default: trainer: online_bc brain_to_imitate: batch_size: 64 time_horizon: 64 summary_freq: 1000 max_steps: 5.0e4 batches_per_epoch: 10 use_recurrent: false hidden_units: 128 learning_rate: 3.0e-4 num_layers: 2 sequence_length: 32 memory_size: 256 BananaLearning: trainer: online_bc max_steps: 10000 summary_freq: 1000 brain_to_imitate: BananaPlayer batch_size: 16 batches_per_epoch: 5 num_layers: 4 hidden_units: 64 use_recurrent: false sequence_length: 16 BouncerLearning: trainer: online_bc max_steps: 10000 summary_freq: 10 brain_to_imitate: BouncerPlayer batch_size: 16 batches_per_epoch: 1 num_layers: 1 hidden_units: 64 use_recurrent: false sequence_length: 16 HallwayLearning: trainer: online_bc max_steps: 10000 summary_freq: 1000 brain_to_imitate: HallwayPlayer batch_size: 16 batches_per_epoch: 5 num_layers: 4 hidden_units: 64 use_recurrent: false sequence_length: 16 PushBlockLearning: trainer: online_bc max_steps: 10000 summary_freq: 1000 brain_to_imitate: PushBlockPlayer batch_size: 16 batches_per_epoch: 5 num_layers: 4 hidden_units: 64 use_recurrent: false sequence_length: 16 PyramidsLearning: trainer: online_bc max_steps: 10000 summary_freq: 1000 brain_to_imitate: PyramidsPlayer batch_size: 16 batches_per_epoch: 5 num_layers: 4 hidden_units: 64 use_recurrent: false sequence_length: 16 TennisLearning: trainer: online_bc max_steps: 10000 summary_freq: 1000 brain_to_imitate: TennisPlayer batch_size: 16 batches_per_epoch: 5 num_layers: 4 hidden_units: 64 use_recurrent: false sequence_length: 16 StudentBrain: trainer: online_bc max_steps: 10000 summary_freq: 1000 brain_to_imitate: TeacherBrain batch_size: 16 batches_per_epoch: 5 num_layers: 4 hidden_units: 64 use_recurrent: false sequence_length: 16 StudentRecurrentBrain: trainer: online_bc max_steps: 10000 summary_freq: 1000 brain_to_imitate: TeacherBrain batch_size: 16 batches_per_epoch: 5 num_layers: 4 hidden_units: 64 use_recurrent: true sequence_length: 32