update configs

config/ppo/PushBlock.yaml

   PushBlock:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 128
-      buffer_size: 2048
+      batch_size: 512
+      buffer_size: 10240
-      beta: 0.001
+      beta: 0.01
-      learning_rate_schedule: linear
+      learning_rate_schedule: constant
     network_settings:
       normalize: false
       hidden_units: 256

config/ppo/Zombie.yaml

       learning_rate: 0.0003
       beta: 0.01
       epsilon: 0.2
-      lambd: 0.95
+      lambd: 1.0
       num_epoch: 3
       learning_rate_schedule: constant
     network_settings: