First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b170b0883c3f1df267cd6ae2b964fcc4c4d06ca6828bede64219ecd4bb735b30
-size 2468409
+oid sha256:e5948dc4647959e04237e06ea935731983470b845e5e1ba52497dc1a20997095
+size 1417437

Pyramids/{Pyramids-1000119.onnx → Pyramids-1000028.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c987ee99077eced31dded3b23bac025125e491c742bbf88435f656aac5d865c9
-size 9128511
+oid sha256:e5948dc4647959e04237e06ea935731983470b845e5e1ba52497dc1a20997095
+size 1417437

Pyramids/{Pyramids-1499957.onnx → Pyramids-1000028.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b987b6dc44962f91af19f5a261a4794fcd4a3a93f5217ba6a6701ea343528c03
-size 9128511
+oid sha256:1bef324818f3fb3965abdf4a6e9ea41456f11d5aef63f32e92dc6b41aa7a2cf4
+size 8652382

Pyramids/Pyramids-1000119.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:649eceaaad4c2cc0124972d3e5182969a77977c24782b8a1e6ef59d19465a580
-size 54902362

Pyramids/Pyramids-1499935.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:042cea09bac907dae2faf14c72cc1e152d4171d6f47cec2f28b2c5af1eef5aee
-size 14960218

Pyramids/Pyramids-1499957.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7b2c3b372abf040a36084181171cc743b150c3fe36226bcd040437f38706296a
-size 54902362

Pyramids/Pyramids-1515793.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b85e76247107c4598e79b78af4ff17ecfd0889e168e49ab74486cb2de33a276d
-size 54902362

Pyramids/Pyramids-1999957.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b170b0883c3f1df267cd6ae2b964fcc4c4d06ca6828bede64219ecd4bb735b30
-size 2468409

Pyramids/Pyramids-1999957.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:19816295053302f783fa26f54368cbddfae57a3c0b6a529b45d67c8d356731a4
-size 14960218

Pyramids/Pyramids-2000085.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b170b0883c3f1df267cd6ae2b964fcc4c4d06ca6828bede64219ecd4bb735b30
-size 2468409

Pyramids/Pyramids-2000085.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e4b3d321eccd49ae2d04dc874f5cd163041585f45a90e576909a4e426bc675a6
-size 14960218

Pyramids/{Pyramids-1499935.onnx → Pyramids-499879.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c43a9fd706bc38d2e0495364447dd21acce8304bf15d843566cb577c70d046b4
-size 2468409
+oid sha256:3e50bb5e3c3c2dd3d8a593ea3e839996d957e2c65bbf4fbe52b692f08448506e
+size 1417437

Pyramids/{Pyramids-1515793.onnx → Pyramids-499879.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:030626ecc824eec004087274a2dccf9acebda1993f2a8934c2dfb03ab15fa2e9
-size 9128511
+oid sha256:a8a46b3323660bf64281e491d8e62e2ca165c2407aefa6be7ca4baebe87ddc15
+size 8652382

Pyramids/Pyramids-499975.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cc9089d9a752b0cc3568c998b3dc7e69ae03d83f124817fb4a9a3dda918440fd
-size 2468409

Pyramids/Pyramids-499975.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2888f588272126e2bf2a3536b5a06e023df495d607981d429e85d4eeba35e5cf
-size 14960218

Pyramids/Pyramids-999959.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5948dc4647959e04237e06ea935731983470b845e5e1ba52497dc1a20997095
+size 1417437

Pyramids/Pyramids-999959.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e388af6e6880e27a2b6cfd17aa88e53b3230ffa94d274b328e97caabbb74ca5
+size 8652382

Pyramids/Pyramids-999984.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f98ba09b90414b2092f4d0699bb3af16dad3534e8f73c743a186625a6adf8546
-size 2468409

Pyramids/Pyramids-999984.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:63ed3e810f9edae8e90520f7d2364d3a0c7f0d420b53f59226bc353ead668a7f
-size 14960218

Pyramids/Pyramids-999991.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c987ee99077eced31dded3b23bac025125e491c742bbf88435f656aac5d865c9
-size 9128511

Pyramids/Pyramids-999991.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:226d60d64d51ffaaef461622d4d6eb11227d19b0cb1a46a44f9d5fd75ad25095
-size 54902362

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b3d321eccd49ae2d04dc874f5cd163041585f45a90e576909a4e426bc675a6
-size 14960218
+oid sha256:1bef324818f3fb3965abdf4a6e9ea41456f11d5aef63f32e92dc6b41aa7a2cf4
+size 8652382

Pyramids/{events.out.tfevents.1673665142.701d88e6b6ff.19004.0 → events.out.tfevents.1673701999.e4526b1a626c.7046.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63594214b7bedec5b5161ea10cb9e046f415684f1733f5f8faf16731c806060
-size 619135
+oid sha256:c23b2a9c43e82cbb8dc79cb0dd95fc8fd4531c986abef17cca9b843fd9b07f6a
+size 333154

config.json

@@ -1 +1 @@
-{"default_settings": null, "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", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 2000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "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", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -16,7 +16,7 @@ behaviors:
     network_settings:
       normalize: false
       hidden_units: 512
-      num_layers: 3
+      num_layers: 2
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
@@ -49,7 +49,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 500000
-    max_steps: 2000000
+    max_steps: 1000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,9 +1,12 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55441 [Flags] 2 [Guid] 2484954069 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.2 [Port] 55430 [Flags] 2 [Guid] 2302582900 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -33,7 +36,7 @@ ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.086 seconds
+- Completed reload, in  0.085 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -65,7 +68,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.863739 ms
+UnloadTime: 0.849959 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -73,7 +76,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 4591 frames, [32.0 KB-64.0 KB]: 22415 frames, [64.0 KB-128.0 KB]: 10511 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2831 frames, [32.0 KB-64.0 KB]: 11918 frames, [64.0 KB-128.0 KB]: 4019 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -204,28 +207,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37219 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.5 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 11053
+  Peak main deferred allocation count 12215
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37517 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18768 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 28.9 MB
+      Peak Allocated memory 30.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 37518 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 24.3 MB
+      Peak Allocated memory 22.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -254,13 +257,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 37517 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 37518 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,13 +275,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37219 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 37517 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18768 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -290,19 +293,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 37518 frames
+      Peak usage frame count: [0-1.0 KB]: 18769 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 37518 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18769 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 37518 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18769 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -311,4 +314,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673670012436,"processId":19021,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673704170704,"processId":7067,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,189 +2,189 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.16722942888736725,
-            "min": 0.16722942888736725,
-            "max": 1.4317348003387451,
-            "count": 66
+            "value": 0.3197597563266754,
+            "min": 0.3197597563266754,
+            "max": 1.50977623462677,
+            "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 5014.20703125,
-            "min": 5014.20703125,
-            "max": 43433.10546875,
-            "count": 66
+            "value": 9587.6767578125,
+            "min": 9587.6767578125,
+            "max": 45800.5703125,
+            "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 1979943.0,
-            "min": 29952.0,
-            "max": 1979943.0,
-            "count": 66
+            "value": 989983.0,
+            "min": 29932.0,
+            "max": 989983.0,
+            "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 1979943.0,
-            "min": 29952.0,
-            "max": 1979943.0,
-            "count": 66
+            "value": 989983.0,
+            "min": 29932.0,
+            "max": 989983.0,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.8022924065589905,
-            "min": -0.10438932478427887,
-            "max": 0.8278008699417114,
-            "count": 66
+            "value": 0.7090317606925964,
+            "min": -0.1796794980764389,
+            "max": 0.7090317606925964,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 246.30377197265625,
-            "min": -24.740270614624023,
-            "max": 249.16806030273438,
-            "count": 66
+            "value": 201.36502075195312,
+            "min": -42.584041595458984,
+            "max": 201.36502075195312,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.005353621672838926,
-            "min": -0.020794695243239403,
-            "max": 0.3657146096229553,
-            "count": 66
+            "value": 0.01316074002534151,
+            "min": 0.008814494125545025,
+            "max": 0.20890237390995026,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -1.643561840057373,
-            "min": -5.968077659606934,
-            "max": 86.67436218261719,
-            "count": 66
+            "value": 3.737650156021118,
+            "min": 2.5738322734832764,
+            "max": 50.13656997680664,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.07038080369238742,
-            "min": 0.06451708645566696,
-            "max": 0.07374978699359105,
-            "count": 66
+            "value": 0.06606735144673355,
+            "min": 0.06275290679713223,
+            "max": 0.07418008866541578,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9853312516934238,
-            "min": 0.4850758255215833,
-            "max": 1.065685099757199,
-            "count": 66
+            "value": 0.9910102717010032,
+            "min": 0.5705853553153585,
+            "max": 1.1067902058421168,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01578767323406369,
-            "min": 0.0012236097575646088,
-            "max": 0.016009724266724062,
-            "count": 66
+            "value": 0.01504734700391209,
+            "min": 0.001071458480008155,
+            "max": 0.016733134661761052,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.22102742527689168,
-            "min": 0.015906926848339914,
-            "max": 0.22735921353645,
-            "count": 66
+            "value": 0.22571020505868136,
+            "min": 0.011786043280089704,
+            "max": 0.24887661990314705,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 5.295901806160716e-06,
-            "min": 5.295901806160716e-06,
-            "max": 0.0002975753150939428,
-            "count": 66
+            "value": 7.443237518953331e-06,
+            "min": 7.443237518953331e-06,
+            "max": 0.00029501685166105,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 7.414262528625003e-05,
-            "min": 7.414262528625003e-05,
-            "max": 0.0039173409942197,
-            "count": 66
+            "value": 0.00011164856278429996,
+            "min": 0.00011164856278429996,
+            "max": 0.0036322021892659997,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10176526785714288,
-            "min": 0.10176526785714288,
-            "max": 0.19919177142857142,
-            "count": 66
+            "value": 0.10248104666666667,
+            "min": 0.10248104666666667,
+            "max": 0.19833894999999999,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4247137500000002,
-            "min": 1.3943424,
-            "max": 2.7057803000000007,
-            "count": 66
+            "value": 1.5372157000000002,
+            "min": 1.4775717000000002,
+            "max": 2.707736,
+            "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0001863502589285715,
-            "min": 0.0001863502589285715,
-            "max": 0.009919257965714285,
-            "count": 66
+            "value": 0.0002578565619999999,
+            "min": 0.0002578565619999999,
+            "max": 0.009834061105,
+            "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.002608903625000001,
-            "min": 0.002608903625000001,
-            "max": 0.13058745197000002,
-            "count": 66
+            "value": 0.003867848429999999,
+            "min": 0.003867848429999999,
+            "max": 0.12109232660000001,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.007294944953173399,
-            "min": 0.007294944953173399,
-            "max": 0.4627639353275299,
-            "count": 66
+            "value": 0.01209727767854929,
+            "min": 0.01209727767854929,
+            "max": 0.34102651476860046,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.10212922841310501,
-            "min": 0.10212922841310501,
-            "max": 3.239347457885742,
-            "count": 66
+            "value": 0.18145915865898132,
+            "min": 0.17492011189460754,
+            "max": 2.7282121181488037,
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 228.57575757575756,
-            "min": 224.04545454545453,
+            "value": 275.48148148148147,
+            "min": 275.48148148148147,
             "max": 999.0,
-            "count": 66
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30172.0,
-            "min": 15984.0,
-            "max": 32863.0,
-            "count": 66
+            "value": 29752.0,
+            "min": 16859.0,
+            "max": 32800.0,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.7411090785242391,
-            "min": -1.0000000521540642,
-            "max": 1.7757480776946963,
-            "count": 66
+            "value": 1.668106520496239,
+            "min": -0.9999742455059483,
+            "max": 1.6871491158217715,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 229.82639836519957,
-            "min": -26.203001618385315,
-            "max": 232.62299817800522,
-            "count": 66
+            "value": 178.4873976930976,
+            "min": -30.999201610684395,
+            "max": 192.33499920368195,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.7411090785242391,
-            "min": -1.0000000521540642,
-            "max": 1.7757480776946963,
-            "count": 66
+            "value": 1.668106520496239,
+            "min": -0.9999742455059483,
+            "max": 1.6871491158217715,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 229.82639836519957,
-            "min": -26.203001618385315,
-            "max": 232.62299817800522,
-            "count": 66
+            "value": 178.4873976930976,
+            "min": -30.999201610684395,
+            "max": 192.33499920368195,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.0171635204962072,
-            "min": 0.0171635204962072,
-            "max": 9.541543171741068,
-            "count": 66
+            "value": 0.034556155181141725,
+            "min": 0.034556155181141725,
+            "max": 6.2553583041710015,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 2.26558470549935,
-            "min": 2.2248614110721974,
-            "max": 152.6646907478571,
-            "count": 66
+            "value": 3.6975086043821648,
+            "min": 3.6975086043821648,
+            "max": 106.34109117090702,
+            "count": 33
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 66
+            "count": 33
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 66
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673665139",
+        "start_time_seconds": "1673701993",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
         "mlagents_version": "0.29.0.dev0",
@@ -192,66 +192,66 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1673670012"
+        "end_time_seconds": "1673704170"
     },
-    "total": 4872.814098399001,
+    "total": 2177.7436456060004,
     "count": 1,
-    "self": 0.4293696890008505,
+    "self": 0.44360577200041007,
     "children": {
         "run_training.setup": {
-            "total": 0.10736680300033186,
+            "total": 0.1064905060000001,
             "count": 1,
-            "self": 0.10736680300033186
+            "self": 0.1064905060000001
         },
         "TrainerController.start_learning": {
-            "total": 4872.277361906999,
+            "total": 2177.193549328,
             "count": 1,
-            "self": 3.0869327308910215,
+            "self": 1.2594084910374477,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.367885843999829,
+                    "total": 10.848057856999958,
                     "count": 1,
-                    "self": 6.367885843999829
+                    "self": 10.848057856999958
                 },
                 "TrainerController.advance": {
-                    "total": 4862.691678847109,
-                    "count": 129993,
-                    "self": 3.178628663023119,
+                    "total": 2164.9903745319625,
+                    "count": 64412,
+                    "self": 1.3844421119097206,
                     "children": {
                         "env_step": {
-                            "total": 3438.7495797619995,
-                            "count": 129993,
-                            "self": 3188.721794311795,
+                            "total": 1484.0237981480275,
+                            "count": 64412,
+                            "self": 1379.250566092966,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 248.0623247890744,
-                                    "count": 129993,
-                                    "self": 9.840852666827232,
+                                    "total": 103.97687022003129,
+                                    "count": 64412,
+                                    "self": 4.309614343043222,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 238.22147212224718,
-                                            "count": 125060,
-                                            "self": 75.9586107760806,
+                                            "total": 99.66725587698807,
+                                            "count": 62564,
+                                            "self": 33.72057458598715,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 162.26286134616657,
-                                                    "count": 125060,
-                                                    "self": 162.26286134616657
+                                                    "total": 65.94668129100091,
+                                                    "count": 62564,
+                                                    "self": 65.94668129100091
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.965460661130237,
-                                    "count": 129993,
+                                    "total": 0.7963618350302113,
+                                    "count": 64412,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 4861.602301260307,
-                                            "count": 129993,
+                                            "total": 2172.893048014934,
+                                            "count": 64412,
                                             "is_parallel": true,
-                                            "self": 1903.1582843585766,
+                                            "self": 892.7327636448767,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0019798660005108104,
+                                                            "total": 0.006417272000135199,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007296190005945391,
+                                                            "self": 0.0038793659998646035,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0012502469999162713,
+                                                                    "total": 0.0025379060002705955,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0012502469999162713
+                                                                    "self": 0.0025379060002705955
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05018026900052064,
+                                                            "total": 0.04508785500001977,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005339550007192884,
+                                                            "self": 0.0005295040000419249,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004908669998258119,
+                                                                    "total": 0.0004895429999578482,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004908669998258119
+                                                                    "self": 0.0004895429999578482
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.047197503999996115,
+                                                                    "total": 0.04251383199994052,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.047197503999996115
+                                                                    "self": 0.04251383199994052
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001957942999979423,
+                                                                    "total": 0.0015549760000794777,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005910729996685404,
+                                                                    "self": 0.00039897599981486565,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013668700003108825,
+                                                                            "total": 0.001156000000264612,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013668700003108825
+                                                                            "self": 0.001156000000264612
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 2958.4440169017307,
-                                                    "count": 129992,
+                                                    "total": 1280.160284370057,
+                                                    "count": 64411,
                                                     "is_parallel": true,
-                                                    "self": 60.168580463639046,
+                                                    "self": 28.64011411809247,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 49.458883084012996,
-                                                            "count": 129992,
+                                                            "total": 22.43861035595728,
+                                                            "count": 64411,
                                                             "is_parallel": true,
-                                                            "self": 49.458883084012996
+                                                            "self": 22.43861035595728
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2626.4426615690163,
-                                                            "count": 129992,
+                                                            "total": 1135.594442906051,
+                                                            "count": 64411,
                                                             "is_parallel": true,
-                                                            "self": 2626.4426615690163
+                                                            "self": 1135.594442906051
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 222.37389178506237,
-                                                            "count": 129992,
+                                                            "total": 93.48711698995635,
+                                                            "count": 64411,
                                                             "is_parallel": true,
-                                                            "self": 51.015502264122915,
+                                                            "self": 21.85404763880024,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 171.35838952093945,
-                                                                    "count": 1039936,
+                                                                    "total": 71.63306935115611,
+                                                                    "count": 515288,
                                                                     "is_parallel": true,
-                                                                    "self": 171.35838952093945
+                                                                    "self": 71.63306935115611
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1420.7634704220864,
-                            "count": 129993,
-                            "self": 5.949818072253947,
+                            "total": 679.5821342720253,
+                            "count": 64412,
+                            "self": 2.458762720074219,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 325.49482968784196,
-                                    "count": 129993,
-                                    "self": 324.7808535078402,
+                                    "total": 149.97058549094845,
+                                    "count": 64412,
+                                    "self": 149.7750294459488,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.7139761800017368,
-                                            "count": 4,
-                                            "self": 0.7139761800017368
+                                            "total": 0.1955560449996483,
+                                            "count": 2,
+                                            "self": 0.1955560449996483
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1089.3188226619905,
-                                    "count": 932,
-                                    "self": 404.1811011988293,
+                                    "total": 527.1527860610026,
+                                    "count": 458,
+                                    "self": 201.9019030049833,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 685.1377214631611,
-                                            "count": 45612,
-                                            "self": 685.1377214631611
+                                            "total": 325.25088305601935,
+                                            "count": 22839,
+                                            "self": 325.25088305601935
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.850001904647797e-07,
+                    "total": 8.560000424040481e-07,
                     "count": 1,
-                    "self": 8.850001904647797e-07
+                    "self": 8.560000424040481e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.13086359999942943,
+                    "total": 0.09570759200005341,
                     "count": 1,
-                    "self": 0.003977417998612509,
+                    "self": 0.0013996820002830646,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12688618200081692,
+                            "total": 0.09430790999977035,
                             "count": 1,
-                            "self": 0.12688618200081692
+                            "self": 0.09430790999977035
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499975,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499975.onnx",
-                "reward": null,
-                "creation_time": 1673666212.4608846,
+                "steps": 499879,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499879.onnx",
+                "reward": 1.425000011920929,
+                "creation_time": 1673703020.3506935,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499975.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499879.pt"
                 ]
             },
             {
-                "steps": 999984,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999984.onnx",
-                "reward": 1.761999987065792,
-                "creation_time": 1673667444.623405,
+                "steps": 999959,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999959.onnx",
+                "reward": 1.756714261003903,
+                "creation_time": 1673704170.1070614,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999984.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999959.pt"
                 ]
             },
             {
-                "steps": 1499935,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499935.onnx",
-                "reward": 1.4638600051403046,
-                "creation_time": 1673668726.2742608,
+                "steps": 1000028,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000028.onnx",
+                "reward": 1.7626249827444553,
+                "creation_time": 1673704170.3269916,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1499935.pt"
-                ]
-            },
-            {
-                "steps": 1999957,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999957.onnx",
-                "reward": null,
-                "creation_time": 1673670011.8876271,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1999957.pt"
-                ]
-            },
-            {
-                "steps": 2000085,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2000085.onnx",
-                "reward": null,
-                "creation_time": 1673670012.0301795,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-2000085.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000028.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000085,
+            "steps": 1000028,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1673670012.0301795,
+            "reward": 1.7626249827444553,
+            "creation_time": 1673704170.3269916,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-2000085.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000028.pt"
             ]
         }
     },