# TouchCube:
#     trainer: sac
#     hyperparameters:
#     batch_size: 128
#     buffer_size: 50000
#     buffer_init_steps: 0
#     hidden_units: 128
#     init_entcoef: 1.0
#     learning_rate: 3.0e-4
#     learning_rate_schedule: constant
#     max_steps: 5.0e5
#     memory_size: 128
#     normalize: false
#     num_update: 1
#     train_interval: 1
#     steps_per_update: 1
#     num_layers: 2
#     time_horizon: 64
#     sequence_length: 64
#     summary_freq: 5000
#     tau: 0.005
#     use_recurrent: false
#     vis_encode_type: simple
#     reward_signals:
#         extrinsic:
#             strength: 1.0
#             gamma: 0.95
behaviors:
  TouchCube:
    trainer_type: ppo
    hyperparameters:
      batch_size: 512 #2048
      buffer_size: 5120 #20480
      learning_rate: 0.0003
      beta: 0.005
      epsilon: 0.2
      lambd: 0.95
      num_epoch: 3
      learning_rate_schedule: linear
    network_settings:
      normalize: true
      hidden_units: 512
      num_layers: 3
      vis_encode_type: simple
    reward_signals:
      extrinsic:
        gamma: 0.995
        strength: 1.0
    output_path: default
    keep_checkpoints: 5
    max_steps: 20000000
    time_horizon: 500 #1000
    summary_freq: 30000
    threaded: true
# behaviors:
#   TouchCube:
#     trainer_type: sac
#     hyperparameters:
#       learning_rate: 0.0003
#       learning_rate_schedule: constant
#       batch_size: 256
#       buffer_size: 500000
#       buffer_init_steps: 0
#       tau: 0.005
#       steps_per_update: 30.0
#       save_replay_buffer: false
#       init_entcoef: 1.0
#       reward_signal_steps_per_update: 30.0
#     network_settings:
#       normalize: true
#       hidden_units: 512
#       num_layers: 4
#       vis_encode_type: simple
#     reward_signals:
#       extrinsic:
#         gamma: 0.995
#         strength: 1.0
#     output_path: default
#     keep_checkpoints: 5
#     max_steps: 20000000
#     time_horizon: 1000
#     summary_freq: 30000
#     threaded: true