Hugging Face's logo

LeCAR-Lab
/
BFM-Zero

ONNX
Safetensors
Model card Files
xet
 Community
BFM-Zero
File size: 3,807 Bytes
ad16c0e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
134
{
    "name": "FBcprAuxModel",
    "device": "cuda",
    "archi": {
        "name": "FBcprAuxModelArchiConfig",
        "z_dim": 256,
        "norm_z": true,
        "f": {
            "name": "ForwardArchi",
            "hidden_dim": 2048,
            "model": "residual",
            "hidden_layers": 6,
            "embedding_layers": 2,
            "num_parallel": 2,
            "ensemble_mode": "batch",
            "input_filter": {
                "name": "DictInputFilterConfig",
                "key": [
                    "state",
                    "privileged_state",
                    "last_action",
                    "history_actor"
                ]
            }
        },
        "b": {
            "name": "BackwardArchi",
            "hidden_dim": 256,
            "hidden_layers": 1,
            "norm": true,
            "input_filter": {
                "name": "DictInputFilterConfig",
                "key": [
                    "state",
                    "privileged_state"
                ]
            }
        },
        "actor": {
            "name": "actor",
            "model": "residual",
            "hidden_dim": 2048,
            "hidden_layers": 6,
            "embedding_layers": 2,
            "input_filter": {
                "name": "DictInputFilterConfig",
                "key": [
                    "state",
                    "last_action",
                    "history_actor"
                ]
            }
        },
        "critic": {
            "name": "ForwardArchi",
            "hidden_dim": 2048,
            "model": "residual",
            "hidden_layers": 6,
            "embedding_layers": 2,
            "num_parallel": 2,
            "ensemble_mode": "batch",
            "input_filter": {
                "name": "DictInputFilterConfig",
                "key": [
                    "state",
                    "privileged_state",
                    "last_action",
                    "history_actor"
                ]
            }
        },
        "discriminator": {
            "name": "DiscriminatorArchi",
            "hidden_dim": 1024,
            "hidden_layers": 3,
            "input_filter": {
                "name": "DictInputFilterConfig",
                "key": [
                    "state",
                    "privileged_state"
                ]
            }
        },
        "aux_critic": {
            "name": "ForwardArchi",
            "hidden_dim": 2048,
            "model": "residual",
            "hidden_layers": 6,
            "embedding_layers": 2,
            "num_parallel": 2,
            "ensemble_mode": "batch",
            "input_filter": {
                "name": "DictInputFilterConfig",
                "key": [
                    "state",
                    "privileged_state",
                    "last_action",
                    "history_actor"
                ]
            }
        }
    },
    "obs_normalizer": {
        "name": "ObsNormalizerConfig",
        "normalizers": {
            "state": {
                "name": "BatchNormNormalizerConfig",
                "momentum": 0.01
            },
            "privileged_state": {
                "name": "BatchNormNormalizerConfig",
                "momentum": 0.01
            },
            "last_action": {
                "name": "BatchNormNormalizerConfig",
                "momentum": 0.01
            },
            "history_actor": {
                "name": "BatchNormNormalizerConfig",
                "momentum": 0.01
            }
        },
        "allow_mismatching_keys": true
    },
    "inference_batch_size": 500000,
    "seq_length": 8,
    "actor_std": 0.05,
    "amp": false,
    "norm_aux_reward": {
        "name": "RewardNormalizer",
        "translate": false,
        "scale": true
    }
}