Hugging Face's logo

miki030
/
poca-SoccerTwos-v3

Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
poca-SoccerTwos-v3
File size: 2,012 Bytes 
cf3f411
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ec606a4
cf3f411
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ec606a4
cf3f411
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ec606a4
 
cf3f411
 
 
 
 
 
 
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
 
default_settings: null
behaviors:
  SoccerTwos:
    trainer_type: poca
    hyperparameters:
      batch_size: 2048
      buffer_size: 20480
      learning_rate: 0.0003
      beta: 0.005
      epsilon: 0.2
      lambd: 0.95
      num_epoch: 3
      learning_rate_schedule: constant
      beta_schedule: constant
      epsilon_schedule: constant
    checkpoint_interval: 500000
    network_settings:
      normalize: true
      hidden_units: 1024
      num_layers: 24
      vis_encode_type: resnet
      memory:
        sequence_length: 128
        memory_size: 512
      goal_conditioning_type: hyper
      deterministic: false
    reward_signals:
      extrinsic:
        gamma: 0.999
        strength: 1.0
        network_settings:
          normalize: true
          hidden_units: 1024
          num_layers: 12
          vis_encode_type: resnet
          memory:
            sequence_length: 128
            memory_size: 512
          goal_conditioning_type: hyper
          deterministic: false
    init_path: null
    keep_checkpoints: 10
    even_checkpoints: false
    max_steps: 15000000
    time_horizon: 1000
    summary_freq: 10000
    threaded: false
    self_play:
      save_steps: 10000
      team_change: 50000
      swap_steps: 1000
      window: 100
      play_against_latest_model_ratio: 0.5
      initial_elo: 1200.0
    behavioral_cloning: null
env_settings:
  env_path: ./training-envs-executables/SoccerTwos/SoccerTwos.exe
  env_args: null
  base_port: 5005
  num_envs: 1
  num_areas: 1
  seed: -1
  max_lifetime_restarts: 10
  restarts_rate_limit_n: 1
  restarts_rate_limit_period_s: 60
engine_settings:
  width: 84
  height: 84
  quality_level: 5
  time_scale: 20
  target_frame_rate: -1
  capture_frame_rate: 60
  no_graphics: true
environment_parameters: null
checkpoint_settings:
  run_id: SoccerTwos-v3
  initialize_from: null
  load_model: false
  resume: true
  force: false
  train_model: false
  inference: false
  results_dir: results
torch_settings:
  device: null
debug: false