v1 model commit

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27ac8ad77972b3c87cad73233e62afd9a345464eb72651616f12bb3914828cc3
+oid sha256:29aecd9da55663f4e6da738686fe8fe1bf3bb05d09d4f5c84df236d2b5db4fc4
 size 1420238

Pyramids/Pyramids-3499995.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39cb6974ca1b0ecd9f6e0828cfc4ad32e527724ecd4f4e6a086f2f9c9368610c
+size 1420238

Pyramids/Pyramids-3499995.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e52ff14b3269ecd510dd8c0b755112596fbc59e9717ae2e80700d0c752d96bc
+size 8655228

Pyramids/Pyramids-3999878.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b8a0a703472187d0156d029ec7fee5afdc2a16ea18c9dc48e253b2609ee0d86
+size 1420238

Pyramids/Pyramids-3999878.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575da6e6e9ef07a4f17f60914e077c27d20bd8abc6113264f7b65669bda1f361
+size 8655228

Pyramids/Pyramids-4499887.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc9b8d1d7518ea9642be70f387ad14b3b81a581bd5806292a80b6874b35a3870
+size 1420238

Pyramids/Pyramids-4499887.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2318cc8dd6d56facca729c0093c8763ab23b57ff7f0f05b471b2ed1722b1500c
+size 8655228

Pyramids/Pyramids-4999937.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29aecd9da55663f4e6da738686fe8fe1bf3bb05d09d4f5c84df236d2b5db4fc4
+size 1420238

Pyramids/Pyramids-4999937.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab33693c6042f3b849823709f9df6af0ca3e73747efe20b291ba2d62536da2a3
+size 8655228

Pyramids/Pyramids-5000065.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29aecd9da55663f4e6da738686fe8fe1bf3bb05d09d4f5c84df236d2b5db4fc4
+size 1420238

Pyramids/Pyramids-5000065.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf163433d233469a0670b364a4a64f289c7b159045131032d56bd0a1a067afdb
+size 8655228

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43a89fecd051b5f0c18b59c32edd0afa9a25e03002890e9e6900361dc061f835
+oid sha256:f90bf751f27f5d80f83b2de5463c3a2fbc6ccab8f9c0a4fc15f9271ff5b55c23
 size 8654754

Pyramids/events.out.tfevents.1734987363.2481a850ebf0.98169.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557c57341f9f0591788bd078a8506c318334ba8c59b91e756c17a1f5fa7aaeee
+size 1608147

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55022 [Flags] 2 [Guid] 2616298168 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55124 [Flags] 2 [Guid] 19483045 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,7 +33,7 @@ ALSA lib pcm.c:2664:(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  0.139 seconds
+- Completed reload, in  0.207 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -65,7 +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: 1.173293 ms
+UnloadTime: 1.469596 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -73,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 14136 frames, [32.0 KB-64.0 KB]: 64005 frames, [64.0 KB-128.0 KB]: 15625 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 4091 frames, [32.0 KB-64.0 KB]: 65463 frames, [64.0 KB-128.0 KB]: 24210 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
@@ -146,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -204,28 +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]: 93468 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 93466 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.5 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12366
+  Peak main deferred allocation count 11151
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 93766 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 93764 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 29.8 MB
+      Peak Allocated memory 30.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 93767 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 93765 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 24.1 MB
+      Peak Allocated memory 22.0 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -252,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 93766 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 93764 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]: 93767 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 93765 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -270,39 +270,39 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 93468 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 93466 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]: 93766 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 93764 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 2
-      Peak Allocated memory 4.7 MB
+      Peak Block count 1
+      Peak Allocated memory 3.9 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 93767 frames
+      Peak usage frame count: [0-1.0 KB]: 93765 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]: 93767 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 93765 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]: 93767 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 93765 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -311,4 +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":1734987042577,"processId":29534,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":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":1735005229334,"processId":98214,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":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

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.20263810455799103,
-            "min": 0.18606819212436676,
-            "max": 1.5211589336395264,
+            "value": 0.1565660834312439,
+            "min": 0.1565660834312439,
+            "max": 1.5110344886779785,
             "count": 166
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 6024.025390625,
-            "min": 5519.52685546875,
-            "max": 46145.87890625,
+            "value": 4707.0029296875,
+            "min": 4707.0029296875,
+            "max": 45838.7421875,
             "count": 166
         },
         "Pyramids.Step.mean": {
-            "value": 4979908.0,
-            "min": 29952.0,
-            "max": 4979908.0,
+            "value": 4979915.0,
+            "min": 29896.0,
+            "max": 4979915.0,
             "count": 166
         },
         "Pyramids.Step.sum": {
-            "value": 4979908.0,
-            "min": 29952.0,
-            "max": 4979908.0,
+            "value": 4979915.0,
+            "min": 29896.0,
+            "max": 4979915.0,
             "count": 166
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.5474892854690552,
-            "min": -0.11868464946746826,
-            "max": 0.6541125774383545,
+            "value": 0.7596249580383301,
+            "min": -0.09912478178739548,
+            "max": 0.8510122299194336,
             "count": 166
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 156.03443908691406,
-            "min": -28.484315872192383,
-            "max": 187.07620239257812,
+            "value": 224.08937072753906,
+            "min": -23.789947509765625,
+            "max": 251.6753692626953,
             "count": 166
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.003891777480021119,
-            "min": -0.0001794881682144478,
-            "max": 0.40868350863456726,
+            "value": 0.006613036151975393,
+            "min": -0.010047239251434803,
+            "max": 0.41730430722236633,
             "count": 166
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 1.109156608581543,
-            "min": -0.044333577156066895,
-            "max": 96.85799407958984,
+            "value": 1.950845718383789,
+            "min": -2.5319042205810547,
+            "max": 98.901123046875,
             "count": 166
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06785497067626454,
-            "min": 0.06456926350795836,
-            "max": 0.07412152656283737,
+            "value": 0.06918241804227114,
+            "min": 0.06377434989415286,
+            "max": 0.0774429734715659,
             "count": 166
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9499695894677037,
-            "min": 0.48167031040417174,
-            "max": 1.066803775014705,
+            "value": 0.9685538525917959,
+            "min": 0.6041385523189573,
+            "max": 1.1208737455502462,
             "count": 166
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.04457872647271004,
-            "min": 0.0001203750704734234,
-            "max": 0.0499658899295016,
+            "value": 0.04013408112736856,
+            "min": 0.00024820707498477806,
+            "max": 0.05166137777930856,
             "count": 166
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.6241021706179405,
-            "min": 0.0016852509866279277,
-            "max": 0.749488348942524,
+            "value": 0.5618771357831599,
+            "min": 0.002978484899817337,
+            "max": 0.7749206666896283,
             "count": 166
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.072876451931428e-06,
-            "min": 2.072876451931428e-06,
-            "max": 0.0002990301260375771,
+            "value": 2.053942172528571e-06,
+            "min": 2.053942172528571e-06,
+            "max": 0.0002990583003139,
             "count": 166
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 2.902027032703999e-05,
-            "min": 2.902027032703999e-05,
-            "max": 0.003985891631369479,
+            "value": 2.8755190415399995e-05,
+            "min": 2.8755190415399995e-05,
+            "max": 0.00398644741118422,
             "count": 166
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10069092571428571,
-            "min": 0.10069092571428571,
-            "max": 0.1996767085714286,
+            "value": 0.10068461428571429,
+            "min": 0.10068461428571429,
+            "max": 0.19968610000000003,
             "count": 166
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.40967296,
-            "min": 1.3977369600000003,
-            "max": 2.7286305200000003,
+            "value": 1.4095846,
+            "min": 1.4095846,
+            "max": 2.82450166,
             "count": 166
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 7.902347885714284e-05,
-            "min": 7.902347885714284e-05,
-            "max": 0.009967703186285714,
+            "value": 7.839296714285714e-05,
+            "min": 7.839296714285714e-05,
+            "max": 0.009968641390000001,
             "count": 166
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0011063287039999997,
-            "min": 0.0011063287039999997,
-            "max": 0.132870188948,
+            "value": 0.0010975015399999999,
+            "min": 0.0010975015399999999,
+            "max": 0.13288869642200002,
             "count": 166
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.002816483611240983,
-            "min": 0.0027454495429992676,
-            "max": 0.35313504934310913,
+            "value": 0.005115506239235401,
+            "min": 0.004736213944852352,
+            "max": 0.31785112619400024,
             "count": 166
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.03943077102303505,
-            "min": 0.038436293601989746,
-            "max": 2.471945285797119,
+            "value": 0.07161708921194077,
+            "min": 0.06630699336528778,
+            "max": 2.542809009552002,
             "count": 166
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 322.1847826086956,
-            "min": 276.578431372549,
+            "value": 241.38709677419354,
+            "min": 205.47972972972974,
             "max": 999.0,
             "count": 166
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29641.0,
-            "min": 15984.0,
-            "max": 33902.0,
+            "value": 29932.0,
+            "min": 16567.0,
+            "max": 34376.0,
             "count": 166
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.6361376101611762,
-            "min": -1.0000000521540642,
-            "max": 1.703809794111579,
+            "value": 1.726343543358868,
+            "min": -0.9999226331710815,
+            "max": 1.7945202548761625,
             "count": 166
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 152.1607977449894,
-            "min": -30.987801551818848,
-            "max": 173.78859899938107,
+            "value": 214.06659937649965,
+            "min": -31.996001675724983,
+            "max": 265.58899772167206,
             "count": 166
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.6361376101611762,
-            "min": -1.0000000521540642,
-            "max": 1.703809794111579,
+            "value": 1.726343543358868,
+            "min": -0.9999226331710815,
+            "max": 1.7945202548761625,
             "count": 166
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 152.1607977449894,
-            "min": -30.987801551818848,
-            "max": 173.78859899938107,
+            "value": 214.06659937649965,
+            "min": -31.996001675724983,
+            "max": 265.58899772167206,
             "count": 166
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.00944085115477191,
-            "min": 0.008513158594295793,
-            "max": 7.493621550500393,
+            "value": 0.013032083267849121,
+            "min": 0.011718307633133451,
+            "max": 5.836820939884467,
             "count": 166
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 0.8779991573937878,
-            "min": 0.8242430516984314,
-            "max": 119.89794480800629,
+            "value": 1.615978325213291,
+            "min": 1.4186316576087847,
+            "max": 99.22595597803593,
             "count": 166
         },
         "Pyramids.IsTraining.mean": {
@@ -184,7 +184,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1734970163",
+        "start_time_seconds": "1734987362",
         "python_version": "3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
         "mlagents_version": "1.2.0.dev0",
@@ -192,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.5.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1734987042"
+        "end_time_seconds": "1735005229"
     },
-    "total": 16878.847795566002,
+    "total": 17867.267364968004,
     "count": 1,
-    "self": 0.798003444000642,
+    "self": 0.8428121540055145,
     "children": {
         "run_training.setup": {
-            "total": 0.0724199280002722,
+            "total": 0.08742685800098116,
             "count": 1,
-            "self": 0.0724199280002722
+            "self": 0.08742685800098116
         },
         "TrainerController.start_learning": {
-            "total": 16877.977372194,
+            "total": 17866.337125955997,
             "count": 1,
-            "self": 12.471625841291825,
+            "self": 12.875868430684932,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.6637820199994167,
+                    "total": 3.051176987999497,
                     "count": 1,
-                    "self": 3.6637820199994167
+                    "self": 3.051176987999497
                 },
                 "TrainerController.advance": {
-                    "total": 16861.747509734705,
-                    "count": 319625,
-                    "self": 12.873840043728705,
+                    "total": 17850.31568798432,
+                    "count": 323137,
+                    "self": 13.148603702771652,
                     "children": {
                         "env_step": {
-                            "total": 11066.010913566362,
-                            "count": 319625,
-                            "self": 10203.38014739893,
+                            "total": 12121.302369412471,
+                            "count": 323137,
+                            "self": 11261.368638919383,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 855.4581128178334,
-                                    "count": 319625,
-                                    "self": 37.17884754494207,
+                                    "total": 852.5072753742788,
+                                    "count": 323137,
+                                    "self": 36.90964546420946,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 818.2792652728913,
-                                            "count": 312555,
-                                            "self": 818.2792652728913
+                                            "total": 815.5976299100694,
+                                            "count": 312548,
+                                            "self": 815.5976299100694
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 7.172653349599386,
-                                    "count": 319625,
+                                    "total": 7.426455118809827,
+                                    "count": 323137,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 16840.956668090013,
-                                            "count": 319625,
+                                            "total": 17827.616065522045,
+                                            "count": 323137,
                                             "is_parallel": true,
-                                            "self": 7561.997823861238,
+                                            "self": 7507.531310763992,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0032782139996925252,
+                                                            "total": 0.003829181001492543,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0009515169995211181,
+                                                            "self": 0.0012291770108276978,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.002326697000171407,
+                                                                    "total": 0.0026000039906648453,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.002326697000171407
+                                                                    "self": 0.0026000039906648453
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.13887105900084862,
+                                                            "total": 0.06282151399864233,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007677910007259925,
+                                                            "self": 0.0008316169951285701,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005996520003463957,
+                                                                    "total": 0.0005301090022840071,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005996520003463957
+                                                                    "self": 0.0005301090022840071
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.13546122400020977,
+                                                                    "total": 0.05940465100138681,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.13546122400020977
+                                                                    "self": 0.05940465100138681
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002042391999566462,
+                                                                    "total": 0.0020551369998429436,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004463499972189311,
+                                                                    "self": 0.00041780299943638965,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015960420023475308,
+                                                                            "total": 0.001637334000406554,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015960420023475308
+                                                                            "self": 0.001637334000406554
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 9278.958844228775,
-                                                    "count": 319624,
+                                                    "total": 10320.084754758052,
+                                                    "count": 323136,
                                                     "is_parallel": true,
-                                                    "self": 255.8220693386702,
+                                                    "self": 254.79581349675573,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 158.2712478019721,
-                                                            "count": 319624,
+                                                            "total": 152.1197451789485,
+                                                            "count": 323136,
                                                             "is_parallel": true,
-                                                            "self": 158.2712478019721
+                                                            "self": 152.1197451789485
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 8200.441692352266,
-                                                            "count": 319624,
+                                                            "total": 9243.167876113377,
+                                                            "count": 323136,
                                                             "is_parallel": true,
-                                                            "self": 8200.441692352266
+                                                            "self": 9243.167876113377
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 664.4238347358678,
-                                                            "count": 319624,
+                                                            "total": 670.0013199689711,
+                                                            "count": 323136,
                                                             "is_parallel": true,
-                                                            "self": 144.3269272668358,
+                                                            "self": 142.95692691750446,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 520.096907469032,
-                                                                    "count": 2556992,
+                                                                    "total": 527.0443930514666,
+                                                                    "count": 2585088,
                                                                     "is_parallel": true,
-                                                                    "self": 520.096907469032
+                                                                    "self": 527.0443930514666
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 5782.862756124616,
-                            "count": 319625,
-                            "self": 24.616622787247252,
+                            "total": 5715.864714869076,
+                            "count": 323137,
+                            "self": 24.701568577238504,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 877.171149347344,
-                                    "count": 319625,
-                                    "self": 876.153903157342,
+                                    "total": 884.9840235098454,
+                                    "count": 323137,
+                                    "self": 884.0035877718292,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.0172461900019698,
+                                            "total": 0.9804357380162401,
                                             "count": 10,
-                                            "self": 1.0172461900019698
+                                            "self": 0.9804357380162401
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 4881.0749839900245,
-                                    "count": 2331,
-                                    "self": 1966.28244934144,
+                                    "total": 4806.179122781992,
+                                    "count": 2343,
+                                    "self": 1923.9686476778588,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 2914.7925346485845,
-                                            "count": 113823,
-                                            "self": 2914.7925346485845
+                                            "total": 2882.2104751041334,
+                                            "count": 113877,
+                                            "self": 2882.2104751041334
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.2840027920901775e-06,
+                    "total": 1.0660005500540137e-06,
                     "count": 1,
-                    "self": 1.2840027920901775e-06
+                    "self": 1.0660005500540137e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09445331400274881,
+                    "total": 0.09439148699311772,
                     "count": 1,
-                    "self": 0.0032456500048283488,
+                    "self": 0.004332470991357695,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09120766399792046,
+                            "total": 0.09005901600176003,
                             "count": 1,
-                            "self": 0.09120766399792046
+                            "self": 0.09005901600176003
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 3499889,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3499889.onnx",
-                "reward": null,
-                "creation_time": 1734981587.15081,
+                "steps": 3499995,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3499995.onnx",
+                "reward": 1.2864999684194725,
+                "creation_time": 1734999473.7088268,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-3499889.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-3499995.pt"
                 ]
             },
             {
-                "steps": 3999936,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3999936.onnx",
-                "reward": 0.7922666271527609,
-                "creation_time": 1734983389.1241875,
+                "steps": 3999878,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3999878.onnx",
+                "reward": 1.6369999684393406,
+                "creation_time": 1735001375.7569773,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-3999936.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-3999878.pt"
                 ]
             },
             {
-                "steps": 4499974,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-4499974.onnx",
-                "reward": null,
-                "creation_time": 1734985214.8552246,
+                "steps": 4499887,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-4499887.onnx",
+                "reward": 1.7352856972387858,
+                "creation_time": 1735003289.6504326,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-4499974.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-4499887.pt"
                 ]
             },
             {
-                "steps": 4999925,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-4999925.onnx",
-                "reward": 1.7694999972979228,
-                "creation_time": 1734987041.7436519,
+                "steps": 4999937,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-4999937.onnx",
+                "reward": 1.8023999840021134,
+                "creation_time": 1735005228.425816,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-4999925.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-4999937.pt"
                 ]
             },
             {
-                "steps": 5000053,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-5000053.onnx",
-                "reward": 1.7694999972979228,
-                "creation_time": 1734987041.85069,
+                "steps": 5000065,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-5000065.onnx",
+                "reward": 1.8023999840021134,
+                "creation_time": 1735005228.5316072,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-5000053.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-5000065.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 5000053,
+            "steps": 5000065,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.7694999972979228,
-            "creation_time": 1734987041.85069,
+            "reward": 1.8023999840021134,
+            "creation_time": 1735005228.5316072,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-5000053.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-5000065.pt"
             ]
         }
     },