Second Push

.gitattributes

@@ -49,10 +49,13 @@ com.unity.ml-agents/Tests/Editor/TestModels/hybrid0vis53vec_3c_2daction_v1_0.onn
 com.unity.ml-agents/Tests/Editor/TestModels/hybrid0vis8vec_2c_2_3d_v2_0.onnx filter=lfs diff=lfs merge=lfs -text
 docs/images/image-banner.png filter=lfs diff=lfs merge=lfs -text
 localized_docs/KR/docs/images/image-banner.png filter=lfs diff=lfs merge=lfs -text
-results/Pyramids[[:space:]]Training/Pyramids/Pyramids-100064.onnx filter=lfs diff=lfs merge=lfs -text
-results/Pyramids[[:space:]]Training/Pyramids/Pyramids-100064.pt filter=lfs diff=lfs merge=lfs -text
+results/Pyramids[[:space:]]Training/Pyramids/Pyramids-1000115.onnx filter=lfs diff=lfs merge=lfs -text
+results/Pyramids[[:space:]]Training/Pyramids/Pyramids-1000115.pt filter=lfs diff=lfs merge=lfs -text
+results/Pyramids[[:space:]]Training/Pyramids/Pyramids-499967.onnx filter=lfs diff=lfs merge=lfs -text
+results/Pyramids[[:space:]]Training/Pyramids/Pyramids-499967.pt filter=lfs diff=lfs merge=lfs -text
+results/Pyramids[[:space:]]Training/Pyramids/Pyramids-999987.onnx filter=lfs diff=lfs merge=lfs -text
+results/Pyramids[[:space:]]Training/Pyramids/Pyramids-999987.pt filter=lfs diff=lfs merge=lfs -text
 results/Pyramids[[:space:]]Training/Pyramids/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-results/Pyramids[[:space:]]Training/Pyramids/events.out.tfevents.1692804545.f1fcbdb9d0a8.1697.0 filter=lfs diff=lfs merge=lfs -text
 results/Pyramids[[:space:]]Training/Pyramids.onnx filter=lfs diff=lfs merge=lfs -text
 training-envs-executables/linux/Pyramids/Pyramids_Data/Managed/System.Core.dll filter=lfs diff=lfs merge=lfs -text
 training-envs-executables/linux/Pyramids/Pyramids_Data/Managed/System.Data.dll filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1 +1 @@
-{"behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple"}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"hidden_units": 64, "num_layers": 3}, "learning_rate": 0.0001}}, "keep_checkpoints": 5, "max_steps": 100000, "time_horizon": 128, "summary_freq": 30000}}}
+{"behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple"}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"hidden_units": 64, "num_layers": 3}, "learning_rate": 0.0001}}, "keep_checkpoints": 5, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000}}}

config/ppo/PyramidsRND.yaml

@@ -27,6 +27,6 @@ behaviors:
           num_layers: 3
         learning_rate: 0.0001
     keep_checkpoints: 5
-    max_steps: 100000
+    max_steps: 1000000
     time_horizon: 128
     summary_freq: 30000

configuration.yaml

@@ -27,6 +27,6 @@ behaviors:
           num_layers: 3
         learning_rate: 0.0001
     keep_checkpoints: 5
-    max_steps: 100000
+    max_steps: 1000000
     time_horizon: 128
     summary_freq: 30000