bird.yaml

behaviors:
  bird:
    trainer_type: ppo
    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: linear
    network_settings:
      normalize: true
      hidden_units: 512
      num_layers: 3
      vis_encode_type: simple
    reward_signals:
      extrinsic:
        gamma: 0.8
        strength: 1.0
    keep_checkpoints: 5
    max_steps: 10000000
    time_horizon: 1000
    summary_freq: 30000
    threaded: true
#environment_parameters:
  #lesson:
    #curriculum:
      #- name: Lesson1 # Sin obstaculos
        #completion_criteria:
          #measure: progress
          #behavior: bird
          #signal_smoothing: true
          #min_lesson_length: 100
          #threshold: 0.5
        #value: 0.0  
      #- name: Lesson2 # Con obstaculos
        #value: 1.0