add configs

config/ppo/CrawlerDynamic.yaml

   CrawlerDynamic:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 2024
-      buffer_size: 20240
+      batch_size: 2048
+      buffer_size: 20480
       learning_rate: 0.0003
       beta: 0.005
       epsilon: 0.2

config/ppo/CrawlerDynamic10240.yaml

+behaviors:
+  CrawlerDynamic:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 10240
+      buffer_size: 102400
+      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
+    keep_checkpoints: 5
+    max_steps: 15000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: true

config/ppo/CrawlerDynamic4096.yaml

+behaviors:
+  CrawlerDynamic:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 4096
+      buffer_size: 40960
+      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
+    keep_checkpoints: 5
+    max_steps: 15000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: true

config/ppo/CrawlerDynamic8192.yaml

+behaviors:
+  CrawlerDynamic:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 8192
+      buffer_size: 81920
+      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
+    keep_checkpoints: 5
+    max_steps: 15000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: true