lowered max_iterations

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96891ce684d7da08f007b5ee257ef4dd244e780b48db73501c3774ae5939e1d6
+oid sha256:c614025fe9c6a150d99edcee772815ef897d6e8f906c04ed0b1598b533f76de3
 size 1420238

Pyramids/Pyramids-1048670.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c614025fe9c6a150d99edcee772815ef897d6e8f906c04ed0b1598b533f76de3
+size 1420238

Pyramids/Pyramids-1048670.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ac0ec3d49ef7881f31dbc539d832002ba71f7568d808309e095ffcf2abe681
+size 10002044

Pyramids/Pyramids-499873.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01db9e7cb5b7b82c1b25fe8d9a46ffe932063eebf9a3ee20f9534bf5fced2cb
+size 1420238

Pyramids/Pyramids-499873.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de74d2df7a06eb766e11eb2205248a031118b2edcbdb6e63b595f6746c6305f3
+size 10001965

Pyramids/Pyramids-999896.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9187acdeffc04d293bace613b2875fb184b8aa0ce0291e16e3abaf83e8acda13
+size 1420238

Pyramids/Pyramids-999896.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ba6e4114f6718a2eaa4804aa0f5bbe291161caf38095fd113e773ebf98559f
+size 10001965

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fd7ae826fac5a1ab9f4ceb603c0f4b545dc3d4ab0433d57da45dc6660294669
+oid sha256:aa6b6bfc6ebabc50a99a115b39a14a0313bc5af445e47cf0e545f7d24ee2be4f
 size 10001506

Pyramids/events.out.tfevents.1738524599.hrichter-5950x.25015.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f1e53176af9971be1ea82a0347a548abeb53481c662c902a6f5b128f633016
+size 327191

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/home/hrichter/projects/hf_rl_course/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/home/hrichter/projects/hf_rl_course/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 3 interfaces on host : 0) 192.168.101.72 1) 10.113.249.15 2) 172.17.0.1
-Multi-casting "[IP] 192.168.101.72 [Port] 55186 [Flags] 2 [Guid] 652531144 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.101.72) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 192.168.101.72 [Port] 55208 [Flags] 2 [Guid] 2271002728 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.101.72) [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: /home/hrichter/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /home/hrichter/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /home/hrichter/projects/hf_rl_course/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -16,7 +13,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.058 seconds
+- Completed reload, in  0.066 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)
@@ -48,7 +45,7 @@ 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: 0.500290 ms
+UnloadTime: 0.854601 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 16 worker threads for Enlighten.
@@ -56,7 +53,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 15850 frames, [32.0 KB-64.0 KB]: 2584 frames, [64.0 KB-128.0 KB]: 1241 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 16698 frames, [32.0 KB-64.0 KB]: 1596 frames, [64.0 KB-128.0 KB]: 1385 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
@@ -64,7 +61,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 18]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 8]
       Initial Block Size 32.0 KB
@@ -146,17 +143,22 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 14]
+    [ALLOC_TEMP_Job.Worker 17]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 17]
+    [ALLOC_TEMP_Job.Worker 3]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 3]
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -176,21 +178,11 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Profiler.Dispatcher]
-      Initial Block Size 64.0 KB
-      Current Block Size 64.0 KB
-      Peak Allocated Bytes 3.8 KB
-      Overflow Count 0
     [ALLOC_TEMP_Job.Worker 11]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 6]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
@@ -201,9 +193,9 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_EnlightenWorker] x 16
@@ -216,6 +208,11 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [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_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
@@ -251,12 +248,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 26]
+    [ALLOC_TEMP_Job.Worker 30]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 30]
+    [ALLOC_TEMP_Job.Worker 26]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -281,12 +278,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 1]
+    [ALLOC_TEMP_Job.Worker 23]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 23]
+    [ALLOC_TEMP_Job.Worker 1]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -294,7 +291,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 24]
       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 12]
       Initial Block Size 32.0 KB
@@ -337,28 +334,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 19377 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 19381 frames
   Requested Block Size 1.0 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 12810
+  Peak main deferred allocation count 11550
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       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]: 19675 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 19679 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.3 MB
+      Peak Allocated memory 30.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 19676 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 19680 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 30.8 MB
+      Peak Allocated memory 30.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -387,13 +384,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 19675 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 19679 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]: 19676 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 19680 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -405,13 +402,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 19377 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 19381 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]: 19675 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 19679 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
@@ -423,25 +420,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 19676 frames
+      Peak usage frame count: [0-1.0 KB]: 19680 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]: 19676 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 19680 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: [32.0 KB-64.0 KB]: 19676 frames
+  Peak usage frame count: [32.0 KB-64.0 KB]: 19680 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 54.4 KB
+  Peak Allocated memory 53.6 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":1738511213892,"processId":21381,"allocatedMemory":2006255,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":35300},{"Manager":33551},{"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":3541},{"DynamicArray":30868},{"HashMap":7680},{"Utility":13600},{"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":1738525559746,"processId":25112,"allocatedMemory":2006255,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":35300},{"Manager":33551},{"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":3541},{"DynamicArray":30868},{"HashMap":7680},{"Utility":13600},{"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

@@ -2,183 +2,183 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.4543474614620209,
-            "min": 0.4543474614620209,
-            "max": 1.5112195014953613,
+            "value": 0.37492474913597107,
+            "min": 0.36654171347618103,
+            "max": 1.472686529159546,
             "count": 34
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 13608.615234375,
-            "min": 13608.615234375,
-            "max": 45844.35546875,
+            "value": 11295.732421875,
+            "min": 10978.6572265625,
+            "max": 44675.41796875,
             "count": 34
         },
         "Pyramids.Step.mean": {
-            "value": 1019962.0,
+            "value": 1019999.0,
             "min": 29952.0,
-            "max": 1019962.0,
+            "max": 1019999.0,
             "count": 34
         },
         "Pyramids.Step.sum": {
-            "value": 1019962.0,
+            "value": 1019999.0,
             "min": 29952.0,
-            "max": 1019962.0,
+            "max": 1019999.0,
             "count": 34
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.06637323647737503,
-            "min": -0.0984974354505539,
-            "max": 0.05833796411752701,
+            "value": -0.03032447025179863,
+            "min": -0.20310690999031067,
+            "max": -0.03032447025179863,
             "count": 34
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -15.995950698852539,
-            "min": -23.44239044189453,
-            "max": 13.82609748840332,
+            "value": -7.429495334625244,
+            "min": -48.13633728027344,
+            "max": -7.429495334625244,
             "count": 34
         },
         "Pyramids.Policy.CuriosityValueEstimate.mean": {
-            "value": 0.172653928399086,
-            "min": 0.172653928399086,
-            "max": 0.6127722263336182,
+            "value": 0.1564064770936966,
+            "min": 0.1564064770936966,
+            "max": 0.44639909267425537,
             "count": 34
         },
         "Pyramids.Policy.CuriosityValueEstimate.sum": {
-            "value": 41.609596252441406,
-            "min": 41.609596252441406,
-            "max": 147.06533813476562,
+            "value": 38.31958770751953,
+            "min": 38.210716247558594,
+            "max": 108.02857971191406,
             "count": 34
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06753937733212566,
-            "min": 0.06403414026754138,
-            "max": 0.07400685542682015,
+            "value": 0.06718603229835869,
+            "min": 0.06478804335382495,
+            "max": 0.07394896972318263,
             "count": 34
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9455512826497593,
-            "min": 0.5008653629779944,
-            "max": 1.0311151000042789,
+            "value": 0.9406044521770217,
+            "min": 0.49618800863758766,
+            "max": 1.0529568219661836,
             "count": 34
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0010010373539647926,
-            "min": 0.00022825133976742587,
-            "max": 0.004660744971986814,
+            "value": 0.002840339800961007,
+            "min": 0.00012460844201482606,
+            "max": 0.004310364597613544,
             "count": 34
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.014014522955507097,
-            "min": 0.0025107647374416845,
-            "max": 0.04636992843615743,
+            "value": 0.0397647572134541,
+            "min": 0.0017445181882075648,
+            "max": 0.06034510436658962,
             "count": 34
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 1.2229129802526743e-05,
-            "min": 1.2229129802526743e-05,
+            "value": 1.2261868068504335e-05,
+            "min": 1.2261868068504335e-05,
             "max": 0.0002953752805594308,
             "count": 34
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00017120781723537441,
-            "min": 0.00017120781723537441,
-            "max": 0.0029310438478633875,
+            "value": 0.00017166615295906068,
+            "min": 0.00017166615295906068,
+            "max": 0.0036590319529362673,
             "count": 34
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10407634462629045,
-            "min": 0.10407634462629045,
+            "value": 0.10408725738525391,
+            "min": 0.10408725738525391,
             "max": 0.19845842633928573,
             "count": 34
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4570688247680663,
-            "min": 1.3304809570312501,
-            "max": 2.2465369224548337,
+            "value": 1.4572216033935548,
+            "min": 1.3892089843750002,
+            "max": 2.6196772575378415,
             "count": 34
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0004172268281664167,
-            "min": 0.0004172268281664167,
+            "value": 0.00041831701278686524,
+            "min": 0.00041831701278686524,
             "max": 0.009845996791294642,
             "count": 34
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.005841175594329834,
-            "min": 0.005841175594329834,
-            "max": 0.09772375270843506,
+            "value": 0.005856438179016113,
+            "min": 0.005856438179016113,
+            "max": 0.12198575802803038,
             "count": 34
         },
         "Pyramids.Losses.CuriosityForwardLoss.mean": {
-            "value": 0.07906412933783538,
-            "min": 0.07906412933783538,
-            "max": 0.46284705355812367,
+            "value": 0.07406188456076836,
+            "min": 0.07187406965550976,
+            "max": 0.41989175825378267,
             "count": 34
         },
         "Pyramids.Losses.CuriosityForwardLoss.sum": {
-            "value": 1.1068978107296954,
-            "min": 1.1068978107296954,
-            "max": 3.2399293749068656,
+            "value": 1.036866383850757,
+            "min": 0.9707603916233661,
+            "max": 2.9392423077764787,
             "count": 34
         },
         "Pyramids.Losses.CuriosityInverseLoss.mean": {
-            "value": 0.07675328405852935,
-            "min": 0.07675328405852935,
-            "max": 0.7302169783074525,
+            "value": 0.06697648263649547,
+            "min": 0.06312481397228102,
+            "max": 0.7277615498644353,
             "count": 34
         },
         "Pyramids.Losses.CuriosityInverseLoss.sum": {
-            "value": 1.074545976819411,
-            "min": 1.074545976819411,
-            "max": 5.111518848152167,
+            "value": 0.9376707569109366,
+            "min": 0.8529724184858529,
+            "max": 5.0943308490510475,
             "count": 34
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 983.34375,
-            "min": 902.3333333333334,
+            "value": 899.060606060606,
+            "min": 881.741935483871,
             "max": 999.0,
             "count": 34
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31467.0,
+            "value": 29669.0,
             "min": 15984.0,
-            "max": 31977.0,
+            "max": 33110.0,
             "count": 34
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.8589000543579459,
+            "value": -0.4147697470404885,
             "min": -1.0000000521540642,
-            "max": -0.4543032689440635,
+            "max": -0.23707746089466156,
             "count": 34
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -27.48480173945427,
-            "min": -32.000001668930054,
-            "max": -14.083401337265968,
+            "value": -13.68740165233612,
+            "min": -31.99360166490078,
+            "max": -7.3494012877345085,
             "count": 34
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.8589000543579459,
+            "value": -0.4147697470404885,
             "min": -1.0000000521540642,
-            "max": -0.4543032689440635,
+            "max": -0.23707746089466156,
             "count": 34
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -27.48480173945427,
-            "min": -32.000001668930054,
-            "max": -14.083401337265968,
+            "value": -13.68740165233612,
+            "min": -31.99360166490078,
+            "max": -7.3494012877345085,
             "count": 34
         },
         "Pyramids.Policy.CuriosityReward.mean": {
-            "value": 1.652078541344963,
-            "min": 1.652078541344963,
-            "max": 7.098222507163882,
+            "value": 1.3701743991537527,
+            "min": 1.3701743991537527,
+            "max": 6.27729257196188,
             "count": 34
         },
         "Pyramids.Policy.CuriosityReward.sum": {
-            "value": 52.86651332303882,
-            "min": 43.25800512731075,
-            "max": 227.14312022924423,
+            "value": 45.21575517207384,
+            "min": 45.21575517207384,
+            "max": 174.45192439109087,
             "count": 34
         },
         "Pyramids.IsTraining.mean": {
@@ -196,7 +196,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1738510301",
+        "start_time_seconds": "1738524599",
         "python_version": "3.10.16 (main, Dec  4 2024, 08:53:38) [GCC 13.2.0]",
         "command_line_arguments": "/home/hrichter/projects/hf_rl_course/.venv/bin/mlagents-learn ml-agents/config/ppo/Pyramids.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
         "mlagents_version": "1.2.0.dev0",
@@ -204,59 +204,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.5.1+cu124",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1738511213"
+        "end_time_seconds": "1738525559"
     },
-    "total": 912.3542327689997,
+    "total": 960.69417054,
     "count": 1,
-    "self": 0.21796088999963104,
+    "self": 0.21820811000020512,
     "children": {
         "run_training.setup": {
-            "total": 0.015217674000268744,
+            "total": 0.014896433999865621,
             "count": 1,
-            "self": 0.015217674000268744
+            "self": 0.014896433999865621
         },
         "TrainerController.start_learning": {
-            "total": 912.1210542049998,
+            "total": 960.4610659959999,
             "count": 1,
-            "self": 0.6126094490464311,
+            "self": 0.6438697869684802,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.3287241719999656,
+                    "total": 1.2939183309999862,
                     "count": 1,
-                    "self": 1.3287241719999656
+                    "self": 1.2939183309999862
                 },
                 "TrainerController.advance": {
-                    "total": 910.1381253989539,
-                    "count": 66017,
-                    "self": 0.5998701820549286,
+                    "total": 958.4810456990313,
+                    "count": 66200,
+                    "self": 0.6672122379852681,
                     "children": {
                         "env_step": {
-                            "total": 485.25273342594437,
-                            "count": 66017,
-                            "self": 444.6313050909266,
+                            "total": 516.2186331370485,
+                            "count": 66200,
+                            "self": 472.8256553351712,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 40.23746882602245,
-                                    "count": 66017,
-                                    "self": 1.9413799550957265,
+                                    "total": 42.98896845993613,
+                                    "count": 66200,
+                                    "self": 2.0265824469049676,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 38.296088870926724,
-                                            "count": 65585,
-                                            "self": 38.296088870926724
+                                            "total": 40.962386013031164,
+                                            "count": 65598,
+                                            "self": 40.962386013031164
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.3839595089953036,
-                                    "count": 66017,
+                                    "total": 0.40400934194121874,
+                                    "count": 66200,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 911.1650806679077,
-                                            "count": 66017,
+                                            "total": 959.4559383770147,
+                                            "count": 66200,
                                             "is_parallel": true,
-                                            "self": 511.17713061890663,
+                                            "self": 533.8106512569464,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0009802099998523772,
+                                                            "total": 0.0009145409999291587,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000247952999870904,
+                                                            "self": 0.00022774500007471943,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0007322569999814732,
+                                                                    "total": 0.0006867959998544393,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007322569999814732
+                                                                    "self": 0.0006867959998544393
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.020602015999884316,
+                                                            "total": 0.018782304000069416,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00018806199932441814,
+                                                            "self": 0.0003025040000466106,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00019271200017101364,
+                                                                    "total": 0.0002825439999014634,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00019271200017101364
+                                                                    "self": 0.0002825439999014634
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.019664047000333085,
+                                                                    "total": 0.01733245400009764,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.019664047000333085
+                                                                    "self": 0.01733245400009764
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.000557195000055799,
+                                                                    "total": 0.0008648020000237011,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00013419100014289143,
+                                                                    "self": 0.0001828549998208473,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0004230039999129076,
+                                                                            "total": 0.0006819470002028538,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0004230039999129076
+                                                                            "self": 0.0006819470002028538
                                                                         }
                                                                     }
                                                                 }
@@ -315,34 +315,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 399.98795004900103,
-                                                    "count": 66016,
+                                                    "total": 425.64528712006836,
+                                                    "count": 66199,
                                                     "is_parallel": true,
-                                                    "self": 11.616755930049294,
+                                                    "self": 11.960250902025791,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 8.229266628003643,
-                                                            "count": 66016,
+                                                            "total": 8.491987588990696,
+                                                            "count": 66199,
                                                             "is_parallel": true,
-                                                            "self": 8.229266628003643
+                                                            "self": 8.491987588990696
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 346.46593935402007,
-                                                            "count": 66016,
+                                                            "total": 370.419048640038,
+                                                            "count": 66199,
                                                             "is_parallel": true,
-                                                            "self": 346.46593935402007
+                                                            "self": 370.419048640038
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 33.67598813692803,
-                                                            "count": 66016,
+                                                            "total": 34.77399998901387,
+                                                            "count": 66199,
                                                             "is_parallel": true,
-                                                            "self": 7.211483213929569,
+                                                            "self": 7.488494236913766,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 26.464504922998458,
-                                                                    "count": 528128,
+                                                                    "total": 27.285505752100107,
+                                                                    "count": 529592,
                                                                     "is_parallel": true,
-                                                                    "self": 26.464504922998458
+                                                                    "self": 27.285505752100107
                                                                 }
                                                             }
                                                         }
@@ -355,31 +355,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 424.2855217909546,
-                            "count": 66017,
-                            "self": 1.111752062913638,
+                            "total": 441.59520032399746,
+                            "count": 66200,
+                            "self": 1.3063789900720622,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 60.70824232404675,
-                                    "count": 66017,
-                                    "self": 60.62343418304681,
+                                    "total": 63.53832344492298,
+                                    "count": 66200,
+                                    "self": 63.442949675923046,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.0848081409999395,
+                                            "total": 0.09537376899993433,
                                             "count": 2,
-                                            "self": 0.0848081409999395
+                                            "self": 0.09537376899993433
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 362.4655274039942,
-                                    "count": 445,
-                                    "self": 237.48609379300842,
+                                    "total": 376.7504978890024,
+                                    "count": 469,
+                                    "self": 251.99174821898123,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 124.97943361098578,
-                                            "count": 23931,
-                                            "self": 124.97943361098578
+                                            "total": 124.75874967002119,
+                                            "count": 23895,
+                                            "self": 124.75874967002119
                                         }
                                     }
                                 }
@@ -388,19 +388,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 5.699998837371822e-07,
+                    "total": 7.300000106624793e-07,
                     "count": 1,
-                    "self": 5.699998837371822e-07
+                    "self": 7.300000106624793e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0415946149996671,
+                    "total": 0.04223144900015541,
                     "count": 1,
-                    "self": 0.0010204019999946468,
+                    "self": 0.0018124279999938153,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.040574212999672454,
+                            "total": 0.04041902100016159,
                             "count": 1,
-                            "self": 0.040574212999672454
+                            "self": 0.04041902100016159
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499897,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499897.onnx",
-                "reward": -1.0000000521540642,
-                "creation_time": 1738510731.9819715,
+                "steps": 499873,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499873.onnx",
+                "reward": -0.9994000494480133,
+                "creation_time": 1738525043.464673,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499897.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499873.pt"
                 ]
             },
             {
-                "steps": 999894,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999894.onnx",
-                "reward": null,
-                "creation_time": 1738511171.0059083,
+                "steps": 999896,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999896.onnx",
+                "reward": 1.3289999514818192,
+                "creation_time": 1738525513.1658812,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999894.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999896.pt"
                 ]
             },
             {
-                "steps": 1048626,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1048626.onnx",
-                "reward": 0.022899948060512543,
-                "creation_time": 1738511213.7234762,
+                "steps": 1048670,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1048670.onnx",
+                "reward": -0.22300003468990326,
+                "creation_time": 1738525559.5502157,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1048626.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1048670.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1048626,
+            "steps": 1048670,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 0.022899948060512543,
-            "creation_time": 1738511213.7234762,
+            "reward": -0.22300003468990326,
+            "creation_time": 1738525559.5502157,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1048626.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1048670.pt"
             ]
         }
     },