add ppo pyramids agent

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c786f9a535cbf76f3d835ce5f1e96c78003be49b73c107e418a49e1bd6023988
+oid sha256:5602ae15bea9daf55177383712ab1fa60106409861eb94a219842f6c197d5f8c
 size 1418184

Pyramids/{Pyramids-2048.onnx → Pyramids-1499974.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c786f9a535cbf76f3d835ce5f1e96c78003be49b73c107e418a49e1bd6023988
+oid sha256:dc2a7b8f5258038a5a3234177804b466700cbe132be4283611e937e8eb0c5240
 size 1418184

Pyramids/{Pyramids-2048.pt → Pyramids-1499974.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d0aa8e3e225c748010f38b28d26cc8bd9e0a9a2f0ef6618b538a0b7858bb8d9
-size 2994114
+oid sha256:026ba70e05158db08c07876365ce4867b876cdd8632d4333ebf4c8704f29a047
+size 8650990

Pyramids/{Pyramids-22144.onnx → Pyramids-1999977.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fff74973de2716fa6f9abb6c75538bf31ec061c5e1cbf1036eb17a9d32558bfa
+oid sha256:d11cd6712bb9d669d451a91947bbb20ffdda4908a05585fc409d625abe4f385c
 size 1418184

Pyramids/{Pyramids-22144.pt → Pyramids-1999977.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87348f9bcbe32e6809a49d726af0f234ec65e5d82971b1b6499c7656d2874e8
-size 8650158
+oid sha256:1bae08297b0dcc4012cf70b74989da7a824ad6af415d7c038c017a4b4a94ba6b
+size 8650990

Pyramids/Pyramids-2499948.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44b08fdf8b5885739684a9645c43732ff1e11bd7994e5a373c99cc3cc94de12f
+size 1418184

Pyramids/Pyramids-2499948.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052777516839aaf0ed904a89a9fb27cecc9e23b9c8918bf007b97fec1db4f380
+size 8650990

Pyramids/Pyramids-2999979.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5602ae15bea9daf55177383712ab1fa60106409861eb94a219842f6c197d5f8c
+size 1418184

Pyramids/Pyramids-2999979.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a27f9e96b3ef6343b4c0bf00c97da63d936d30c63f73c727b3fdf19afd053d8
+size 8650990

Pyramids/Pyramids-3000107.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5602ae15bea9daf55177383712ab1fa60106409861eb94a219842f6c197d5f8c
+size 1418184

Pyramids/Pyramids-3000107.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:197872521f91d27554a7683adce6dd0d0d17752f786a2d2211ed4b404091f7ad
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d0aa8e3e225c748010f38b28d26cc8bd9e0a9a2f0ef6618b538a0b7858bb8d9
-size 2994114
+oid sha256:197872521f91d27554a7683adce6dd0d0d17752f786a2d2211ed4b404091f7ad
+size 8650990

Pyramids/{events.out.tfevents.1680809479.538c53bac510.1399.0 → events.out.tfevents.1680810012.452c581d3d14.966.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7017e6110e7e1e9529bac27fbafd514b9200c59ecbabf6d00a2d737dd01191b
-size 1420
+oid sha256:96c04680f22db91ab96bcb46f8712818d7bca3af0157e1a0630a19b032a9315f
+size 934236

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, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "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, "even_checkpoints": false, "max_steps": 1000, "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, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "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, "even_checkpoints": false, "max_steps": 3000000, "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

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000
+    max_steps: 3000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,9 +1,12 @@
 Mono path[0] = '/kaggle/working/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/kaggle/working/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.19.2.2
-Multi-casting "[IP] 172.19.2.2 [Port] 55221 [Flags] 2 [Guid] 3204726395 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.19.2.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.19.2.2 [Port] 55106 [Flags] 2 [Guid] 492131874 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.19.2.2) [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 /kaggle/working/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -33,17 +36,10 @@ ALSA lib pcm.c:2642:(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  0.151 seconds
+- Completed reload, in  0.097 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)
-WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
-ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
 WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - 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?
@@ -65,15 +61,22 @@ 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: 1.578526 ms
+WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - 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: 0.899049 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 2 worker threads for Enlighten.
+Setting up 1 worker threads for Enlighten.
 PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 6 frames, [32.0 KB-64.0 KB]: 32 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 8470 frames, [32.0 KB-64.0 KB]: 30703 frames, [64.0 KB-128.0 KB]: 17095 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
@@ -138,11 +141,6 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 1]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
-      Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
       Current Block Size 320.0 KB
@@ -151,14 +149,14 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 480 B
+      Peak Allocated Bytes 240 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 3
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
@@ -173,11 +171,6 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 2]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -191,19 +184,19 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      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
       Overflow Count 0
-    [ALLOC_TEMP_EnlightenWorker] x 2
+    [ALLOC_TEMP_EnlightenWorker]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
@@ -214,29 +207,29 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 39 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55970 frames
   Requested Block Size 1.0 MB
-  Peak Block count 1
-  Peak Allocated memory 0.9 MB
+  Peak Block count 2
+  Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 1536
+  Peak main deferred allocation count 13128
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.2 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 38 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames, [32.0 MB-64.0 MB]: 56268 frames
       Requested Block Size 16.0 MB
-      Peak Block count 2
-      Peak Allocated memory 18.3 MB
-      Peak Large allocation bytes 0 B
+      Peak Block count 3
+      Peak Allocated memory 47.3 MB
+      Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 39 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames, [4.0 MB-8.0 MB]: 56268 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.2 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 6.3 MB
+      Peak Large allocation bytes 0 B
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -249,7 +242,7 @@ PlayerConnection::CleanupMemory Statistics:
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
   Initial Block Size 2.0 MB
-  Used Block Count 1
+  Used Block Count 2
   Overflow Count (too large) 0
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -262,15 +255,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.2 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 38 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 56268 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]: 39 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 56269 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -280,15 +273,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.2 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 39 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55970 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.9 MB
+      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]: 38 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 56268 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
@@ -298,27 +291,27 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.2 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 39 frames
+      Peak usage frame count: [0-1.0 KB]: 56269 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]: 39 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 56269 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]: 39 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 56269 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.5 KB
+  Peak Allocated memory 29.2 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1680809483772,"processId":1417,"allocatedMemory":1972146,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34516},{"Manager":11723},{"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":3468},{"DynamicArray":30868},{"HashMap":7680},{"Utility":2176},{"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":1680816995386,"processId":978,"allocatedMemory":1970154,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"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":3468},{"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

@@ -1,8 +1,190 @@
 {
     "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.14276349544525146,
+            "min": 0.13769082725048065,
+            "max": 1.4572417736053467,
+            "count": 100
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 4319.4521484375,
+            "min": 4143.943359375,
+            "max": 44206.88671875,
+            "count": 100
+        },
+        "Pyramids.Step.mean": {
+            "value": 2999979.0,
+            "min": 29952.0,
+            "max": 2999979.0,
+            "count": 100
+        },
+        "Pyramids.Step.sum": {
+            "value": 2999979.0,
+            "min": 29952.0,
+            "max": 2999979.0,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.7880120277404785,
+            "min": -0.13937515020370483,
+            "max": 0.884117603302002,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 236.4036102294922,
+            "min": -33.03190994262695,
+            "max": 270.53997802734375,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.01058814488351345,
+            "min": -0.01058814488351345,
+            "max": 0.38161441683769226,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -3.176443576812744,
+            "min": -3.176443576812744,
+            "max": 90.44261932373047,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06460294349970007,
+            "min": 0.06460294349970007,
+            "max": 0.07245850729980573,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.904441208995801,
+            "min": 0.4809648404198955,
+            "max": 1.0805650154692485,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.015231969922232176,
+            "min": 0.0010879355447108963,
+            "max": 0.01642314226041682,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.21324757891125046,
+            "min": 0.014143162081241653,
+            "max": 0.2463471339062523,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.4421280907523867e-06,
+            "min": 1.4421280907523867e-06,
+            "max": 0.00029838354339596195,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 2.0189793270533415e-05,
+            "min": 2.0189793270533415e-05,
+            "max": 0.004052848449050532,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.1004806761904762,
+            "min": 0.1004806761904762,
+            "max": 0.19946118095238097,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4067294666666668,
+            "min": 1.3962282666666668,
+            "max": 2.8275573333333335,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 5.801955142857163e-05,
+            "min": 5.801955142857163e-05,
+            "max": 0.009946171977142856,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0008122737200000028,
+            "min": 0.0008122737200000028,
+            "max": 0.13509985172,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.0068816328421235085,
+            "min": 0.0068551101721823215,
+            "max": 0.5026339292526245,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.09634286165237427,
+            "min": 0.09597153961658478,
+            "max": 3.518437623977661,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 229.82835820895522,
+            "min": 203.53571428571428,
+            "max": 999.0,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30797.0,
+            "min": 15984.0,
+            "max": 33616.0,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7403134184319582,
+            "min": -1.0000000521540642,
+            "max": 1.796464268969638,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 233.2019980698824,
+            "min": -27.647201739251614,
+            "max": 258.2169983237982,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7403134184319582,
+            "min": -1.0000000521540642,
+            "max": 1.796464268969638,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 233.2019980698824,
+            "min": -27.647201739251614,
+            "max": 258.2169983237982,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.016465745684997014,
+            "min": 0.014973602063745213,
+            "max": 10.631956234574318,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.2064099217896,
+            "min": 2.088437120008166,
+            "max": 170.1112997531891,
+            "count": 100
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1680809478",
+        "start_time_seconds": "1680810011",
         "python_version": "3.10.5 | packaged by conda-forge | (main, Jun 14 2022, 07:04:59) [GCC 10.3.0]",
         "command_line_arguments": "ml-agents/mlagents/trainers/learn.py ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
         "mlagents_version": "0.31.0.dev0",
@@ -10,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1680809483"
+        "end_time_seconds": "1680816995"
     },
-    "total": 5.488942410000163,
+    "total": 6983.470412672,
     "count": 1,
-    "self": 0.3839939360000244,
+    "self": 0.49378166499991494,
     "children": {
         "run_training.setup": {
-            "total": 0.028669853000337753,
+            "total": 0.01997928400010096,
             "count": 1,
-            "self": 0.028669853000337753
+            "self": 0.01997928400010096
         },
         "TrainerController.start_learning": {
-            "total": 5.076278620999801,
+            "total": 6982.956651723,
             "count": 1,
-            "self": 0.004815533995042642,
+            "self": 4.835357799255689,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.2575389300000097,
+                    "total": 3.3798891459998686,
                     "count": 1,
-                    "self": 1.2575389300000097
+                    "self": 3.3798891459998686
                 },
                 "TrainerController.advance": {
-                    "total": 3.6890459210048903,
-                    "count": 128,
-                    "self": 0.005096853004943114,
+                    "total": 6974.634803342744,
+                    "count": 195694,
+                    "self": 4.595577090563893,
                     "children": {
                         "env_step": {
-                            "total": 3.4049632540027233,
-                            "count": 128,
-                            "self": 3.1243298950043936,
+                            "total": 5169.338238900851,
+                            "count": 195694,
+                            "self": 4856.954858979969,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 0.27806894400009696,
-                                    "count": 128,
-                                    "self": 0.014406682001663285,
+                                    "total": 309.48048991081714,
+                                    "count": 195694,
+                                    "self": 13.959444717980205,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 0.2636622619984337,
-                                            "count": 128,
-                                            "self": 0.2636622619984337
+                                            "total": 295.52104519283694,
+                                            "count": 187562,
+                                            "self": 295.52104519283694
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.002564414998232678,
-                                    "count": 128,
+                                    "total": 2.902890010065221,
+                                    "count": 195694,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 4.695457389996591,
-                                            "count": 128,
+                                            "total": 6962.905718054875,
+                                            "count": 195694,
                                             "is_parallel": true,
-                                            "self": 2.0522189569906004,
+                                            "self": 2467.113556077011,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -71,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0022281389997260703,
+                                                            "total": 0.0018009939999501512,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00073014300005525,
+                                                            "self": 0.0005803920000744256,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014979959996708203,
+                                                                    "total": 0.0012206019998757256,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014979959996708203
+                                                                    "self": 0.0012206019998757256
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04985738900040815,
+                                                            "total": 0.08273205199998301,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00039290800032176776,
+                                                            "self": 0.0005607649998182751,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00037218099987512687,
+                                                                    "total": 0.0005139909999343217,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00037218099987512687
+                                                                    "self": 0.0005139909999343217
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04784012500022072,
+                                                                    "total": 0.07560907800007044,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04784012500022072
+                                                                    "self": 0.07560907800007044
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0012521749999905296,
+                                                                    "total": 0.006048218000159977,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003200290002496331,
+                                                                    "self": 0.00040821899983711774,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0009321459997408965,
+                                                                            "total": 0.0056399990003228595,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0009321459997408965
+                                                                            "self": 0.0056399990003228595
                                                                         }
                                                                     }
                                                                 }
@@ -121,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 2.6432384330059904,
-                                                    "count": 127,
+                                                    "total": 4495.792161977864,
+                                                    "count": 195693,
                                                     "is_parallel": true,
-                                                    "self": 0.07031876200653642,
+                                                    "self": 99.70346102174699,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.04903905799756103,
-                                                            "count": 127,
+                                                            "total": 75.05140697701268,
+                                                            "count": 195693,
                                                             "is_parallel": true,
-                                                            "self": 0.04903905799756103
+                                                            "self": 75.05140697701268
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2.3157620660008433,
-                                                            "count": 127,
+                                                            "total": 4017.900902720913,
+                                                            "count": 195693,
                                                             "is_parallel": true,
-                                                            "self": 2.3157620660008433
+                                                            "self": 4017.900902720913
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 0.2081185470010496,
-                                                            "count": 127,
+                                                            "total": 303.1363912581919,
+                                                            "count": 195693,
                                                             "is_parallel": true,
-                                                            "self": 0.0484633290061538,
+                                                            "self": 68.8161426400427,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.1596552179948958,
-                                                                    "count": 1016,
+                                                                    "total": 234.3202486181492,
+                                                                    "count": 1565544,
                                                                     "is_parallel": true,
-                                                                    "self": 0.1596552179948958
+                                                                    "self": 234.3202486181492
                                                                 }
                                                             }
                                                         }
@@ -161,33 +343,52 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 0.2789858139972239,
-                            "count": 128,
-                            "self": 0.003896467999311426,
+                            "total": 1800.7009873513293,
+                            "count": 195694,
+                            "self": 8.696883420345102,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 0.27508934599791246,
-                                    "count": 128,
-                                    "self": 0.27508934599791246
+                                    "total": 332.2479694359938,
+                                    "count": 195694,
+                                    "self": 331.58103084599384,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.6669385899999725,
+                                            "count": 6,
+                                            "self": 0.6669385899999725
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 1459.7561344949904,
+                                    "count": 1406,
+                                    "self": 974.2329162310107,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 485.52321826397974,
+                                            "count": 68394,
+                                            "self": 485.52321826397974
+                                        }
+                                    }
                                 }
                             }
                         }
                     }
                 },
                 "trainer_threads": {
-                    "total": 2.1310002011887264e-06,
+                    "total": 8.930001058615744e-07,
                     "count": 1,
-                    "self": 2.1310002011887264e-06
+                    "self": 8.930001058615744e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1248761049996574,
+                    "total": 0.1066005419997964,
                     "count": 1,
-                    "self": 0.0032216149993473664,
+                    "self": 0.0015894160005700542,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12165449000031003,
+                            "total": 0.10501112599922635,
                             "count": 1,
-                            "self": 0.12165449000031003
+                            "self": 0.10501112599922635
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 2048,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2048.onnx",
-                "reward": null,
-                "creation_time": 1680809483.4232855,
+                "steps": 1499974,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499974.onnx",
+                "reward": 1.644599974155426,
+                "creation_time": 1680813284.0813012,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-2048.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1499974.pt"
+                ]
+            },
+            {
+                "steps": 1999977,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999977.onnx",
+                "reward": 1.698428554194314,
+                "creation_time": 1680814530.3991463,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999977.pt"
+                ]
+            },
+            {
+                "steps": 2499948,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499948.onnx",
+                "reward": 1.8989999294281006,
+                "creation_time": 1680815772.9335077,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2499948.pt"
+                ]
+            },
+            {
+                "steps": 2999979,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999979.onnx",
+                "reward": 1.7519999941190083,
+                "creation_time": 1680816994.8330595,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2999979.pt"
+                ]
+            },
+            {
+                "steps": 3000107,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000107.onnx",
+                "reward": 1.7519999941190083,
+                "creation_time": 1680816994.9509661,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-3000107.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2048,
+            "steps": 3000107,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1680809483.4232855,
+            "reward": 1.7519999941190083,
+            "creation_time": 1680816994.9509661,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-2048.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-3000107.pt"
             ]
         }
     },