push block transfer setting

config/sac_transfer/ReacherTransfer.yaml

       action_feature_size: 16
       separate_policy_train: true
       separate_policy_net: true
-      separate_model_train: true
       reuse_encoder: true
       in_epoch_alter: false
       in_batch_alter: true
       train_model: false
       load_action: true
       train_action: false
-      transfer_path: "results/reacher/Reacher"
+      transfer_path: "results/sacmod_reacher_f64_e2v2/Reacher"
     network_settings:
       normalize: true
       hidden_units: 128

config/sac_transfer/PushBlockTransfer.yaml

+behaviors:
+  PushBlock:
+    trainer_type: sac_transfer
+    hyperparameters:
+      learning_rate: 0.0003
+      learning_rate_schedule: constant
+      batch_size: 128
+      buffer_size: 50000
+      buffer_init_steps: 0
+      tau: 0.005
+      steps_per_update: 10.0
+      save_replay_buffer: false
+      init_entcoef: 0.05
+      reward_signal_steps_per_update: 10.0
+      encoder_layers: 2
+      policy_layers: 2
+      forward_layers: 0
+      value_layers: 2
+      action_layers: 2
+      feature_size: 128
+      action_feature_size: 64
+      separate_policy_train: true
+      separate_policy_net: true
+      reuse_encoder: true
+      in_epoch_alter: false
+      in_batch_alter: true
+      use_op_buffer: false
+      use_var_predict: true
+      with_prior: false
+      predict_return: true
+      use_bisim: false
+      use_transfer: true
+      load_model: true
+      train_model: false
+      load_action: true
+      train_action: false
+      transfer_path: "results/block/PushBlock"
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 2000000
+    time_horizon: 64
+    summary_freq: 100000
+    threaded: true