default:
    trainer: ppo
    batch_size: 1024
    beta: 5.0e-3
    buffer_size: 10240
    epsilon: 0.2
    hidden_units: 128
    lambd: 0.95
    learning_rate: 3.0e-4
    max_steps: 5.0e4
    memory_size: 256
    normalize: false
    num_epoch: 3
    num_layers: 2
    time_horizon: 64
    sequence_length: 64
    summary_freq: 1000
    use_recurrent: false
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.99

Pyramids:
    summary_freq: 2000
    time_horizon: 128
    batch_size: 128
    buffer_size: 2048
    hidden_units: 512
    num_layers: 2
    beta: 1.0e-2
    max_steps: 5.0e5
    num_epoch: 3
    behavioral_cloning:
        demo_path: demos/ExpertPyramid.demo
        strength: 0.5
        steps: 10000
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.99
        curiosity:
            strength: 0.02
            gamma: 0.99
            encoding_size: 256
        gail:
            strength: 0.01
            gamma: 0.99
            encoding_size: 128
            demo_path: demos/ExpertPyramid.demo

CrawlerStatic:
    normalize: true
    num_epoch: 3
    time_horizon: 1000
    batch_size: 2024
    buffer_size: 20240
    max_steps: 1e6
    summary_freq: 3000
    num_layers: 3
    hidden_units: 512
    behavioral_cloning:
        demo_path: demos/ExpertCrawlerSta.demo
        strength: 0.5
        steps: 5000
    reward_signals:
        gail:
            strength: 1.0
            gamma: 0.99
            encoding_size: 128
            demo_path: demos/ExpertCrawlerSta.demo

PushBlock:
    max_steps: 5.0e4
    batch_size: 128
    buffer_size: 2048
    beta: 1.0e-2
    hidden_units: 256
    summary_freq: 2000
    time_horizon: 64
    num_layers: 2
    reward_signals:
        gail:
            strength: 1.0
            gamma: 0.99
            encoding_size: 128
            demo_path: demos/ExpertPush.demo

Hallway:
    use_recurrent: true
    sequence_length: 64
    num_layers: 2
    hidden_units: 128
    memory_size: 256
    beta: 1.0e-2
    num_epoch: 3
    buffer_size: 1024
    batch_size: 128
    max_steps: 5.0e5
    summary_freq: 1000
    time_horizon: 64
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.99
        gail:
            strength: 0.1
            gamma: 0.99
            encoding_size: 128
            demo_path: demos/ExpertHallway.demo

FoodCollector:
    batch_size: 64
    summary_freq: 1000
    max_steps: 5.0e4
    use_recurrent: false
    hidden_units: 128
    learning_rate: 3.0e-4
    num_layers: 2
    sequence_length: 32
    reward_signals:
        gail:
            strength: 0.1
            gamma: 0.99
            encoding_size: 128
            demo_path: demos/ExpertFood.demo
    behavioral_cloning:
        demo_path: demos/ExpertFood.demo
        strength: 1.0
        steps: 0