fourth Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f65662ad0e129eb7ac3aa4af9a003d9502ac8159cb9fb7bfb7be8d8c5e4e85
+oid sha256:a99fa7045cfb6723f06cd8e42e25792bd553203e5528ee04e61048158abb0a3e
 size 2468409

Pyramids/{Pyramids-1499934.onnx → Pyramids-2499958.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:146c4c3a36bf6501e776486853d2952cf4d7f2b0f50223fff759ddc87fddc12f
+oid sha256:ece5e10459ed9c7fc78b0838894116fd97228a225f0c59e609b6abe7e639c251
 size 2468409

Pyramids/{Pyramids-999926.pt → Pyramids-2499958.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671eeabce0cb1d77c4cbfd26046b4d79c33aa9520f8189b4808b57a975c01142
+oid sha256:423ffc118ff6bebc42541a96a9c161d9df3e254287bff534fdeba201e1623122
 size 14960218

Pyramids/{Pyramids-999926.onnx → Pyramids-2999960.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c433971f2c0b657273fc4c51fca0cc1f7deb030045d9707cdda8cd12c5f1615d
+oid sha256:a99fa7045cfb6723f06cd8e42e25792bd553203e5528ee04e61048158abb0a3e
 size 2468409

Pyramids/{Pyramids-1499934.pt → Pyramids-2999960.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e08c559b2b47cd1aa1f00222277ba26a597aa2d644667136f4c1132c201e854
-size 14960218
+oid sha256:34d73b66b40648c02ed4c0cd4dae53cd4b549063f290c3b742076cdbd5388745
+size 14960282

Pyramids/{Pyramids-499941.onnx → Pyramids-3000055.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63765fc5c113df7bc6ed76d157ed077b0b40414c8dbc0de9d8d43fb2b9954060
+oid sha256:a99fa7045cfb6723f06cd8e42e25792bd553203e5528ee04e61048158abb0a3e
 size 2468409

Pyramids/{Pyramids-499941.pt → Pyramids-3000055.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb0092280f1a4bec315c49cbca05c8a332e87e2300a98c3d8b2ee2baee463dac
-size 14960218
+oid sha256:2d58c15a9ca171b0a9340a743f8be760816555456df48d83c662a1c72a900668
+size 14960282

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb6e774af9fcc642d46830829f6196781791f32973f787ac929b3e5ea3d1772e
-size 14960218
+oid sha256:2d58c15a9ca171b0a9340a743f8be760816555456df48d83c662a1c72a900668
+size 14960282

Pyramids/events.out.tfevents.1673836162.c4fb3cad320e.22724.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6a8b6d624ffdb833b7ec5382209ea37df10f68b04ba13fd67bdaa30cbecdba7
+size 208668

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 2000000, "time_horizon": 128, "summary_freq": 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}
+{"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": 3000000, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -49,7 +49,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 500000
-    max_steps: 2000000
+    max_steps: 3000000
     time_horizon: 128
     summary_freq: 50000
     threaded: false
@@ -78,8 +78,8 @@ checkpoint_settings:
   run_id: Pyramids Training
   initialize_from: null
   load_model: false
-  resume: false
-  force: true
+  resume: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 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] 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]...
+Multi-casting "[IP] 172.28.0.2 [Port] 55311 [Flags] 2 [Guid] 4237741522 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ 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  0.081 seconds
+- Completed reload, in  0.085 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -68,7 +65,7 @@ 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: 0.993092 ms
+UnloadTime: 0.745713 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 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      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
+      Peak usage frame count: [16.0 KB-32.0 KB]: 907 frames, [32.0 KB-64.0 KB]: 10896 frames, [64.0 KB-128.0 KB]: 6965 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
@@ -131,12 +128,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       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 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -186,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       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_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
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37219 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 41 frames, [1.0 MB-2.0 MB]: 18728 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 11816
+  Peak main deferred allocation count 8666
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.2 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37517 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18768 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 31.0 MB
+      Peak Block count 2
+      Peak Allocated memory 24.1 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 37518 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.3 MB
+      Peak Allocated memory 21.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.2 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 37517 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 37518 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.2 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37219 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 54 frames, [1.0 MB-2.0 MB]: 18715 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 37517 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18768 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -291,21 +288,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.2 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 37518 frames
+      Peak usage frame count: [0-1.0 KB]: 18769 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 37518 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18769 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 37518 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18769 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -314,4 +311,4 @@ 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":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}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673838641717,"processId":22741,"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

@@ -2,256 +2,256 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.14041484892368317,
-            "min": 0.13712115585803986,
-            "max": 1.2966101169586182,
-            "count": 40
+            "value": 0.10759957879781723,
+            "min": 0.09833017736673355,
+            "max": 0.1674557477235794,
+            "count": 20
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 6984.7958984375,
-            "min": 6873.609375,
-            "max": 65556.609375,
-            "count": 40
+            "value": 5376.53564453125,
+            "min": 4889.76318359375,
+            "max": 8335.27734375,
+            "count": 20
         },
         "Pyramids.Step.mean": {
-            "value": 1999915.0,
-            "min": 49933.0,
-            "max": 1999915.0,
-            "count": 40
+            "value": 2999960.0,
+            "min": 2049908.0,
+            "max": 2999960.0,
+            "count": 20
         },
         "Pyramids.Step.sum": {
-            "value": 1999915.0,
-            "min": 49933.0,
-            "max": 1999915.0,
-            "count": 40
+            "value": 2999960.0,
+            "min": 2049908.0,
+            "max": 2999960.0,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.757975161075592,
-            "min": -0.07929027825593948,
-            "max": 0.7789816856384277,
-            "count": 40
+            "value": 0.776948094367981,
+            "min": 0.7297616600990295,
+            "max": 0.841191828250885,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 374.4397277832031,
-            "min": -31.716110229492188,
-            "max": 389.4908447265625,
-            "count": 40
+            "value": 378.37371826171875,
+            "min": 349.55584716796875,
+            "max": 423.960693359375,
+            "count": 20
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.012441575527191162,
-            "min": 0.0021538061555474997,
-            "max": 0.3765905797481537,
-            "count": 40
+            "value": 0.013783132657408714,
+            "min": 0.00496201915666461,
+            "max": 0.025915388017892838,
+            "count": 20
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 6.1461381912231445,
-            "min": 1.0445959568023682,
-            "max": 150.63623046875,
-            "count": 40
+            "value": 6.712385654449463,
+            "min": 2.4561994075775146,
+            "max": 12.957694053649902,
+            "count": 20
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 249.16915422885572,
+            "min": 220.00892857142858,
+            "max": 256.3315789473684,
+            "count": 20
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 50083.0,
+            "min": 47474.0,
+            "max": 51618.0,
+            "count": 20
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7200469828397036,
+            "min": 1.6804831448354218,
+            "max": 1.7571175246724586,
+            "count": 20
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 344.0093965679407,
+            "min": 319.29179751873016,
+            "max": 394.57019747793674,
+            "count": 20
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7200469828397036,
+            "min": 1.6804831448354218,
+            "max": 1.7571175246724586,
+            "count": 20
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 344.0093965679407,
+            "min": 319.29179751873016,
+            "max": 394.57019747793674,
+            "count": 20
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.02017505864481791,
+            "min": 0.017814976329229668,
+            "max": 0.022875287693515288,
+            "count": 20
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 4.035011728963582,
+            "min": 4.008369674076675,
+            "max": 4.635133538788068,
+            "count": 20
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.0674945751894299,
-            "min": 0.06639079328863891,
-            "max": 0.07274179220459903,
-            "count": 40
+            "value": 0.06441230353079637,
+            "min": 0.06441230353079637,
+            "max": 0.07152059890489823,
+            "count": 20
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 1.5523752293568878,
-            "min": 0.9712289379387837,
-            "max": 1.7458030129103768,
-            "count": 40
+            "value": 1.545895284739113,
+            "min": 1.545895284739113,
+            "max": 1.6852988610044122,
+            "count": 20
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.015106265140828955,
-            "min": 0.001978774983687255,
-            "max": 0.015877475243530104,
-            "count": 40
+            "value": 0.014486338870221896,
+            "min": 0.012602381536685156,
+            "max": 0.016407988183750097,
+            "count": 20
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.34744409823906597,
-            "min": 0.0400164191713699,
-            "max": 0.38105940584472253,
-            "count": 40
+            "value": 0.3476721328853255,
+            "min": 0.3024571568804437,
+            "max": 0.3937917164100023,
+            "count": 20
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 3.776994393208696e-06,
-            "min": 3.776994393208696e-06,
-            "max": 0.00029583776924455355,
-            "count": 40
+            "value": 2.5669449777180556e-06,
+            "min": 2.5669449777180556e-06,
+            "max": 9.750826749726666e-05,
+            "count": 20
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 8.687087104380001e-05,
-            "min": 8.687087104380001e-05,
-            "max": 0.006351212032929351,
-            "count": 40
+            "value": 6.160667946523334e-05,
+            "min": 6.160667946523334e-05,
+            "max": 0.002242690152437133,
+            "count": 20
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1012589652173913,
-            "min": 0.1012589652173913,
-            "max": 0.1986125892857143,
-            "count": 40
+            "value": 0.10085561527777777,
+            "min": 0.10085561527777777,
+            "max": 0.13250273333333334,
+            "count": 20
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 2.3289562,
-            "min": 2.3289562,
-            "max": 4.4103963,
-            "count": 40
+            "value": 2.4205347666666666,
+            "min": 2.3578400333333334,
+            "max": 3.1405211000000004,
+            "count": 20
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0001357706252173913,
-            "min": 0.0001357706252173913,
-            "max": 0.009861397669642854,
-            "count": 40
+            "value": 9.547596625000002e-05,
+            "min": 9.547596625000002e-05,
+            "max": 0.0032570230599999997,
+            "count": 20
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.00312272438,
-            "min": 0.00312272438,
-            "max": 0.21171535793500001,
-            "count": 40
+            "value": 0.0022914231900000004,
+            "min": 0.0022914231900000004,
+            "max": 0.07491153038,
+            "count": 20
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.009165954776108265,
-            "min": 0.009165954776108265,
-            "max": 0.33213332295417786,
-            "count": 40
+            "value": 0.007792776916176081,
+            "min": 0.007732097525149584,
+            "max": 0.008955762721598148,
+            "count": 20
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.21081696450710297,
-            "min": 0.21081696450710297,
-            "max": 4.649866580963135,
-            "count": 40
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 246.87623762376236,
-            "min": 243.32682926829267,
-            "max": 985.9375,
-            "count": 40
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 49869.0,
-            "min": 46862.0,
-            "max": 52195.0,
-            "count": 40
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.7234088959965375,
-            "min": -0.9035542171138028,
-            "max": 1.7450465891980431,
-            "count": 40
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 348.1285969913006,
-            "min": -43.370602421462536,
-            "max": 359.47959737479687,
-            "count": 40
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.7234088959965375,
-            "min": -0.9035542171138028,
-            "max": 1.7450465891980431,
-            "count": 40
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 348.1285969913006,
-            "min": -43.370602421462536,
-            "max": 359.47959737479687,
-            "count": 40
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.023520248840555938,
-            "min": 0.023520248840555938,
-            "max": 4.848506656708196,
-            "count": 40
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 4.7510902657923,
-            "min": 4.728349542085198,
-            "max": 232.7283195219934,
-            "count": 40
+            "value": 0.18702664971351624,
+            "min": 0.17860160768032074,
+            "max": 0.21310660243034363,
+            "count": 20
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 40
+            "count": 20
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 40
+            "count": 20
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673831055",
+        "start_time_seconds": "1673836158",
         "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",
+        "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 --resume",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1673835599"
+        "end_time_seconds": "1673838641"
     },
-    "total": 4543.838225563,
+    "total": 2483.075905697,
     "count": 1,
-    "self": 0.5960226670003976,
+    "self": 0.47737065899946174,
     "children": {
         "run_training.setup": {
-            "total": 0.12589435799998228,
+            "total": 0.11172813800021686,
             "count": 1,
-            "self": 0.12589435799998228
+            "self": 0.11172813800021686
         },
         "TrainerController.start_learning": {
-            "total": 4543.116308538,
+            "total": 2482.4868069000004,
             "count": 1,
-            "self": 2.53086013695156,
+            "self": 1.3851928860194676,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 9.631875206000018,
+                    "total": 7.490744086000632,
                     "count": 1,
-                    "self": 9.631875206000018
+                    "self": 7.490744086000632
                 },
                 "TrainerController.advance": {
-                    "total": 4530.822265361048,
-                    "count": 129546,
-                    "self": 2.75618783106529,
+                    "total": 2473.4792359459807,
+                    "count": 65829,
+                    "self": 1.371010698991995,
                     "children": {
                         "env_step": {
-                            "total": 3125.71005376904,
-                            "count": 129546,
-                            "self": 2902.199031741154,
+                            "total": 1755.0665009760141,
+                            "count": 65829,
+                            "self": 1642.3319941180134,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 221.89606513703376,
-                                    "count": 129546,
-                                    "self": 8.891637529068419,
+                                    "total": 111.87143168506373,
+                                    "count": 65829,
+                                    "self": 4.56403568001042,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 213.00442760796534,
-                                            "count": 125058,
-                                            "self": 68.88413067501307,
+                                            "total": 107.3073960050533,
+                                            "count": 62561,
+                                            "self": 34.565441578009086,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 144.12029693295227,
-                                                    "count": 125058,
-                                                    "self": 144.12029693295227
+                                                    "total": 72.74195442704422,
+                                                    "count": 62561,
+                                                    "self": 72.74195442704422
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.6149568908521132,
-                                    "count": 129546,
+                                    "total": 0.8630751729369877,
+                                    "count": 65829,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 4534.084476353929,
-                                            "count": 129546,
+                                            "total": 2477.5349528958795,
+                                            "count": 65829,
                                             "is_parallel": true,
-                                            "self": 1840.0976748749172,
+                                            "self": 941.798201854871,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0077296580000165704,
+                                                            "total": 0.0018249739996463177,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0032698439999307993,
+                                                            "self": 0.0006835149988546618,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.004459814000085771,
+                                                                    "total": 0.0011414590007916559,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.004459814000085771
+                                                                    "self": 0.0011414590007916559
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.048913362999996934,
+                                                            "total": 0.046527577999768255,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0004918169999541533,
+                                                            "self": 0.0005311889999575214,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005283230000259209,
+                                                                    "total": 0.00047280000035243575,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005283230000259209
+                                                                    "self": 0.00047280000035243575
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04620942400003969,
+                                                                    "total": 0.043776605999482854,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04620942400003969
+                                                                    "self": 0.043776605999482854
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016837989999771708,
+                                                                    "total": 0.0017469829999754438,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00046671500001593813,
+                                                                    "self": 0.00042640600076992996,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0012170839999612326,
+                                                                            "total": 0.0013205769992055139,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0012170839999612326
+                                                                            "self": 0.0013205769992055139
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 2693.986801479012,
-                                                    "count": 129545,
+                                                    "total": 1535.7367510410086,
+                                                    "count": 65828,
                                                     "is_parallel": true,
-                                                    "self": 57.07145611872829,
+                                                    "self": 28.49123857068389,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 48.814293096192785,
-                                                            "count": 129545,
+                                                            "total": 24.478330455015566,
+                                                            "count": 65828,
                                                             "is_parallel": true,
-                                                            "self": 48.814293096192785
+                                                            "self": 24.478330455015566
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2388.96977148709,
-                                                            "count": 129545,
+                                                            "total": 1372.5174271900978,
+                                                            "count": 65828,
                                                             "is_parallel": true,
-                                                            "self": 2388.96977148709
+                                                            "self": 1372.5174271900978
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 199.131280777001,
-                                                            "count": 129545,
+                                                            "total": 110.24975482521131,
+                                                            "count": 65828,
                                                             "is_parallel": true,
-                                                            "self": 46.97348018092839,
+                                                            "self": 24.411026114208653,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 152.1578005960726,
-                                                                    "count": 1036360,
+                                                                    "total": 85.83872871100266,
+                                                                    "count": 526624,
                                                                     "is_parallel": true,
-                                                                    "self": 152.1578005960726
+                                                                    "self": 85.83872871100266
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1402.3560237609431,
-                            "count": 129546,
-                            "self": 5.057746946869656,
+                            "total": 717.0417242709746,
+                            "count": 65829,
+                            "self": 2.721929752822689,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 313.7211487850659,
-                                    "count": 129546,
-                                    "self": 313.1898563630659,
+                                    "total": 166.9367507981533,
+                                    "count": 65829,
+                                    "self": 166.64181473115332,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.5312924219999786,
-                                            "count": 4,
-                                            "self": 0.5312924219999786
+                                            "total": 0.29493606699998054,
+                                            "count": 2,
+                                            "self": 0.29493606699998054
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1083.5771280290076,
-                                    "count": 932,
-                                    "self": 416.6385965120131,
+                                    "total": 547.3830437199986,
+                                    "count": 473,
+                                    "self": 202.48593196505044,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 666.9385315169944,
-                                            "count": 45561,
-                                            "self": 666.9385315169944
+                                            "total": 344.8971117549481,
+                                            "count": 22746,
+                                            "self": 344.8971117549481
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.080005500232801e-07,
+                    "total": 1.0750000001280569e-06,
                     "count": 1,
-                    "self": 8.080005500232801e-07
+                    "self": 1.0750000001280569e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.131307026000286,
+                    "total": 0.13163290699958452,
                     "count": 1,
-                    "self": 0.002107295999849157,
+                    "self": 0.0030283289997896645,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12919973000043683,
+                            "total": 0.12860457799979486,
                             "count": 1,
-                            "self": 0.12919973000043683
+                            "self": 0.12860457799979486
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499941,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499941.onnx",
-                "reward": null,
-                "creation_time": 1673832058.9279318,
+                "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-499941.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1999915.pt"
                 ]
             },
             {
-                "steps": 999926,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999926.onnx",
-                "reward": 1.123999923467636,
-                "creation_time": 1673833177.4576147,
+                "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-999926.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2000043.pt"
                 ]
             },
             {
-                "steps": 1499934,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499934.onnx",
-                "reward": 1.5677499920129776,
-                "creation_time": 1673834372.5188894,
+                "steps": 2499958,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499958.onnx",
+                "reward": null,
+                "creation_time": 1673837412.9403822,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1499934.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2499958.pt"
                 ]
             },
             {
-                "steps": 1999915,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999915.onnx",
-                "reward": 1.604836344718933,
-                "creation_time": 1673835598.9930935,
+                "steps": 2999960,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999960.onnx",
+                "reward": 1.7033999979496002,
+                "creation_time": 1673838641.1140106,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1999915.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2999960.pt"
                 ]
             },
             {
-                "steps": 2000043,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2000043.onnx",
-                "reward": 1.604836344718933,
-                "creation_time": 1673835599.1385298,
+                "steps": 3000055,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000055.onnx",
+                "reward": 1.737166667977969,
+                "creation_time": 1673838641.2576628,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-2000043.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-3000055.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000043,
+            "steps": 3000055,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.604836344718933,
-            "creation_time": 1673835599.1385298,
+            "reward": 1.737166667977969,
+            "creation_time": 1673838641.2576628,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-2000043.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-3000055.pt"
             ]
         }
     },