behaviors:
  Pyramids:
    trainer_type: ppo
    time_horizon: 128
    max_steps: 1.0e7
    hyperparameters:
      batch_size: 128
      beta: 0.01
      buffer_size: 2048
      epsilon: 0.2
      lambd: 0.95
      learning_rate: 0.0003
      num_epoch: 3
    network_settings:
      num_layers: 2
      normalize: false
      hidden_units: 512
    reward_signals:
      extrinsic:
        strength: 1.0
        gamma: 0.99
      curiosity:
        strength: 0.02
        gamma: 0.99
        network_settings:
          hidden_units: 256
      gail:
        strength: 0.01
        gamma: 0.99
        demo_path: Project/Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo
    behavioral_cloning:
      demo_path: Project/Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo
      strength: 0.5
      steps: 150000