behaviors:
  Pyramids:
    trainer_type: sac
    hyperparameters:
      learning_rate: 0.0003
      learning_rate_schedule: constant
      batch_size: 128
      buffer_size: 2000000
      buffer_init_steps: 1000
      tau: 0.01
      steps_per_update: 10.0
      save_replay_buffer: false
      init_entcoef: 0.01
      reward_signal_steps_per_update: 10.0
    network_settings:
      normalize: false
      hidden_units: 512
      num_layers: 3
      vis_encode_type: simple
    reward_signals:
      extrinsic:
        gamma: 0.995
        strength: 2.0
      gail:
        gamma: 0.99
        strength: 0.01
        learning_rate: 0.0003
        use_actions: true
        use_vail: false
        demo_path: Project/Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo
    keep_checkpoints: 5
    max_steps: 3000000
    time_horizon: 128
    summary_freq: 30000
    threaded: true