default_settings:
  trainer_type: ppo
  hyperparameters:
    batch_size: 16
    buffer_size: 120
    learning_rate: 0.0003
    beta: 0.005
    epsilon: 0.2
    lambd: 0.99
    num_epoch: 3
    learning_rate_schedule: constant
  network_settings:
    normalize: true
    hidden_units: 256
    num_layers: 4
    vis_encode_type: match3
  reward_signals:
    extrinsic:
      gamma: 0.99
      strength: 1.0
  keep_checkpoints: 5
  max_steps: 5000000
  time_horizon: 128
  summary_freq: 10000

behaviors:
  Match3SimpleHeuristic:
    # Settings can be very simple since we don't care about actually training the model
    trainer_type: ppo
    hyperparameters:
      batch_size: 16
      buffer_size: 120
    network_settings:
      hidden_units: 4
      num_layers: 1
    max_steps: 5000000
    summary_freq: 10000
  Match3SmartHeuristic:
    # Settings can be very simple since we don't care about actually training the model
    trainer_type: ppo
    hyperparameters:
      batch_size: 16
      buffer_size: 120
    network_settings:
      hidden_units: 4
      num_layers: 1
    max_steps: 5000000
    summary_freq: 10000