Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
openfront-rl
File size: 1,390 Bytes
e0c179f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ab3e21d
 
e0c179f
 
 
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
{
  "format": "oftrain-safetensors",
  "manifest_schema_version": 1,
  "architecture": {
    "name": "oftrain-policy",
    "schema_version": 2,
    "dimensions": {
      "grid_channels": 89,
      "fine_grid_channels": 90,
      "player_features": 21,
      "scalars": 11,
      "local_planes": 5,
      "actions": 21,
      "build_types": 7,
      "nuke_types": 5,
      "quantity_params": 2,
      "grid_tower_channels": 256,
      "grid_tower_blocks": 4,
      "hidden": 512,
      "player_hidden": 128,
      "local_hidden": 64,
      "transformer_layers": 2,
      "attention_heads": 4
    },
    "recurrent": {
      "cell": "gru",
      "hidden_size": 256,
      "context_schema": "action-outcome-v1",
      "context_features": 14,
      "context_embedding": 128,
      "bptt_length": 16,
      "rollout_length": 32,
      "residual_initialization": "zero-output-projection",
      "hidden_reset_policy": "episode_done"
    }
  },
  "autoencoders": {
    "fine": {
      "ref": "../weights/ae/ae_v31_d8c32.encoder.safetensors",
      "format": "safetensors"
    },
    "coarse": {
      "ref": "../weights/ae/ae_v31_d16c32.encoder.safetensors",
      "format": "safetensors"
    }
  },
  "checkpoint": {
    "weights": "latest.safetensors",
    "state": "latest.state.json"
  },
  "update": 241,
  "stage": 6,
  "curriculum_schedule": "v8.3",
  "reward_profile": "v8.3-closeout-v1"
}