default:
    trainer: ppo
    batch_size: 32
    beta: 5.0e-3
    buffer_size: 512
    epsilon: 0.2
    gamma: 0.99
    hidden_units: 128
    lambd: 0.95
    learning_rate: 3.0e-4
    max_steps: 5.0e4
    normalize: true
    num_epoch: 5
    num_layers: 2
    time_horizon: 64
    sequence_length: 64
    summary_freq: 1000
    use_recurrent: false

Ball3DBrain:
    summary_freq: 1000
    normalize: true
    batch_size: 1000
    buffer_size: 10000 
    hidden_units: 64
    max_steps: 1.0e4

GridWorldBrain:
    batch_size: 32
    num_layers: 1
    hidden_units: 256
    beta: 5.0e-3
    gamma: 0.9
    buffer_size: 256
    max_steps: 5.0e5
    summary_freq: 2000
    time_horizon: 5

StudentBrain:
    trainer: imitation
    max_steps: 10000
    summary_freq: 1000
    brain_to_imitate: ExpertBrain
    batch_size: 16
    batches_per_epoch: 10
    num_layers: 4
    hidden_units: 64
    use_recurrent: false
    sequence_length: 16
    buffer_size: 128