behaviors:
  PushBlock:
    trainer: ppo
    batch_size: 128
    beta: 0.01
    buffer_size: 2048
    epsilon: 0.2
    hidden_units: 256
    lambd: 0.95
    learning_rate: 0.0003
    max_steps: 1.5e7
    memory_size: 256
    normalize: false
    num_epoch: 3
    num_layers: 2
    time_horizon: 64
    sequence_length: 64
    summary_freq: 60000
    use_recurrent: false
    reward_signals:
      gail:
        strength: 1.0
        gamma: 0.99
        encoding_size: 128
        demo_path: Project/Assets/ML-Agents/Examples/PushBlock/Demos/ExpertPush.demo