behaviors:
  Crawler:
    trainer_type: ppo
    hyperparameters:
      batch_size: 2024
      buffer_size: 20240
      learning_rate: 0.0003
      beta: 0.005
      epsilon: 0.2
      lambd: 0.95
      num_epoch: 3
      learning_rate_schedule: linear
    network_settings:
      normalize: true
      hidden_units: 512
      num_layers: 3
      vis_encode_type: simple
    reward_signals:
      gail:
        gamma: 0.99
        strength: 1.0
        network_settings:
          normalize: true
          hidden_units: 128
          num_layers: 2
          vis_encode_type: simple
        learning_rate: 0.0003
        use_actions: false
        use_vail: false
        demo_path: Project/Assets/ML-Agents/Examples/Crawler/Demos/ExpertCrawler.demo
    keep_checkpoints: 5
    max_steps: 10000000
    time_horizon: 1000
    summary_freq: 30000
    threaded: true
    behavioral_cloning:
      demo_path: Project/Assets/ML-Agents/Examples/Crawler/Demos/ExpertCrawler.demo
      steps: 50000
      strength: 0.5
      samples_per_update: 0