First Pyramids

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e271ae1bd7822dc80121372f3bd0084a1c42fab1bac9fb1b262be5bade2d828
+oid sha256:5c88fd710825af05ae196c98ad6f2bde8b6fceaedb6b5a85da1d8dcc30cab2f1
 size 1417437

Pyramids/{Pyramids-499990.onnx → Pyramids-1499935.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e271ae1bd7822dc80121372f3bd0084a1c42fab1bac9fb1b262be5bade2d828
+oid sha256:5c88fd710825af05ae196c98ad6f2bde8b6fceaedb6b5a85da1d8dcc30cab2f1
 size 1417437

Pyramids/{Pyramids-499990.pt → Pyramids-1499935.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b46bd1dcf94a7da41017e6bbcd1854de4172df1e61c8cd89efb9bd37a2ff631
+oid sha256:8b2ea1f6beddc30924a83c5cdfcf0e167b8291aa2dd302bf991afe4a51459419
 size 8652382

Pyramids/{Pyramids-500118.onnx → Pyramids-1500063.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e271ae1bd7822dc80121372f3bd0084a1c42fab1bac9fb1b262be5bade2d828
+oid sha256:5c88fd710825af05ae196c98ad6f2bde8b6fceaedb6b5a85da1d8dcc30cab2f1
 size 1417437

Pyramids/{Pyramids-500118.pt → Pyramids-1500063.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:968ffe022a9112e33bcdbf3722d2ce46b213239010c6412f2fc6dc383827cd18
+oid sha256:cb92238a454cfda4b5fcc743b8ff7377a8f26c3429617d4fad920e8c054ee6bf
 size 8652382

Pyramids/Pyramids-499960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:267c3d6c85fd6eff86c4c874cd2bd152b83117078eef6981df27ef89a9aaaf31
+size 1417437

Pyramids/Pyramids-499960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4744e4d85f1981f7bbf4141648b7e4b22a55e815f2464d049b824aa2ce331a88
+size 8652382

Pyramids/Pyramids-999968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859e4a97cb892a98810176892a1f76612884c34bad078c152e65fa9753f734fa
+size 1417437

Pyramids/Pyramids-999968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ebaafdff6978ad56d6a8dd8cc1dfed121f0d4997b95e7fc5b5c71f6a5eea25a
+size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:968ffe022a9112e33bcdbf3722d2ce46b213239010c6412f2fc6dc383827cd18
+oid sha256:cb92238a454cfda4b5fcc743b8ff7377a8f26c3429617d4fad920e8c054ee6bf
 size 8652382

Pyramids/{events.out.tfevents.1662397187.848e7fa733a9.251.0 → events.out.tfevents.1662399644.c80cc846e2d3.237.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a07c91a995982120b49ed96db33c43d9a46243b50858329e77e6650aef77ff8c
-size 147571
+oid sha256:0dcc67423133716483e16025297b10a486bc2ee3275af64150836c21fe437869
+size 452764

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 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, "checkpoint_interval": 500000, "max_steps": 500000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": 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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 1500000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -49,7 +49,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 500000
-    max_steps: 500000
+    max_steps: 1500000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55034 [Flags] 2 [Guid] 257597058 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.2 [Port] 55091 [Flags] 2 [Guid] 3401726863 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
 PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
@@ -68,7 +68,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.813288 ms
+UnloadTime: 0.874355 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -76,7 +76,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 6494 frames, [32.0 KB-64.0 KB]: 2226 frames, [64.0 KB-128.0 KB]: 672 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 5239 frames, [32.0 KB-64.0 KB]: 17376 frames, [64.0 KB-128.0 KB]: 5527 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
@@ -207,28 +207,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 9094 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 27844 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12317
+  Peak main deferred allocation count 11992
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.6 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 9389 frames, [32.0 MB-64.0 MB]: 3 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 28142 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 32.4 MB
+      Peak Allocated memory 31.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9393 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 28143 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 21.8 MB
+      Peak Allocated memory 21.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +255,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.6 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 9392 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 28142 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]: 9393 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 28143 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,15 +273,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.6 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 9094 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 27844 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]: 9392 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 28142 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -291,27 +291,27 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.6 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9393 frames
+      Peak usage frame count: [0-1.0 KB]: 28143 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]: 9393 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 28143 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]: 9393 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 28143 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 27.4 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":1662398131955,"processId":262,"allocatedMemory":1957329,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3444},{"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":1662402715586,"processId":248,"allocatedMemory":1957329,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3444},{"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": 0.635040819644928,
-            "min": 0.6195599436759949,
-            "max": 1.4484033584594727,
-            "count": 16
+            "value": 0.44389885663986206,
+            "min": 0.4429570138454437,
+            "max": 1.466874361038208,
+            "count": 50
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 19091.8671875,
-            "min": 18666.1015625,
-            "max": 43938.765625,
-            "count": 16
+            "value": 13295.658203125,
+            "min": 13295.658203125,
+            "max": 44499.1015625,
+            "count": 50
         },
         "Pyramids.Step.mean": {
-            "value": 479903.0,
-            "min": 29952.0,
-            "max": 479903.0,
-            "count": 16
+            "value": 1499935.0,
+            "min": 29909.0,
+            "max": 1499935.0,
+            "count": 50
         },
         "Pyramids.Step.sum": {
-            "value": 479903.0,
-            "min": 29952.0,
-            "max": 479903.0,
-            "count": 16
+            "value": 1499935.0,
+            "min": 29909.0,
+            "max": 1499935.0,
+            "count": 50
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.022031402215361595,
-            "min": -0.12023954093456268,
-            "max": 0.002282531000673771,
-            "count": 16
+            "value": 0.7310246229171753,
+            "min": -0.10883622616529465,
+            "max": 0.780449628829956,
+            "count": 50
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -5.353630542755127,
-            "min": -28.97772979736328,
-            "max": 0.5409598350524902,
-            "count": 16
+            "value": 213.4591827392578,
+            "min": -26.229530334472656,
+            "max": 231.79354858398438,
+            "count": 50
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.026707489043474197,
-            "min": 0.01881342940032482,
-            "max": 0.39825522899627686,
-            "count": 16
+            "value": -0.003801656188443303,
+            "min": -0.02046757936477661,
+            "max": 0.4144503176212311,
+            "count": 50
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 6.489919662475586,
-            "min": 4.515223026275635,
-            "max": 94.38648986816406,
-            "count": 16
+            "value": -1.1100835800170898,
+            "min": -5.32157039642334,
+            "max": 98.22472381591797,
+            "count": 50
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06903089465571309,
-            "min": 0.06654039200337301,
-            "max": 0.07528294901977187,
-            "count": 16
+            "value": 0.07093477098581692,
+            "min": 0.06488527835329476,
+            "max": 0.07267788270643603,
+            "count": 50
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9664325251799833,
-            "min": 0.510413526549859,
-            "max": 0.985859763924393,
-            "count": 16
+            "value": 1.0640215647872537,
+            "min": 0.4744797794154347,
+            "max": 1.0901682405965405,
+            "count": 50
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0055766094734607165,
-            "min": 0.0003854638235823371,
-            "max": 0.006516812967725699,
-            "count": 16
+            "value": 0.01536192101031904,
+            "min": 9.669598815068191e-05,
+            "max": 0.017008988528340565,
+            "count": 50
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.07807253262845003,
-            "min": 0.004625565882988045,
-            "max": 0.07807253262845003,
-            "count": 16
+            "value": 0.23042881515478558,
+            "min": 0.0012570478459588649,
+            "max": 0.23812583939676793,
+            "count": 50
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.0899764462014285e-05,
-            "min": 2.0899764462014285e-05,
-            "max": 0.00029030126037577137,
-            "count": 16
+            "value": 3.001725666124444e-06,
+            "min": 3.001725666124444e-06,
+            "max": 0.0002968231724875142,
+            "count": 50
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0002925967024682,
-            "min": 0.0002925967024682,
-            "max": 0.0028513586495472,
-            "count": 16
+            "value": 4.502588499186666e-05,
+            "min": 4.502588499186666e-05,
+            "max": 0.0037061768646077333,
+            "count": 50
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10696655714285716,
-            "min": 0.10696655714285716,
-            "max": 0.19676708571428575,
-            "count": 16
+            "value": 0.10100054222222224,
+            "min": 0.10100054222222224,
+            "max": 0.19894105714285718,
+            "count": 50
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4975318000000002,
-            "min": 1.3773696000000002,
-            "max": 2.2535854000000004,
-            "count": 16
+            "value": 1.5150081333333336,
+            "min": 1.3925874000000003,
+            "max": 2.6183329333333334,
+            "count": 50
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0007059590585714286,
-            "min": 0.0007059590585714286,
-            "max": 0.00967703186285714,
-            "count": 16
+            "value": 0.00010995416799999998,
+            "min": 0.00010995416799999998,
+            "max": 0.00989421160857143,
+            "count": 50
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.00988342682,
-            "min": 0.00988342682,
-            "max": 0.09507023472000002,
-            "count": 16
+            "value": 0.0016493125199999997,
+            "min": 0.0016493125199999997,
+            "max": 0.12354568744000002,
+            "count": 50
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.024755146354436874,
-            "min": 0.02381882071495056,
-            "max": 0.5119829773902893,
-            "count": 16
+            "value": 0.006000143475830555,
+            "min": 0.006000143475830555,
+            "max": 0.43413084745407104,
+            "count": 50
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.34657204151153564,
-            "min": 0.33346349000930786,
-            "max": 3.583880662918091,
-            "count": 16
+            "value": 0.0900021493434906,
+            "min": 0.0850573256611824,
+            "max": 3.0389158725738525,
+            "count": 50
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 869.4571428571429,
-            "min": 869.4571428571429,
+            "value": 260.6475409836066,
+            "min": 242.83870967741936,
             "max": 999.0,
-            "count": 16
+            "count": 50
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30431.0,
-            "min": 15984.0,
-            "max": 32667.0,
-            "count": 16
+            "value": 31799.0,
+            "min": 16708.0,
+            "max": 33023.0,
+            "count": 50
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.24142289906740189,
-            "min": -1.0000000521540642,
-            "max": -0.24142289906740189,
-            "count": 16
+            "value": 1.7232861631527179,
+            "min": -0.9999226326903989,
+            "max": 1.7571612806810486,
+            "count": 50
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -8.449801467359066,
-            "min": -31.99920167028904,
-            "max": -8.449801467359066,
-            "count": 16
+            "value": 211.9641980677843,
+            "min": -30.997601613402367,
+            "max": 217.88799880445004,
+            "count": 50
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.24142289906740189,
-            "min": -1.0000000521540642,
-            "max": -0.24142289906740189,
-            "count": 16
+            "value": 1.7232861631527179,
+            "min": -0.9999226326903989,
+            "max": 1.7571612806810486,
+            "count": 50
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -8.449801467359066,
-            "min": -31.99920167028904,
-            "max": -8.449801467359066,
-            "count": 16
+            "value": 211.9641980677843,
+            "min": -30.997601613402367,
+            "max": 217.88799880445004,
+            "count": 50
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.2221869895234704,
-            "min": 0.2221869895234704,
-            "max": 10.938915073871613,
-            "count": 16
+            "value": 0.01608496457191631,
+            "min": 0.015336832706276666,
+            "max": 8.486839855418486,
+            "count": 50
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 7.776544633321464,
-            "min": 7.159041221719235,
-            "max": 175.0226411819458,
-            "count": 16
+            "value": 1.978450642345706,
+            "min": 1.733607194837532,
+            "max": 144.27627754211426,
+            "count": 50
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
+            "count": 50
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
+            "count": 50
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1662397181",
+        "start_time_seconds": "1662399637",
         "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
         "mlagents_version": "0.29.0.dev0",
@@ -192,66 +192,66 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1662398132"
+        "end_time_seconds": "1662402715"
     },
-    "total": 951.004609726,
+    "total": 3077.788285257,
     "count": 1,
-    "self": 0.43131236900001113,
+    "self": 0.43036782200033485,
     "children": {
         "run_training.setup": {
-            "total": 0.04046260400002666,
+            "total": 0.04394579499989959,
             "count": 1,
-            "self": 0.04046260400002666
+            "self": 0.04394579499989959
         },
         "TrainerController.start_learning": {
-            "total": 950.532834753,
+            "total": 3077.31397164,
             "count": 1,
-            "self": 0.6268865599897708,
+            "self": 2.136831337013973,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 9.366194828000062,
+                    "total": 9.182996784000125,
                     "count": 1,
-                    "self": 9.366194828000062
+                    "self": 9.182996784000125
                 },
                 "TrainerController.advance": {
-                    "total": 940.4457924870102,
-                    "count": 31504,
-                    "self": 0.6710827009733293,
+                    "total": 3065.9042919479857,
+                    "count": 96310,
+                    "self": 2.184833859130322,
                     "children": {
                         "env_step": {
-                            "total": 596.3092096360066,
-                            "count": 31504,
-                            "self": 546.2892377059939,
+                            "total": 2013.6734765389017,
+                            "count": 96310,
+                            "self": 1857.4008511689572,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 49.68120728398753,
-                                    "count": 31504,
-                                    "self": 2.3061239179626227,
+                                    "total": 155.15193579401216,
+                                    "count": 96310,
+                                    "self": 6.822911933089699,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 47.37508336602491,
-                                            "count": 31309,
-                                            "self": 16.754708887039214,
+                                            "total": 148.32902386092246,
+                                            "count": 93810,
+                                            "self": 52.403997892915186,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 30.620374478985696,
-                                                    "count": 31309,
-                                                    "self": 30.620374478985696
+                                                    "total": 95.92502596800728,
+                                                    "count": 93810,
+                                                    "self": 95.92502596800728
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.3387646460251972,
-                                    "count": 31504,
+                                    "total": 1.1206895759323743,
+                                    "count": 96310,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 948.544272317018,
-                                            "count": 31504,
+                                            "total": 3071.4742740630336,
+                                            "count": 96310,
                                             "is_parallel": true,
-                                            "self": 451.60086512602743,
+                                            "self": 1366.19907004606,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.008500959000002695,
+                                                            "total": 0.008565696999994543,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.005098714000268956,
+                                                            "self": 0.0034624649999841495,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.003402244999733739,
+                                                                    "total": 0.005103232000010394,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.003402244999733739
+                                                                    "self": 0.005103232000010394
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04876402299998972,
+                                                            "total": 0.04740006500014715,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005104049999999916,
+                                                            "self": 0.0005839370003286604,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004277729999557778,
+                                                                    "total": 0.0004570389999116742,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004277729999557778
+                                                                    "self": 0.0004570389999116742
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.046241965000035634,
+                                                                    "total": 0.04469502500000999,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.046241965000035634
+                                                                    "self": 0.04469502500000999
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0015838799999983166,
+                                                                    "total": 0.0016640639998968254,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004104419999748643,
+                                                                    "self": 0.00048067899979287176,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0011734380000234523,
+                                                                            "total": 0.0011833850001039536,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0011734380000234523
+                                                                            "self": 0.0011833850001039536
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 496.94340719099057,
-                                                    "count": 31503,
+                                                    "total": 1705.2752040169737,
+                                                    "count": 96309,
                                                     "is_parallel": true,
-                                                    "self": 13.395765122044509,
+                                                    "self": 41.235679040122704,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 11.061469420977005,
-                                                            "count": 31503,
+                                                            "total": 33.987226408951756,
+                                                            "count": 96309,
                                                             "is_parallel": true,
-                                                            "self": 11.061469420977005
+                                                            "self": 33.987226408951756
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 427.62793611195616,
-                                                            "count": 31503,
+                                                            "total": 1492.7428819050608,
+                                                            "count": 96309,
                                                             "is_parallel": true,
-                                                            "self": 427.62793611195616
+                                                            "self": 1492.7428819050608
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 44.858236536012896,
-                                                            "count": 31503,
+                                                            "total": 137.30941666283843,
+                                                            "count": 96309,
                                                             "is_parallel": true,
-                                                            "self": 11.016676441014283,
+                                                            "self": 34.05759684784812,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 33.84156009499861,
-                                                                    "count": 252024,
+                                                                    "total": 103.25181981499031,
+                                                                    "count": 770472,
                                                                     "is_parallel": true,
-                                                                    "self": 33.84156009499861
+                                                                    "self": 103.25181981499031
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 343.46550015003027,
-                            "count": 31504,
-                            "self": 1.051371121038983,
+                            "total": 1050.0459815499537,
+                            "count": 96310,
+                            "self": 4.0948472109603244,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 76.59021024599292,
-                                    "count": 31504,
-                                    "self": 76.48676475299294,
+                                    "total": 241.16208699599724,
+                                    "count": 96310,
+                                    "self": 240.86859932199673,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.10344549299998107,
-                                            "count": 1,
-                                            "self": 0.10344549299998107
+                                            "total": 0.29348767400051656,
+                                            "count": 3,
+                                            "self": 0.29348767400051656
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 265.82391878299836,
-                                    "count": 210,
-                                    "self": 107.03819743400868,
+                                    "total": 804.7890473429961,
+                                    "count": 690,
+                                    "self": 320.0053215850396,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 158.78572134898968,
-                                            "count": 11373,
-                                            "self": 158.78572134898968
+                                            "total": 484.7837257579565,
+                                            "count": 34251,
+                                            "self": 484.7837257579565
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.092000047719921e-06,
+                    "total": 1.0730000212788582e-06,
                     "count": 1,
-                    "self": 1.092000047719921e-06
+                    "self": 1.0730000212788582e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09395978599991395,
+                    "total": 0.08985049800048728,
                     "count": 1,
-                    "self": 0.0015390850001040235,
+                    "self": 0.0016160260001925053,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09242070099980992,
+                            "total": 0.08823447200029477,
                             "count": 1,
-                            "self": 0.09242070099980992
+                            "self": 0.08823447200029477
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,31 +2,49 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499990,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499990.onnx",
-                "reward": -0.23236671338478723,
-                "creation_time": 1662398131.4782503,
+                "steps": 499960,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499960.onnx",
+                "reward": -0.999800056219101,
+                "creation_time": 1662400558.333212,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499990.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499960.pt"
                 ]
             },
             {
-                "steps": 500118,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-500118.onnx",
-                "reward": -0.23236671338478723,
-                "creation_time": 1662398131.587565,
+                "steps": 999968,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999968.onnx",
+                "reward": 1.642499988898635,
+                "creation_time": 1662401581.4466605,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-500118.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999968.pt"
+                ]
+            },
+            {
+                "steps": 1499935,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499935.onnx",
+                "reward": 1.8949999809265137,
+                "creation_time": 1662402715.0827851,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499935.pt"
+                ]
+            },
+            {
+                "steps": 1500063,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1500063.onnx",
+                "reward": 1.8949999809265137,
+                "creation_time": 1662402715.1879466,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1500063.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 500118,
+            "steps": 1500063,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": -0.23236671338478723,
-            "creation_time": 1662398131.587565,
+            "reward": 1.8949999809265137,
+            "creation_time": 1662402715.1879466,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-500118.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1500063.pt"
             ]
         }
     },