 
{
  "libero_10_no_noops": {
    "action": {
      "mean": [
        0.01820324920117855,
        0.05858374014496803,
        -0.05592384561896324,
        0.004626928828656673,
        0.00289608770981431,
        -0.007673131301999092,
        0.5457824468612671
      ],
      "std": [
        0.2825464606285095,
        0.35904666781425476,
        0.3673802614212036,
        0.03770702704787254,
        0.05429719388484955,
        0.08725254982709885,
        0.49815231561660767
      ],
      "max": [
        0.9375,
        0.9375,
        0.9375,
        0.30000001192092896,
        0.29357144236564636,
        0.375,
        1.0
      ],
      "min": [
        -0.9375,
        -0.9375,
        -0.9375,
        -0.23642857372760773,
        -0.3053571283817291,
        -0.3675000071525574,
        0.0
      ],
      "q01": [
        -0.6348214149475098,
        -0.7741071581840515,
        -0.7633928656578064,
        -0.09749999642372131,
        -0.14819999992847435,
        -0.2742857038974762,
        0.0
      ],
      "q99": [
        0.7714285850524902,
        0.8464285731315613,
        0.9375,
        0.13928571343421936,
        0.15964286029338837,
        0.3246428668498993,
        1.0
      ],
      "mask": [
        true,
        true,
        true,
        true,
        true,
        true,
        false
      ]
    },
    "proprio": {
      "mean": [
        -0.04190658777952194,
        0.03539430722594261,
        0.8257141709327698,
        2.908308267593384,
        -0.5562185049057007,
        -0.16649018228054047,
        0.028316624462604523,
        -0.028561657294631004
      ],
      "std": [
        0.10743364691734314,
        0.14424669742584229,
        0.2572328448295593,
        0.3441362977027893,
        1.234421730041504,
        0.3579835891723633,
        0.013308707624673843,
        0.013174631632864475
      ],
      "max": [
        0.21031762659549713,
        0.39128610491752625,
        1.3332009315490723,
        3.6714255809783936,
        3.560650587081909,
        1.386339545249939,
        0.04160946607589722,
        0.0013633022317662835
      ],
      "min": [
        -0.4828203022480011,
        -0.3255046010017395,
        0.445506751537323,
        1.1321442127227783,
        -3.641430377960205,
        -1.842738389968872,
        -0.0010040868073701859,
        -0.04111652821302414
      ],
      "q01": [
        -0.3899900782108307,
        -0.2838300323486328,
        0.44795057058334353,
        1.8810229921340942,
        -2.886677579879761,
        -1.1599004411697387,
        0.002066459748893976,
        -0.04001387819647789
      ],
      "q99": [
        0.1530261474847791,
        0.32915401458740223,
        1.2546923208236693,
        3.303542451858519,
        2.7496529006957933,
        0.6893712210655194,
        0.040048558115959164,
        -0.0017598449345678235
      ]
    },
    "num_transitions": 101469,
    "num_trajectories": 379
  }
}