First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77a3c634b7c8aff01d2182cc91e30a4bed530c0f0e338c2bc970dba6cb3e5963
+oid sha256:3a7c57d9b69468054354c4b9ad8f0482e8749e4cf76a8e672170ab014363e972
 size 1420238

Pyramids/Pyramids-2499906.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b3d803bcf2c6c9eb1db53fa47f482c56fcdc44d09d93fa3ab59bf7784f0864
+size 1420238

Pyramids/Pyramids-2499906.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abaea7d3f7ff680d552967e483305e78022435d7841de7f03e4c7cf710937772
+size 8656731

Pyramids/Pyramids-2999912.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7c57d9b69468054354c4b9ad8f0482e8749e4cf76a8e672170ab014363e972
+size 1420238

Pyramids/Pyramids-2999912.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecdb58673177e494e35b8678ba158e4fd71a9041497156aff40dba261ae1393a
+size 8656731

Pyramids/Pyramids-3000040.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7c57d9b69468054354c4b9ad8f0482e8749e4cf76a8e672170ab014363e972
+size 1420238

Pyramids/Pyramids-3000040.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f1280912eaecddfbdc92dee808ed9701afc83ad839286756be1ae09570594a
+size 8656731

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d88d36c1bb27a52ef52542386ae94134c96d55c1ce88caa7a2fc464f7c0aee4
+oid sha256:cc6090a1505a631686e33c01d2e11a4fe61a0b4123ca2080e00750755375334c
 size 8656181

Pyramids/events.out.tfevents.1753093557.1b7113565678.26256.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b9e20912f8a18d841005692ea9911c0aa8037e2f06592321e406f301a5a2f0
+size 269889

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "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}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "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

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 2000000
+    max_steps: 3000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

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] 55315 [Flags] 2 [Guid] 845203319 [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] 55096 [Flags] 2 [Guid] 1706177475 [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)
@@ -33,10 +33,17 @@ 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  0.121 seconds
+- Completed reload, in  0.094 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
 WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
@@ -58,14 +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?
-WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
-WARNING: Shader Did you use #pragma only_renderers and omit this platform?
-WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
-WARNING: Shader Did you use #pragma only_renderers and omit this platform?
-WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.977024 ms
+UnloadTime: 0.739518 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]: 1736 frames, [32.0 KB-64.0 KB]: 11406 frames, [64.0 KB-128.0 KB]: 5620 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2155 frames, [32.0 KB-64.0 KB]: 10160 frames, [64.0 KB-128.0 KB]: 6451 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 480 B
+      Peak Allocated Bytes 240 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -204,29 +204,29 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 96 frames, [1.0 MB-2.0 MB]: 18667 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 27 frames, [1.0 MB-2.0 MB]: 18740 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 8843
+  Peak main deferred allocation count 11028
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames, [32.0 MB-64.0 MB]: 18762 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18766 frames
       Requested Block Size 16.0 MB
       Peak Block count 2
-      Peak Allocated memory 40.1 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 26.0 MB
+      Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames, [4.0 MB-8.0 MB]: 18762 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18767 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 6.9 MB
-      Peak Large allocation bytes 0 B
+      Peak Allocated memory 20.9 MB
+      Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -254,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18762 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18766 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]: 18763 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18767 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,13 +272,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 65 frames, [1.0 MB-2.0 MB]: 18698 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 36 frames, [1.0 MB-2.0 MB]: 18731 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]: 18762 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18766 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
@@ -290,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18763 frames
+      Peak usage frame count: [0-1.0 KB]: 18767 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]: 18763 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18767 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]: 18763 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18767 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 28.6 KB
+  Peak Allocated memory 29.2 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1753093376100,"processId":15501,"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":1753096027867,"processId":26278,"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

@@ -2,189 +2,189 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.2890987992286682,
-            "min": 0.27647459506988525,
-            "max": 0.6194453239440918,
-            "count": 33
+            "value": 0.18840862810611725,
+            "min": 0.18400797247886658,
+            "max": 0.2804012894630432,
+            "count": 34
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 8659.0869140625,
-            "min": 8219.037109375,
-            "max": 18583.359375,
-            "count": 33
+            "value": 5625.1279296875,
+            "min": 3084.85693359375,
+            "max": 8434.470703125,
+            "count": 34
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 257.4909090909091,
-            "min": 241.78861788617886,
-            "max": 405.61538461538464,
-            "count": 33
+            "value": 222.52592592592592,
+            "min": 192.1627906976744,
+            "max": 310.87368421052633,
+            "count": 34
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 28324.0,
-            "min": 16056.0,
-            "max": 32783.0,
-            "count": 33
+            "value": 30041.0,
+            "min": 8263.0,
+            "max": 31917.0,
+            "count": 34
         },
         "Pyramids.Step.mean": {
-            "value": 1979917.0,
-            "min": 1019944.0,
-            "max": 1979917.0,
-            "count": 33
+            "value": 2999912.0,
+            "min": 2009986.0,
+            "max": 2999912.0,
+            "count": 34
         },
         "Pyramids.Step.sum": {
-            "value": 1979917.0,
-            "min": 1019944.0,
-            "max": 1979917.0,
-            "count": 33
+            "value": 2999912.0,
+            "min": 2009986.0,
+            "max": 2999912.0,
+            "count": 34
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.7219787836074829,
-            "min": 0.4005979597568512,
-            "max": 0.7771360874176025,
-            "count": 33
+            "value": 0.8403334021568298,
+            "min": 0.6287362575531006,
+            "max": 0.8403334021568298,
+            "count": 34
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 207.9298858642578,
-            "min": 70.10464477539062,
-            "max": 231.5865478515625,
-            "count": 33
+            "value": 258.82269287109375,
+            "min": 74.38394165039062,
+            "max": 258.82269287109375,
+            "count": 34
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.001356392283923924,
-            "min": -0.058055855333805084,
-            "max": 0.040079277008771896,
-            "count": 33
+            "value": 0.008804552257061005,
+            "min": -0.014464023523032665,
+            "max": 0.02289220131933689,
+            "count": 34
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -0.3906409740447998,
-            "min": -10.159774780273438,
-            "max": 10.86148452758789,
-            "count": 33
+            "value": 2.7118020057678223,
+            "min": -1.8769246339797974,
+            "max": 6.798983573913574,
+            "count": 34
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.7246900772726215,
-            "min": 1.5020584418223455,
-            "max": 1.7582113700426691,
-            "count": 33
+            "value": 1.777474061537672,
+            "min": 1.6048926098566307,
+            "max": 1.8078372076500293,
+            "count": 34
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 191.44059857726097,
-            "min": 64.26859942823648,
-            "max": 216.2599985152483,
-            "count": 33
+            "value": 239.95899830758572,
+            "min": 77.73699992895126,
+            "max": 239.95899830758572,
+            "count": 34
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.7246900772726215,
-            "min": 1.5020584418223455,
-            "max": 1.7582113700426691,
-            "count": 33
+            "value": 1.777474061537672,
+            "min": 1.6048926098566307,
+            "max": 1.8078372076500293,
+            "count": 34
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 191.44059857726097,
-            "min": 64.26859942823648,
-            "max": 216.2599985152483,
-            "count": 33
+            "value": 239.95899830758572,
+            "min": 77.73699992895126,
+            "max": 239.95899830758572,
+            "count": 34
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.015308689450230796,
-            "min": 0.014581127780086429,
-            "max": 0.03442884677671827,
-            "count": 33
+            "value": 0.010327311727289472,
+            "min": 0.010327311727289472,
+            "max": 0.016723708555984654,
+            "count": 34
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 1.6992645289756183,
-            "min": 1.4310290696739685,
-            "max": 2.7959636427112855,
-            "count": 33
+            "value": 1.3941870831840788,
+            "min": 0.4957260352821322,
+            "max": 1.8668560988735408,
+            "count": 34
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.0723181798887349,
-            "min": 0.06344992305301797,
-            "max": 0.07534196404380697,
-            "count": 33
+            "value": 0.0678519000062368,
+            "min": 0.06323107099021961,
+            "max": 0.07358351286910916,
+            "count": 34
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 1.0124545184422886,
-            "min": 0.6105756317071306,
-            "max": 1.0547874966132975,
-            "count": 33
+            "value": 0.9499266000873152,
+            "min": 0.2692302552476416,
+            "max": 1.0497650696100511,
+            "count": 34
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.014281555990680678,
-            "min": 0.009865218712851249,
-            "max": 0.016138729900062994,
-            "count": 33
+            "value": 0.015059468376675897,
+            "min": 0.011901597794868784,
+            "max": 0.016053768207105655,
+            "count": 34
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.1999417838695295,
-            "min": 0.11269369220584242,
-            "max": 0.23955682700262496,
-            "count": 33
+            "value": 0.21083255727346256,
+            "min": 0.06421507282842262,
+            "max": 0.22995169926434758,
+            "count": 34
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 5.123509006482144e-06,
-            "min": 5.123509006482144e-06,
-            "max": 0.00014839028386992223,
-            "count": 33
+            "value": 1.5854923286785776e-06,
+            "min": 1.5854923286785776e-06,
+            "max": 9.947019184329167e-05,
+            "count": 34
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 7.172912609075001e-05,
-            "min": 7.172912609075001e-05,
-            "max": 0.0020262253245917996,
-            "count": 33
+            "value": 2.2196892601500087e-05,
+            "min": 2.2196892601500087e-05,
+            "max": 0.0014623016125664666,
+            "count": 34
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1017078035714286,
-            "min": 0.1017078035714286,
-            "max": 0.14946341111111114,
-            "count": 33
+            "value": 0.10052846428571428,
+            "min": 0.10052846428571428,
+            "max": 0.13315670833333335,
+            "count": 34
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4239092500000003,
-            "min": 1.3451707000000002,
-            "max": 2.1337129999999997,
-            "count": 33
+            "value": 1.4073985,
+            "min": 0.5326268333333334,
+            "max": 1.9874335333333333,
+            "count": 34
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0001806095767857143,
-            "min": 0.0001806095767857143,
-            "max": 0.00495139477,
-            "count": 33
+            "value": 6.279358214285736e-05,
+            "min": 6.279358214285736e-05,
+            "max": 0.003322355162500001,
+            "count": 34
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0025285340750000004,
-            "min": 0.0025285340750000004,
-            "max": 0.06761327917999999,
-            "count": 33
+            "value": 0.0008791101500000031,
+            "min": 0.0008791101500000031,
+            "max": 0.04884460998,
+            "count": 34
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.0057084821164608,
-            "min": 0.0057084821164608,
-            "max": 0.00873806793242693,
-            "count": 33
+            "value": 0.00449164304882288,
+            "min": 0.0044595287181437016,
+            "max": 0.005885581020265818,
+            "count": 34
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.0799187496304512,
-            "min": 0.07864261418581009,
-            "max": 0.11764119565486908,
-            "count": 33
+            "value": 0.06288300454616547,
+            "min": 0.02354232408106327,
+            "max": 0.08803229033946991,
+            "count": 34
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 34
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 34
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1753091009",
+        "start_time_seconds": "1753093556",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
         "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 --resume",
         "mlagents_version": "1.2.0.dev0",
@@ -192,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.7.1+cu126",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1753093376"
+        "end_time_seconds": "1753096027"
     },
-    "total": 2366.2507866389997,
+    "total": 2471.187962529001,
     "count": 1,
-    "self": 0.8770031709996147,
+    "self": 0.47706635700069455,
     "children": {
         "run_training.setup": {
-            "total": 0.02639951099990867,
+            "total": 0.02064571499977319,
             "count": 1,
-            "self": 0.02639951099990867
+            "self": 0.02064571499977319
         },
         "TrainerController.start_learning": {
-            "total": 2365.347383957,
+            "total": 2470.6902504570007,
             "count": 1,
-            "self": 1.1934797169806188,
+            "self": 1.2502839620237864,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.717111567000302,
+                    "total": 2.2784153870006776,
                     "count": 1,
-                    "self": 2.717111567000302
+                    "self": 2.2784153870006776
                 },
                 "TrainerController.advance": {
-                    "total": 2361.3261606300193,
-                    "count": 65163,
-                    "self": 1.3624014600236478,
+                    "total": 2467.077936038975,
+                    "count": 65747,
+                    "self": 1.3252463601666022,
                     "children": {
                         "env_step": {
-                            "total": 1711.4332194609997,
-                            "count": 65163,
-                            "self": 1573.457499761866,
+                            "total": 1814.2487259380023,
+                            "count": 65747,
+                            "self": 1675.5348490689512,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 137.24458744205276,
-                                    "count": 65163,
-                                    "self": 4.234710036889737,
+                                    "total": 137.9759848011763,
+                                    "count": 65747,
+                                    "self": 4.379366755234514,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 133.00987740516302,
-                                            "count": 62541,
-                                            "self": 133.00987740516302
+                                            "total": 133.5966180459418,
+                                            "count": 62556,
+                                            "self": 133.5966180459418
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7311322570808443,
-                                    "count": 65163,
+                                    "total": 0.7378920678747818,
+                                    "count": 65747,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2360.3488373919376,
-                                            "count": 65163,
+                                            "total": 2465.483885176981,
+                                            "count": 65747,
                                             "is_parallel": true,
-                                            "self": 894.4140760919768,
+                                            "self": 897.5958427070655,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0024430629996459174,
+                                                            "total": 0.0020146099996054545,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007260339998538257,
+                                                            "self": 0.0006397510005626827,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0017170289997920918,
+                                                                    "total": 0.0013748589990427718,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0017170289997920918
+                                                                    "self": 0.0013748589990427718
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06627171300033297,
+                                                            "total": 0.09754352199979621,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005250780004644184,
+                                                            "self": 0.0005564289995163563,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00043442600008347654,
+                                                                    "total": 0.0004128700002183905,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00043442600008347654
+                                                                    "self": 0.0004128700002183905
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.06376828800011936,
+                                                                    "total": 0.09495889400022861,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.06376828800011936
+                                                                    "self": 0.09495889400022861
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0015439209996657155,
+                                                                    "total": 0.0016153289998328546,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003323669993733347,
+                                                                    "self": 0.00035787800061370945,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0012115540002923808,
+                                                                            "total": 0.0012574509992191452,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0012115540002923808
+                                                                            "self": 0.0012574509992191452
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1465.9347612999609,
-                                                    "count": 65162,
+                                                    "total": 1567.8880424699155,
+                                                    "count": 65746,
                                                     "is_parallel": true,
-                                                    "self": 30.592568646956806,
+                                                    "self": 31.039047085002494,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 21.612736951007264,
-                                                            "count": 65162,
+                                                            "total": 21.627355150889343,
+                                                            "count": 65746,
                                                             "is_parallel": true,
-                                                            "self": 21.612736951007264
+                                                            "self": 21.627355150889343
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1323.0864241190093,
-                                                            "count": 65162,
+                                                            "total": 1423.794196472004,
+                                                            "count": 65746,
                                                             "is_parallel": true,
-                                                            "self": 1323.0864241190093
+                                                            "self": 1423.794196472004
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 90.64303158298753,
-                                                            "count": 65162,
+                                                            "total": 91.42744376201972,
+                                                            "count": 65746,
                                                             "is_parallel": true,
-                                                            "self": 17.69570631912211,
+                                                            "self": 17.88784387161013,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 72.94732526386542,
-                                                                    "count": 521296,
+                                                                    "total": 73.53959989040959,
+                                                                    "count": 525968,
                                                                     "is_parallel": true,
-                                                                    "self": 72.94732526386542
+                                                                    "self": 73.53959989040959
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 648.530539708996,
-                            "count": 65163,
-                            "self": 2.5051592239342426,
+                            "total": 651.5039637408063,
+                            "count": 65747,
+                            "self": 2.4893087617301717,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 125.09708008505959,
-                                    "count": 65163,
-                                    "self": 124.86934269105996,
+                                    "total": 127.4065734170872,
+                                    "count": 65747,
+                                    "self": 127.15094464108734,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.22773739399963233,
+                                            "total": 0.2556287759998668,
                                             "count": 2,
-                                            "self": 0.22773739399963233
+                                            "self": 0.2556287759998668
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 520.9283004000022,
+                                    "total": 521.6080815619889,
                                     "count": 473,
-                                    "self": 290.31461967394443,
+                                    "self": 288.9219459850201,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 230.61368072605774,
-                                            "count": 22767,
-                                            "self": 230.61368072605774
+                                            "total": 232.6861355769688,
+                                            "count": 22761,
+                                            "self": 232.6861355769688
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.202000021294225e-06,
+                    "total": 8.750012057134882e-07,
                     "count": 1,
-                    "self": 1.202000021294225e-06
+                    "self": 8.750012057134882e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.11063084099987464,
+                    "total": 0.08361419399989245,
                     "count": 1,
-                    "self": 0.002327762000277289,
+                    "self": 0.0016051209986471804,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10830307899959735,
+                            "total": 0.08200907300124527,
                             "count": 1,
-                            "self": 0.10830307899959735
+                            "self": 0.08200907300124527
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 1000204,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000204.onnx",
-                "reward": null,
-                "creation_time": 1753090120.216176,
+                "steps": 1999888,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999888.onnx",
+                "reward": 1.8024999722838402,
+                "creation_time": 1753093375.148163,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000204.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1999888.pt"
                 ]
             },
             {
-                "steps": 1000204,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000204.onnx",
-                "reward": null,
-                "creation_time": 1753090986.0941153,
+                "steps": 2000016,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2000016.onnx",
+                "reward": 1.8024999722838402,
+                "creation_time": 1753093375.2740035,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000204.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2000016.pt"
                 ]
             },
             {
-                "steps": 1499910,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499910.onnx",
-                "reward": 0.8047999739646912,
-                "creation_time": 1753092159.6534793,
+                "steps": 2499906,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499906.onnx",
+                "reward": 1.7261666506528854,
+                "creation_time": 1753094775.0340555,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1499910.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2499906.pt"
                 ]
             },
             {
-                "steps": 1999888,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999888.onnx",
-                "reward": 1.8024999722838402,
-                "creation_time": 1753093375.148163,
+                "steps": 2999912,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999912.onnx",
+                "reward": 1.7890999972820283,
+                "creation_time": 1753096027.3562975,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1999888.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2999912.pt"
                 ]
             },
             {
-                "steps": 2000016,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2000016.onnx",
-                "reward": 1.8024999722838402,
-                "creation_time": 1753093375.2740035,
+                "steps": 3000040,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000040.onnx",
+                "reward": 1.7890999972820283,
+                "creation_time": 1753096027.4496286,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-2000016.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-3000040.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000016,
+            "steps": 3000040,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.8024999722838402,
-            "creation_time": 1753093375.2740035,
+            "reward": 1.7890999972820283,
+            "creation_time": 1753096027.4496286,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-2000016.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-3000040.pt"
             ]
         }
     },