third Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5948dc4647959e04237e06ea935731983470b845e5e1ba52497dc1a20997095
-size 1417437
+oid sha256:37f65662ad0e129eb7ac3aa4af9a003d9502ac8159cb9fb7bfb7be8d8c5e4e85
+size 2468409

Pyramids/{Pyramids-1000028.onnx → Pyramids-1499934.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5948dc4647959e04237e06ea935731983470b845e5e1ba52497dc1a20997095
-size 1417437
+oid sha256:146c4c3a36bf6501e776486853d2952cf4d7f2b0f50223fff759ddc87fddc12f
+size 2468409

Pyramids/Pyramids-1499934.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e08c559b2b47cd1aa1f00222277ba26a597aa2d644667136f4c1132c201e854
+size 14960218

Pyramids/{Pyramids-1000028.pt → Pyramids-1999915.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bef324818f3fb3965abdf4a6e9ea41456f11d5aef63f32e92dc6b41aa7a2cf4
-size 8652382
+oid sha256:37f65662ad0e129eb7ac3aa4af9a003d9502ac8159cb9fb7bfb7be8d8c5e4e85
+size 2468409

Pyramids/Pyramids-1999915.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c517427f44f236f9691859b0f769fa6282d201255af4d3e5794c1e1f64cfd17e
+size 14960218

Pyramids/{Pyramids-499879.onnx → Pyramids-2000043.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e50bb5e3c3c2dd3d8a593ea3e839996d957e2c65bbf4fbe52b692f08448506e
-size 1417437
+oid sha256:37f65662ad0e129eb7ac3aa4af9a003d9502ac8159cb9fb7bfb7be8d8c5e4e85
+size 2468409

Pyramids/Pyramids-2000043.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb6e774af9fcc642d46830829f6196781791f32973f787ac929b3e5ea3d1772e
+size 14960218

Pyramids/{Pyramids-499879.pt → Pyramids-499941.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a46b3323660bf64281e491d8e62e2ca165c2407aefa6be7ca4baebe87ddc15
-size 8652382
+oid sha256:63765fc5c113df7bc6ed76d157ed077b0b40414c8dbc0de9d8d43fb2b9954060
+size 2468409

Pyramids/Pyramids-499941.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0092280f1a4bec315c49cbca05c8a332e87e2300a98c3d8b2ee2baee463dac
+size 14960218

Pyramids/Pyramids-999926.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c433971f2c0b657273fc4c51fca0cc1f7deb030045d9707cdda8cd12c5f1615d
+size 2468409

Pyramids/Pyramids-999926.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:671eeabce0cb1d77c4cbfd26046b4d79c33aa9520f8189b4808b57a975c01142
+size 14960218

Pyramids/Pyramids-999959.onnx

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

Pyramids/Pyramids-999959.pt

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

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bef324818f3fb3965abdf4a6e9ea41456f11d5aef63f32e92dc6b41aa7a2cf4
-size 8652382
+oid sha256:bb6e774af9fcc642d46830829f6196781791f32973f787ac929b3e5ea3d1772e
+size 14960218

Pyramids/{events.out.tfevents.1673701999.e4526b1a626c.7046.0 → events.out.tfevents.1673831062.c4fb3cad320e.1604.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c23b2a9c43e82cbb8dc79cb0dd95fc8fd4531c986abef17cca9b843fd9b07f6a
-size 333154
+oid sha256:9a776410c07586f2001f233ccb7ddd0f57d5b56cb346ef47597504a1ac7ea6a4
+size 415462

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": 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}
+{"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": 50000, "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: 2
+      num_layers: 3
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
@@ -49,9 +49,9 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 500000
-    max_steps: 1000000
+    max_steps: 2000000
     time_horizon: 128
-    summary_freq: 30000
+    summary_freq: 50000
     threaded: false
     self_play: null
     behavioral_cloning: null

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 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] 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]...
+Multi-casting "[IP] 172.28.0.2 [Port] 55477 [Flags] 2 [Guid] 3132877910 [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
@@ -36,7 +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  0.085 seconds
+- Completed reload, in  0.081 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)
@@ -68,7 +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: 0.849959 ms
+UnloadTime: 0.993092 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.
@@ -76,7 +76,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 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
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2647 frames, [32.0 KB-64.0 KB]: 24956 frames, [64.0 KB-128.0 KB]: 9914 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
@@ -186,12 +186,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -207,28 +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]: 18470 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37219 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.5 MB
+  Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12215
+  Peak main deferred allocation count 11816
     [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]: 18768 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37517 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.4 MB
+      Peak Allocated memory 31.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37518 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.7 MB
+      Peak Allocated memory 22.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +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]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37517 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]: 18769 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 37518 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,13 +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]: 18470 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37219 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]: 18768 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 37517 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
@@ -293,19 +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]: 18769 frames
+      Peak usage frame count: [0-1.0 KB]: 37518 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]: 18769 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37518 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]: 18769 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 37518 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -314,4 +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":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}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673835599694,"processId":1625,"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": 0.3197597563266754,
-            "min": 0.3197597563266754,
-            "max": 1.50977623462677,
-            "count": 33
+            "value": 0.14041484892368317,
+            "min": 0.13712115585803986,
+            "max": 1.2966101169586182,
+            "count": 40
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 9587.6767578125,
-            "min": 9587.6767578125,
-            "max": 45800.5703125,
-            "count": 33
+            "value": 6984.7958984375,
+            "min": 6873.609375,
+            "max": 65556.609375,
+            "count": 40
         },
         "Pyramids.Step.mean": {
-            "value": 989983.0,
-            "min": 29932.0,
-            "max": 989983.0,
-            "count": 33
+            "value": 1999915.0,
+            "min": 49933.0,
+            "max": 1999915.0,
+            "count": 40
         },
         "Pyramids.Step.sum": {
-            "value": 989983.0,
-            "min": 29932.0,
-            "max": 989983.0,
-            "count": 33
+            "value": 1999915.0,
+            "min": 49933.0,
+            "max": 1999915.0,
+            "count": 40
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.7090317606925964,
-            "min": -0.1796794980764389,
-            "max": 0.7090317606925964,
-            "count": 33
+            "value": 0.757975161075592,
+            "min": -0.07929027825593948,
+            "max": 0.7789816856384277,
+            "count": 40
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 201.36502075195312,
-            "min": -42.584041595458984,
-            "max": 201.36502075195312,
-            "count": 33
+            "value": 374.4397277832031,
+            "min": -31.716110229492188,
+            "max": 389.4908447265625,
+            "count": 40
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.01316074002534151,
-            "min": 0.008814494125545025,
-            "max": 0.20890237390995026,
-            "count": 33
+            "value": 0.012441575527191162,
+            "min": 0.0021538061555474997,
+            "max": 0.3765905797481537,
+            "count": 40
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 3.737650156021118,
-            "min": 2.5738322734832764,
-            "max": 50.13656997680664,
-            "count": 33
+            "value": 6.1461381912231445,
+            "min": 1.0445959568023682,
+            "max": 150.63623046875,
+            "count": 40
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06606735144673355,
-            "min": 0.06275290679713223,
-            "max": 0.07418008866541578,
-            "count": 33
+            "value": 0.0674945751894299,
+            "min": 0.06639079328863891,
+            "max": 0.07274179220459903,
+            "count": 40
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9910102717010032,
-            "min": 0.5705853553153585,
-            "max": 1.1067902058421168,
-            "count": 33
+            "value": 1.5523752293568878,
+            "min": 0.9712289379387837,
+            "max": 1.7458030129103768,
+            "count": 40
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01504734700391209,
-            "min": 0.001071458480008155,
-            "max": 0.016733134661761052,
-            "count": 33
+            "value": 0.015106265140828955,
+            "min": 0.001978774983687255,
+            "max": 0.015877475243530104,
+            "count": 40
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.22571020505868136,
-            "min": 0.011786043280089704,
-            "max": 0.24887661990314705,
-            "count": 33
+            "value": 0.34744409823906597,
+            "min": 0.0400164191713699,
+            "max": 0.38105940584472253,
+            "count": 40
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.443237518953331e-06,
-            "min": 7.443237518953331e-06,
-            "max": 0.00029501685166105,
-            "count": 33
+            "value": 3.776994393208696e-06,
+            "min": 3.776994393208696e-06,
+            "max": 0.00029583776924455355,
+            "count": 40
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00011164856278429996,
-            "min": 0.00011164856278429996,
-            "max": 0.0036322021892659997,
-            "count": 33
+            "value": 8.687087104380001e-05,
+            "min": 8.687087104380001e-05,
+            "max": 0.006351212032929351,
+            "count": 40
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10248104666666667,
-            "min": 0.10248104666666667,
-            "max": 0.19833894999999999,
-            "count": 33
+            "value": 0.1012589652173913,
+            "min": 0.1012589652173913,
+            "max": 0.1986125892857143,
+            "count": 40
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.5372157000000002,
-            "min": 1.4775717000000002,
-            "max": 2.707736,
-            "count": 33
+            "value": 2.3289562,
+            "min": 2.3289562,
+            "max": 4.4103963,
+            "count": 40
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002578565619999999,
-            "min": 0.0002578565619999999,
-            "max": 0.009834061105,
-            "count": 33
+            "value": 0.0001357706252173913,
+            "min": 0.0001357706252173913,
+            "max": 0.009861397669642854,
+            "count": 40
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.003867848429999999,
-            "min": 0.003867848429999999,
-            "max": 0.12109232660000001,
-            "count": 33
+            "value": 0.00312272438,
+            "min": 0.00312272438,
+            "max": 0.21171535793500001,
+            "count": 40
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.01209727767854929,
-            "min": 0.01209727767854929,
-            "max": 0.34102651476860046,
-            "count": 33
+            "value": 0.009165954776108265,
+            "min": 0.009165954776108265,
+            "max": 0.33213332295417786,
+            "count": 40
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.18145915865898132,
-            "min": 0.17492011189460754,
-            "max": 2.7282121181488037,
-            "count": 33
+            "value": 0.21081696450710297,
+            "min": 0.21081696450710297,
+            "max": 4.649866580963135,
+            "count": 40
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 275.48148148148147,
-            "min": 275.48148148148147,
-            "max": 999.0,
-            "count": 33
+            "value": 246.87623762376236,
+            "min": 243.32682926829267,
+            "max": 985.9375,
+            "count": 40
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29752.0,
-            "min": 16859.0,
-            "max": 32800.0,
-            "count": 33
+            "value": 49869.0,
+            "min": 46862.0,
+            "max": 52195.0,
+            "count": 40
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.668106520496239,
-            "min": -0.9999742455059483,
-            "max": 1.6871491158217715,
-            "count": 33
+            "value": 1.7234088959965375,
+            "min": -0.9035542171138028,
+            "max": 1.7450465891980431,
+            "count": 40
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 178.4873976930976,
-            "min": -30.999201610684395,
-            "max": 192.33499920368195,
-            "count": 33
+            "value": 348.1285969913006,
+            "min": -43.370602421462536,
+            "max": 359.47959737479687,
+            "count": 40
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.668106520496239,
-            "min": -0.9999742455059483,
-            "max": 1.6871491158217715,
-            "count": 33
+            "value": 1.7234088959965375,
+            "min": -0.9035542171138028,
+            "max": 1.7450465891980431,
+            "count": 40
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 178.4873976930976,
-            "min": -30.999201610684395,
-            "max": 192.33499920368195,
-            "count": 33
+            "value": 348.1285969913006,
+            "min": -43.370602421462536,
+            "max": 359.47959737479687,
+            "count": 40
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.034556155181141725,
-            "min": 0.034556155181141725,
-            "max": 6.2553583041710015,
-            "count": 33
+            "value": 0.023520248840555938,
+            "min": 0.023520248840555938,
+            "max": 4.848506656708196,
+            "count": 40
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 3.6975086043821648,
-            "min": 3.6975086043821648,
-            "max": 106.34109117090702,
-            "count": 33
+            "value": 4.7510902657923,
+            "min": 4.728349542085198,
+            "max": 232.7283195219934,
+            "count": 40
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 40
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 40
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673701993",
+        "start_time_seconds": "1673831055",
         "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": "1673704170"
+        "end_time_seconds": "1673835599"
     },
-    "total": 2177.7436456060004,
+    "total": 4543.838225563,
     "count": 1,
-    "self": 0.44360577200041007,
+    "self": 0.5960226670003976,
     "children": {
         "run_training.setup": {
-            "total": 0.1064905060000001,
+            "total": 0.12589435799998228,
             "count": 1,
-            "self": 0.1064905060000001
+            "self": 0.12589435799998228
         },
         "TrainerController.start_learning": {
-            "total": 2177.193549328,
+            "total": 4543.116308538,
             "count": 1,
-            "self": 1.2594084910374477,
+            "self": 2.53086013695156,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 10.848057856999958,
+                    "total": 9.631875206000018,
                     "count": 1,
-                    "self": 10.848057856999958
+                    "self": 9.631875206000018
                 },
                 "TrainerController.advance": {
-                    "total": 2164.9903745319625,
-                    "count": 64412,
-                    "self": 1.3844421119097206,
+                    "total": 4530.822265361048,
+                    "count": 129546,
+                    "self": 2.75618783106529,
                     "children": {
                         "env_step": {
-                            "total": 1484.0237981480275,
-                            "count": 64412,
-                            "self": 1379.250566092966,
+                            "total": 3125.71005376904,
+                            "count": 129546,
+                            "self": 2902.199031741154,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 103.97687022003129,
-                                    "count": 64412,
-                                    "self": 4.309614343043222,
+                                    "total": 221.89606513703376,
+                                    "count": 129546,
+                                    "self": 8.891637529068419,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 99.66725587698807,
-                                            "count": 62564,
-                                            "self": 33.72057458598715,
+                                            "total": 213.00442760796534,
+                                            "count": 125058,
+                                            "self": 68.88413067501307,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 65.94668129100091,
-                                                    "count": 62564,
-                                                    "self": 65.94668129100091
+                                                    "total": 144.12029693295227,
+                                                    "count": 125058,
+                                                    "self": 144.12029693295227
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7963618350302113,
-                                    "count": 64412,
+                                    "total": 1.6149568908521132,
+                                    "count": 129546,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2172.893048014934,
-                                            "count": 64412,
+                                            "total": 4534.084476353929,
+                                            "count": 129546,
                                             "is_parallel": true,
-                                            "self": 892.7327636448767,
+                                            "self": 1840.0976748749172,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.006417272000135199,
+                                                            "total": 0.0077296580000165704,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0038793659998646035,
+                                                            "self": 0.0032698439999307993,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0025379060002705955,
+                                                                    "total": 0.004459814000085771,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0025379060002705955
+                                                                    "self": 0.004459814000085771
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04508785500001977,
+                                                            "total": 0.048913362999996934,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005295040000419249,
+                                                            "self": 0.0004918169999541533,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004895429999578482,
+                                                                    "total": 0.0005283230000259209,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004895429999578482
+                                                                    "self": 0.0005283230000259209
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04251383199994052,
+                                                                    "total": 0.04620942400003969,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04251383199994052
+                                                                    "self": 0.04620942400003969
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0015549760000794777,
+                                                                    "total": 0.0016837989999771708,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00039897599981486565,
+                                                                    "self": 0.00046671500001593813,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001156000000264612,
+                                                                            "total": 0.0012170839999612326,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001156000000264612
+                                                                            "self": 0.0012170839999612326
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1280.160284370057,
-                                                    "count": 64411,
+                                                    "total": 2693.986801479012,
+                                                    "count": 129545,
                                                     "is_parallel": true,
-                                                    "self": 28.64011411809247,
+                                                    "self": 57.07145611872829,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 22.43861035595728,
-                                                            "count": 64411,
+                                                            "total": 48.814293096192785,
+                                                            "count": 129545,
                                                             "is_parallel": true,
-                                                            "self": 22.43861035595728
+                                                            "self": 48.814293096192785
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1135.594442906051,
-                                                            "count": 64411,
+                                                            "total": 2388.96977148709,
+                                                            "count": 129545,
                                                             "is_parallel": true,
-                                                            "self": 1135.594442906051
+                                                            "self": 2388.96977148709
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 93.48711698995635,
-                                                            "count": 64411,
+                                                            "total": 199.131280777001,
+                                                            "count": 129545,
                                                             "is_parallel": true,
-                                                            "self": 21.85404763880024,
+                                                            "self": 46.97348018092839,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 71.63306935115611,
-                                                                    "count": 515288,
+                                                                    "total": 152.1578005960726,
+                                                                    "count": 1036360,
                                                                     "is_parallel": true,
-                                                                    "self": 71.63306935115611
+                                                                    "self": 152.1578005960726
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 679.5821342720253,
-                            "count": 64412,
-                            "self": 2.458762720074219,
+                            "total": 1402.3560237609431,
+                            "count": 129546,
+                            "self": 5.057746946869656,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 149.97058549094845,
-                                    "count": 64412,
-                                    "self": 149.7750294459488,
+                                    "total": 313.7211487850659,
+                                    "count": 129546,
+                                    "self": 313.1898563630659,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.1955560449996483,
-                                            "count": 2,
-                                            "self": 0.1955560449996483
+                                            "total": 0.5312924219999786,
+                                            "count": 4,
+                                            "self": 0.5312924219999786
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 527.1527860610026,
-                                    "count": 458,
-                                    "self": 201.9019030049833,
+                                    "total": 1083.5771280290076,
+                                    "count": 932,
+                                    "self": 416.6385965120131,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 325.25088305601935,
-                                            "count": 22839,
-                                            "self": 325.25088305601935
+                                            "total": 666.9385315169944,
+                                            "count": 45561,
+                                            "self": 666.9385315169944
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.560000424040481e-07,
+                    "total": 8.080005500232801e-07,
                     "count": 1,
-                    "self": 8.560000424040481e-07
+                    "self": 8.080005500232801e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09570759200005341,
+                    "total": 0.131307026000286,
                     "count": 1,
-                    "self": 0.0013996820002830646,
+                    "self": 0.002107295999849157,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09430790999977035,
+                            "total": 0.12919973000043683,
                             "count": 1,
-                            "self": 0.09430790999977035
+                            "self": 0.12919973000043683
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499879,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499879.onnx",
-                "reward": 1.425000011920929,
-                "creation_time": 1673703020.3506935,
+                "steps": 499941,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499941.onnx",
+                "reward": null,
+                "creation_time": 1673832058.9279318,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499879.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499941.pt"
                 ]
             },
             {
-                "steps": 999959,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999959.onnx",
-                "reward": 1.756714261003903,
-                "creation_time": 1673704170.1070614,
+                "steps": 999926,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999926.onnx",
+                "reward": 1.123999923467636,
+                "creation_time": 1673833177.4576147,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999959.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999926.pt"
                 ]
             },
             {
-                "steps": 1000028,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000028.onnx",
-                "reward": 1.7626249827444553,
-                "creation_time": 1673704170.3269916,
+                "steps": 1499934,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499934.onnx",
+                "reward": 1.5677499920129776,
+                "creation_time": 1673834372.5188894,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000028.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1499934.pt"
+                ]
+            },
+            {
+                "steps": 1999915,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999915.onnx",
+                "reward": 1.604836344718933,
+                "creation_time": 1673835598.9930935,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999915.pt"
+                ]
+            },
+            {
+                "steps": 2000043,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2000043.onnx",
+                "reward": 1.604836344718933,
+                "creation_time": 1673835599.1385298,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2000043.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000028,
+            "steps": 2000043,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.7626249827444553,
-            "creation_time": 1673704170.3269916,
+            "reward": 1.604836344718933,
+            "creation_time": 1673835599.1385298,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000028.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-2000043.pt"
             ]
         }
     },