Second Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:502dbd9f3894b3d80d3f609cbcae39907def0e35358b53ee15166b942d16459c
+oid sha256:a2a9028c8d36f8e6d304b8e2583ed27c3ce57dcacb34f6962db654faf89d2a1e
 size 1418184

Pyramids/Pyramids-2499938.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d2428eb8e7b3e62bae1b011ce240cc7d5a4862890c39e216d669ce53855793
+size 1418184

Pyramids/Pyramids-2499938.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896f5249551df9d0e8f00d05d8c00540f2d2d229d5b34ad6c90082fdf34d4867
+size 8650990

Pyramids/Pyramids-2999883.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a9028c8d36f8e6d304b8e2583ed27c3ce57dcacb34f6962db654faf89d2a1e
+size 1418184

Pyramids/Pyramids-2999883.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab912809d8f88a6a21cd977b10764c5c8df1b850f1043c8395ccba8e084cac2d
+size 8650990

Pyramids/Pyramids-3000011.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a9028c8d36f8e6d304b8e2583ed27c3ce57dcacb34f6962db654faf89d2a1e
+size 1418184

Pyramids/Pyramids-3000011.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26eff33f9e6d053c35fb584b0ad4f9dd0c6a07f326561e9bc6382ecae3c21ecb
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50dae17bed14856020d1d37cf5e7eec29a6f75b7fdba5104aa6b4fa6a86d0751
+oid sha256:26eff33f9e6d053c35fb584b0ad4f9dd0c6a07f326561e9bc6382ecae3c21ecb
 size 8650990

Pyramids/events.out.tfevents.1693050400.3c7d3a2a16df.29987.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb75f19a9370aded283764e5f41c72d83ed81fffc6d883b8d84d896bc7f7f0f
+size 288468

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, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "PyramidsTraining", "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, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "PyramidsTraining", "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] 55165 [Flags] 2 [Guid] 4144762370 [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] 55401 [Flags] 2 [Guid] 988316769 [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  0.132 seconds
+- Completed reload, in  0.088 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: 1.084830 ms
+UnloadTime: 0.900497 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]: 1871 frames, [32.0 KB-64.0 KB]: 10895 frames, [64.0 KB-128.0 KB]: 6000 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2322 frames, [32.0 KB-64.0 KB]: 9964 frames, [64.0 KB-128.0 KB]: 6484 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
@@ -128,12 +128,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -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]: 48 frames, [1.0 MB-2.0 MB]: 18719 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 42 frames, [1.0 MB-2.0 MB]: 18729 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 10340
+  Peak main deferred allocation count 9137
     [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]: 18766 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18770 frames
       Requested Block Size 16.0 MB
       Peak Block count 2
-      Peak Allocated memory 41.4 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 23.4 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]: 18766 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.6 MB
-      Peak Large allocation bytes 0 B
+      Peak Allocated memory 22.3 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]: 18766 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18770 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]: 18767 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,16 +272,16 @@ 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]: 56 frames, [1.0 MB-2.0 MB]: 18711 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 55 frames, [1.0 MB-2.0 MB]: 18716 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]: 18766 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18770 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.4 MB
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -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]: 18767 frames
+      Peak usage frame count: [0-1.0 KB]: 18771 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]: 18767 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18771 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]: 18767 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18771 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.1 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":1693049565439,"processId":15464,"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":1693053095405,"processId":30003,"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": 0.189856618642807,
-            "min": 0.1817089468240738,
-            "max": 0.3481859266757965,
-            "count": 33
+            "value": 0.16728255152702332,
+            "min": 0.15525735914707184,
+            "max": 0.21002553403377533,
+            "count": 34
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 5726.07568359375,
-            "min": 5480.341796875,
-            "max": 10272.8779296875,
-            "count": 33
+            "value": 5053.271484375,
+            "min": 1868.0673828125,
+            "max": 6280.603515625,
+            "count": 34
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 249.94573643410854,
-            "min": 230.5703125,
-            "max": 364.6666666666667,
-            "count": 33
+            "value": 234.51181102362204,
+            "min": 212.17948717948718,
+            "max": 283.64761904761906,
+            "count": 34
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 32243.0,
-            "min": 17353.0,
-            "max": 32243.0,
-            "count": 33
+            "value": 29783.0,
+            "min": 8275.0,
+            "max": 31880.0,
+            "count": 34
         },
         "Pyramids.Step.mean": {
-            "value": 1979995.0,
-            "min": 1019988.0,
-            "max": 1979995.0,
-            "count": 33
+            "value": 2999883.0,
+            "min": 2009983.0,
+            "max": 2999883.0,
+            "count": 34
         },
         "Pyramids.Step.sum": {
-            "value": 1979995.0,
-            "min": 1019988.0,
-            "max": 1979995.0,
-            "count": 33
+            "value": 2999883.0,
+            "min": 2009983.0,
+            "max": 2999883.0,
+            "count": 34
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.7693508267402649,
-            "min": 0.5625669956207275,
-            "max": 0.8056074380874634,
-            "count": 33
+            "value": 0.7479361891746521,
+            "min": 0.6622505784034729,
+            "max": 0.8450698852539062,
+            "count": 34
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 230.8052520751953,
-            "min": 103.35254669189453,
-            "max": 238.45980834960938,
-            "count": 33
+            "value": 224.380859375,
+            "min": 73.65901184082031,
+            "max": 252.65277099609375,
+            "count": 34
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.004943689797073603,
-            "min": -0.004943689797073603,
-            "max": 0.04152600094676018,
-            "count": 33
+            "value": 0.005168822593986988,
+            "min": -0.012601537629961967,
+            "max": 0.01932157576084137,
+            "count": 34
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -1.4831069707870483,
-            "min": -1.4831069707870483,
-            "max": 11.83491039276123,
-            "count": 33
+            "value": 1.5506467819213867,
+            "min": -3.742656707763672,
+            "max": 5.680543422698975,
+            "count": 34
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.735264048911631,
-            "min": 1.5612444244785073,
-            "max": 1.7675039833784103,
-            "count": 33
+            "value": 1.7497338478959452,
+            "min": 1.6608981324566736,
+            "max": 1.787820503497735,
+            "count": 34
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 222.11379826068878,
-            "min": 96.64699840545654,
-            "max": 228.18799858540297,
-            "count": 33
+            "value": 222.21619868278503,
+            "min": 69.72499963641167,
+            "max": 244.80299776792526,
+            "count": 34
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.735264048911631,
-            "min": 1.5612444244785073,
-            "max": 1.7675039833784103,
-            "count": 33
+            "value": 1.7497338478959452,
+            "min": 1.6608981324566736,
+            "max": 1.787820503497735,
+            "count": 34
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 222.11379826068878,
-            "min": 96.64699840545654,
-            "max": 228.18799858540297,
-            "count": 33
+            "value": 222.21619868278503,
+            "min": 69.72499963641167,
+            "max": 244.80299776792526,
+            "count": 34
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.02587083513401467,
-            "min": 0.024559607545597828,
-            "max": 0.05238411585616385,
-            "count": 33
+            "value": 0.01949155884766532,
+            "min": 0.019372238134383223,
+            "max": 0.028201485868443604,
+            "count": 34
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 3.3114668971538777,
-            "min": 2.692943104368169,
-            "max": 4.350430508609861,
-            "count": 33
+            "value": 2.4754279736534954,
+            "min": 0.8830385050969198,
+            "max": 3.0416997363208793,
+            "count": 34
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06605385297734756,
-            "min": 0.06359199066323021,
-            "max": 0.07284611712836957,
-            "count": 33
+            "value": 0.07110694913851966,
+            "min": 0.06405901443975467,
+            "max": 0.07133843297612788,
+            "count": 34
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9247539416828658,
-            "min": 0.5931617736607543,
-            "max": 1.040361449122429,
-            "count": 33
+            "value": 0.9954972879392753,
+            "min": 0.27638910769019276,
+            "max": 1.0520664500654675,
+            "count": 34
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01609122662089898,
-            "min": 0.01255998326559973,
-            "max": 0.016918032216317415,
-            "count": 33
+            "value": 0.01526131886429302,
+            "min": 0.012369724602710143,
+            "max": 0.016298255188782248,
+            "count": 34
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.22527717269258574,
-            "min": 0.11886353706301866,
-            "max": 0.23685245102844382,
-            "count": 33
+            "value": 0.21365846410010228,
+            "min": 0.06191515453004589,
+            "max": 0.23520687879257218,
+            "count": 34
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 5.261755388971429e-06,
-            "min": 5.261755388971429e-06,
-            "max": 0.00014841648386118886,
-            "count": 33
+            "value": 1.5590351946404768e-06,
+            "min": 1.5590351946404768e-06,
+            "max": 9.947719184095832e-05,
+            "count": 34
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 7.36645754456e-05,
-            "min": 7.36645754456e-05,
-            "max": 0.0020265499244836002,
-            "count": 33
+            "value": 2.1826492724966673e-05,
+            "min": 2.1826492724966673e-05,
+            "max": 0.0014621597126137666,
+            "count": 34
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10175388571428572,
-            "min": 0.10175388571428572,
-            "max": 0.14947214444444443,
-            "count": 33
+            "value": 0.10051964523809527,
+            "min": 0.10051964523809527,
+            "max": 0.13315904166666664,
+            "count": 34
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4245544,
-            "min": 1.3452492999999999,
-            "max": 2.1336950999999997,
-            "count": 33
+            "value": 1.4072750333333337,
+            "min": 0.5326361666666666,
+            "max": 1.9873862333333334,
+            "count": 34
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00018521318285714286,
-            "min": 0.00018521318285714286,
-            "max": 0.00495226723,
-            "count": 33
+            "value": 6.191255928571431e-05,
+            "min": 6.191255928571431e-05,
+            "max": 0.0033225882625,
+            "count": 34
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.00259298456,
-            "min": 0.00259298456,
-            "max": 0.06762408835999999,
-            "count": 33
+            "value": 0.0008667758300000004,
+            "min": 0.0008667758300000004,
+            "max": 0.048839884709999996,
+            "count": 34
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.009953402914106846,
-            "min": 0.009953402914106846,
-            "max": 0.015164068900048733,
-            "count": 33
+            "value": 0.008113382384181023,
+            "min": 0.007795785553753376,
+            "max": 0.010242822580039501,
+            "count": 34
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.139347642660141,
-            "min": 0.13647662103176117,
-            "max": 0.2004043012857437,
-            "count": 33
+            "value": 0.11358735710382462,
+            "min": 0.040971290320158005,
+            "max": 0.14452455937862396,
+            "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": "1693046857",
+        "start_time_seconds": "1693050399",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=PyramidsTraining --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
@@ -192,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1693049565"
+        "end_time_seconds": "1693053095"
     },
-    "total": 2707.949965885,
+    "total": 2695.543802821001,
     "count": 1,
-    "self": 0.4775602929998968,
+    "self": 1.1324325500017949,
     "children": {
         "run_training.setup": {
-            "total": 0.0623524739999084,
+            "total": 0.040259501000036835,
             "count": 1,
-            "self": 0.0623524739999084
+            "self": 0.040259501000036835
         },
         "TrainerController.start_learning": {
-            "total": 2707.410053118,
+            "total": 2694.371110769999,
             "count": 1,
-            "self": 1.6329233869714699,
+            "self": 1.6563902417110512,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.2107627870000215,
+                    "total": 5.44096331899982,
                     "count": 1,
-                    "self": 5.2107627870000215
+                    "self": 5.44096331899982
                 },
                 "TrainerController.advance": {
-                    "total": 2700.4612155600284,
-                    "count": 65365,
-                    "self": 1.561065242126915,
+                    "total": 2687.100431038287,
+                    "count": 65705,
+                    "self": 1.5864545440545044,
                     "children": {
                         "env_step": {
-                            "total": 2008.4881389168577,
-                            "count": 65365,
-                            "self": 1891.3168267420342,
+                            "total": 2001.4026687082624,
+                            "count": 65705,
+                            "self": 1886.4337987335402,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 116.24314791791585,
-                                    "count": 65365,
-                                    "self": 4.9299677619242175,
+                                    "total": 114.04875525803072,
+                                    "count": 65705,
+                                    "self": 4.902434129653557,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 111.31318015599163,
-                                            "count": 62555,
-                                            "self": 111.31318015599163
+                                            "total": 109.14632112837717,
+                                            "count": 62569,
+                                            "self": 109.14632112837717
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.9281642569076212,
-                                    "count": 65365,
+                                    "total": 0.920114716691387,
+                                    "count": 65705,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2700.989232571038,
-                                            "count": 65365,
+                                            "total": 2687.969531494088,
+                                            "count": 65705,
                                             "is_parallel": true,
-                                            "self": 936.2675088729279,
+                                            "self": 926.9245235840926,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002749479999692994,
+                                                            "total": 0.0019770689996221336,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006598020004275895,
+                                                            "self": 0.0006251910008359118,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0020896779992654047,
+                                                                    "total": 0.0013518779987862217,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0020896779992654047
+                                                                    "self": 0.0013518779987862217
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05014101799997661,
+                                                            "total": 0.08333673800007091,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005669600000146602,
+                                                            "self": 0.0005924659999436699,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005053139998381084,
+                                                                    "total": 0.00046607700005552033,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005053139998381084
+                                                                    "self": 0.00046607700005552033
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04710479200002737,
+                                                                    "total": 0.07168196800012083,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04710479200002737
+                                                                    "self": 0.07168196800012083
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0019639520000964694,
+                                                                    "total": 0.010596226999950886,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000376612000309251,
+                                                                    "self": 0.009075192998352577,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015873399997872184,
+                                                                            "total": 0.0015210340015983093,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015873399997872184
+                                                                            "self": 0.0015210340015983093
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1764.72172369811,
-                                                    "count": 65364,
+                                                    "total": 1761.0450079099955,
+                                                    "count": 65704,
                                                     "is_parallel": true,
-                                                    "self": 35.592770060198745,
+                                                    "self": 34.77587164081251,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 23.265593657970385,
-                                                            "count": 65364,
+                                                            "total": 23.156331481118286,
+                                                            "count": 65704,
                                                             "is_parallel": true,
-                                                            "self": 23.265593657970385
+                                                            "self": 23.156331481118286
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1593.6019322240054,
-                                                            "count": 65364,
+                                                            "total": 1592.8627225269947,
+                                                            "count": 65704,
                                                             "is_parallel": true,
-                                                            "self": 1593.6019322240054
+                                                            "self": 1592.8627225269947
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 112.26142775593553,
-                                                            "count": 65364,
+                                                            "total": 110.25008226107002,
+                                                            "count": 65704,
                                                             "is_parallel": true,
-                                                            "self": 22.869903264721415,
+                                                            "self": 22.365261638236916,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 89.39152449121411,
-                                                                    "count": 522912,
+                                                                    "total": 87.8848206228331,
+                                                                    "count": 525632,
                                                                     "is_parallel": true,
-                                                                    "self": 89.39152449121411
+                                                                    "self": 87.8848206228331
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 690.4120114010439,
-                            "count": 65365,
-                            "self": 3.0458836080670153,
+                            "total": 684.11130778597,
+                            "count": 65705,
+                            "self": 3.081327651087122,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 120.1345750539781,
-                                    "count": 65365,
-                                    "self": 119.91976739297888,
+                                    "total": 120.54025942088992,
+                                    "count": 65705,
+                                    "self": 120.27275603989074,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.2148076609992131,
+                                            "total": 0.26750338099918736,
                                             "count": 2,
-                                            "self": 0.2148076609992131
+                                            "self": 0.26750338099918736
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 567.2315527389987,
-                                    "count": 471,
-                                    "self": 371.40067953005564,
+                                    "total": 560.4897207139929,
+                                    "count": 473,
+                                    "self": 366.8761716950967,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 195.8308732089431,
-                                            "count": 22692,
-                                            "self": 195.8308732089431
+                                            "total": 193.61354901889626,
+                                            "count": 22752,
+                                            "self": 193.61354901889626
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.820005288929678e-07,
+                    "total": 2.3588001567986794e-05,
                     "count": 1,
-                    "self": 9.820005288929678e-07
+                    "self": 2.3588001567986794e-05
                 },
                 "TrainerController._save_models": {
-                    "total": 0.10515040199970827,
+                    "total": 0.1733025829998951,
                     "count": 1,
-                    "self": 0.0016279530000247178,
+                    "self": 0.0039729189993522596,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10352244899968355,
+                            "total": 0.16932966400054283,
                             "count": 1,
-                            "self": 0.10352244899968355
+                            "self": 0.16932966400054283
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 999890,
-                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-999890.onnx",
-                "reward": 1.6974999867379665,
-                "creation_time": 1693045865.4818895,
+                "steps": 1999877,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1999877.onnx",
+                "reward": 1.7714999821037054,
+                "creation_time": 1693049564.9060664,
                 "auxillary_file_paths": [
-                    "results/PyramidsTraining/Pyramids/Pyramids-999890.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-1999877.pt"
                 ]
             },
             {
-                "steps": 1000018,
-                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1000018.onnx",
-                "reward": 1.6974999867379665,
-                "creation_time": 1693045865.6458752,
+                "steps": 2000005,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-2000005.onnx",
+                "reward": 1.7714999821037054,
+                "creation_time": 1693049565.0193465,
                 "auxillary_file_paths": [
-                    "results/PyramidsTraining/Pyramids/Pyramids-1000018.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-2000005.pt"
                 ]
             },
             {
-                "steps": 1499880,
-                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1499880.onnx",
-                "reward": 1.8224285628114427,
-                "creation_time": 1693048213.750938,
+                "steps": 2499938,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-2499938.onnx",
+                "reward": 1.8116999924182893,
+                "creation_time": 1693051758.2374809,
                 "auxillary_file_paths": [
-                    "results/PyramidsTraining/Pyramids/Pyramids-1499880.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-2499938.pt"
                 ]
             },
             {
-                "steps": 1999877,
-                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1999877.onnx",
-                "reward": 1.7714999821037054,
-                "creation_time": 1693049564.9060664,
+                "steps": 2999883,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-2999883.onnx",
+                "reward": 1.7728999823331832,
+                "creation_time": 1693053094.1241612,
                 "auxillary_file_paths": [
-                    "results/PyramidsTraining/Pyramids/Pyramids-1999877.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-2999883.pt"
                 ]
             },
             {
-                "steps": 2000005,
-                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-2000005.onnx",
-                "reward": 1.7714999821037054,
-                "creation_time": 1693049565.0193465,
+                "steps": 3000011,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-3000011.onnx",
+                "reward": 1.7728999823331832,
+                "creation_time": 1693053094.3118856,
                 "auxillary_file_paths": [
-                    "results/PyramidsTraining/Pyramids/Pyramids-2000005.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-3000011.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000005,
+            "steps": 3000011,
             "file_path": "results/PyramidsTraining/Pyramids.onnx",
-            "reward": 1.7714999821037054,
-            "creation_time": 1693049565.0193465,
+            "reward": 1.7728999823331832,
+            "creation_time": 1693053094.3118856,
             "auxillary_file_paths": [
-                "results/PyramidsTraining/Pyramids/Pyramids-2000005.pt"
+                "results/PyramidsTraining/Pyramids/Pyramids-3000011.pt"
             ]
         }
     },