First Pyramids

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd092f7980b09c85105f4666aa8c085e7c1b83abcc9008708a77c9aaa456457
+oid sha256:205bbc784b7338194e65aeabd4472fe50f74c3920f31a867a59f562c71d3e6ee
 size 1417437

Pyramids/{Pyramids-1000078.onnx → Pyramids-1499939.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd092f7980b09c85105f4666aa8c085e7c1b83abcc9008708a77c9aaa456457
+oid sha256:373dea9a09dac0baf0c99434d520f90911935bfc25831aef67b381dfd22b47a5
 size 1417437

Pyramids/{Pyramids-999950.pt → Pyramids-1499939.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:030db94b8e13893576259ea171379497b84ed09a6e1f11d61488662de6023274
+oid sha256:9a1215e13d412eba5a36f5ccff44e41d0da0b9fc21e6f239d20da6ac48e32dec
 size 8652382

Pyramids/{Pyramids-999950.onnx → Pyramids-1999996.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd092f7980b09c85105f4666aa8c085e7c1b83abcc9008708a77c9aaa456457
+oid sha256:205bbc784b7338194e65aeabd4472fe50f74c3920f31a867a59f562c71d3e6ee
 size 1417437

Pyramids/{Pyramids-1000078.pt → Pyramids-1999996.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac3316dbdc2ffe22bab8e241cbecb18e1b70a7143add4f347efea0d185b6d376
+oid sha256:5e538d931959a52876c2099faea33b078809f4ffc090626a39d28610b442b143
 size 8652382

Pyramids/{Pyramids-499914.onnx → Pyramids-2000252.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:831524841eec3cbb7747bdf783bedc085034727be84d126a342314f52f8d1db9
+oid sha256:205bbc784b7338194e65aeabd4472fe50f74c3920f31a867a59f562c71d3e6ee
 size 1417437

Pyramids/{Pyramids-499914.pt → Pyramids-2000252.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10d4aae718128b38d19338c479d096243d7950ef98d4bdfac7ab884a51d9fac
+oid sha256:05c1bf34ccf5e170bb3ffec7a944623422be6ede50568ecfe6c1144caba78760
 size 8652382

Pyramids/Pyramids-499999.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20581c24958d255311fb1752405be72cb2f9aa5ec3d1b5a2773b1b00d0cc2668
+size 1417437

Pyramids/Pyramids-499999.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb1eca19d94bcc56d177b634078deded42ab4586e21b987edeeee1bd52f16a5
+size 8652382

Pyramids/Pyramids-999938.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f37c7e7975bc2552792ed32f6a2fa85013d006c2bd0c211ddf6be78ff8f441
+size 1417437

Pyramids/Pyramids-999938.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a605125c6c459aa7bd69e05bf92dfac9324016192e63458c82fbdcb6747bfcc
+size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac3316dbdc2ffe22bab8e241cbecb18e1b70a7143add4f347efea0d185b6d376
+oid sha256:05c1bf34ccf5e170bb3ffec7a944623422be6ede50568ecfe6c1144caba78760
 size 8652382

Pyramids/{events.out.tfevents.1658988369.ffeb5670e16e.242.0 → events.out.tfevents.1658995511.aee4839c3045.264.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac920909ec2c471a3eb3554fdf0571dbdd96bd223703ee56305efef33695ed47
-size 323357
+oid sha256:1e06730363f1b8592ef5732c517df4760e4a9729bd7063e8e168d8138b54b4bd
+size 665385

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": 1000000, "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": 2000000, "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: 1000000
+    max_steps: 2000000
     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] 55420 [Flags] 2 [Guid] 3399250847 [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] 55490 [Flags] 2 [Guid] 50212950 [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
@@ -36,7 +36,7 @@ ALSA lib pcm.c:2495:(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  0.097 seconds
+- Completed reload, in  0.091 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)
@@ -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: 1.053185 ms
+UnloadTime: 0.781406 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]: 6613 frames, [32.0 KB-64.0 KB]: 9893 frames, [64.0 KB-128.0 KB]: 2266 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 4126 frames, [32.0 KB-64.0 KB]: 24618 frames, [64.0 KB-128.0 KB]: 8776 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
@@ -131,12 +131,12 @@ PlayerConnection::CleanupMemory Statistics:
       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
       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
@@ -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]: 18474 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37222 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.5 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12717
+  Peak main deferred allocation count 11726
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       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]: 18772 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37520 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.9 MB
+      Peak Allocated memory 30.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18773 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37521 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.8 MB
+      Peak Allocated memory 22.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +257,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18772 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37520 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]: 18773 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 37521 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,16 +275,16 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       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]: 18474 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37222 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]: 18772 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 37520 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 3.9 MB
+      Peak Block count 2
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -293,25 +293,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18773 frames
+      Peak usage frame count: [0-1.0 KB]: 37521 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]: 18773 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37521 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]: 18773 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 37521 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 28.5 KB
+  Peak Allocated memory 29.0 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":1658990412786,"processId":253,"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":1658999863065,"processId":275,"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": 0.5707029700279236,
-            "min": 0.5652757883071899,
-            "max": 1.4192875623703003,
-            "count": 33
+            "value": 0.20300835371017456,
+            "min": 0.2019643932580948,
+            "max": 1.4366331100463867,
+            "count": 66
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 17340.23828125,
-            "min": 16768.341796875,
-            "max": 43055.5078125,
-            "count": 33
+            "value": 6103.2431640625,
+            "min": 6071.857421875,
+            "max": 43581.703125,
+            "count": 66
         },
         "Pyramids.Step.mean": {
-            "value": 989984.0,
+            "value": 1979997.0,
             "min": 29952.0,
-            "max": 989984.0,
-            "count": 33
+            "max": 1979997.0,
+            "count": 66
         },
         "Pyramids.Step.sum": {
-            "value": 989984.0,
+            "value": 1979997.0,
             "min": 29952.0,
-            "max": 989984.0,
-            "count": 33
+            "max": 1979997.0,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.3308829069137573,
-            "min": -0.11201882362365723,
-            "max": 0.4245678186416626,
-            "count": 33
+            "value": 0.7301263809204102,
+            "min": -0.2526001036167145,
+            "max": 0.7522621154785156,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 87.35308837890625,
-            "min": -26.996536254882812,
-            "max": 112.08590698242188,
-            "count": 33
+            "value": 217.57766723632812,
+            "min": -59.8662223815918,
+            "max": 218.156005859375,
+            "count": 66
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.20673494040966034,
-            "min": -0.20673494040966034,
-            "max": 0.3777506947517395,
-            "count": 33
+            "value": 0.011847416870296001,
+            "min": -0.013323443941771984,
+            "max": 0.402437686920166,
+            "count": 66
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -54.578025817871094,
-            "min": -54.578025817871094,
-            "max": 89.52691650390625,
-            "count": 33
+            "value": 3.5305302143096924,
+            "min": -3.7705345153808594,
+            "max": 95.37773132324219,
+            "count": 66
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06530816703716048,
-            "min": 0.06441761891703096,
-            "max": 0.07412208779848813,
-            "count": 33
+            "value": 0.06972024323754124,
+            "min": 0.06557783964888161,
+            "max": 0.074941841448852,
+            "count": 66
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9143143385202468,
-            "min": 0.5188546145894168,
-            "max": 1.0496506169147322,
-            "count": 33
+            "value": 0.9760834053255774,
+            "min": 0.5318717031581739,
+            "max": 1.12412762173278,
+            "count": 66
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01973478001344206,
-            "min": 9.869663770396387e-05,
-            "max": 0.01973478001344206,
-            "count": 33
+            "value": 0.018101951712448962,
+            "min": 0.00025127126369823107,
+            "max": 0.019327633255130913,
+            "count": 66
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.27628692018818884,
-            "min": 0.0012830562901515303,
-            "max": 0.27628692018818884,
-            "count": 33
+            "value": 0.25342732397428547,
+            "min": 0.003266526428077004,
+            "max": 0.2899144988269637,
+            "count": 66
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.657597447500003e-06,
-            "min": 7.657597447500003e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 5.349548216850002e-06,
+            "min": 5.349548216850002e-06,
+            "max": 0.00029750655083115,
+            "count": 66
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010720636426500004,
-            "min": 0.00010720636426500004,
-            "max": 0.0035078069307311,
-            "count": 33
+            "value": 7.489367503590004e-05,
+            "min": 7.489367503590004e-05,
+            "max": 0.0038537651654116495,
+            "count": 66
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1025525,
-            "min": 0.1025525,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10178315,
+            "min": 0.10178315,
+            "max": 0.19916885,
+            "count": 66
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.435735,
-            "min": 1.3886848,
-            "max": 2.5692689,
-            "count": 33
+            "value": 1.4249641,
+            "min": 1.4249641,
+            "max": 2.68458835,
+            "count": 66
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002649947500000001,
-            "min": 0.0002649947500000001,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 0.00018813668500000007,
+            "min": 0.00018813668500000007,
+            "max": 0.009916968115,
+            "count": 66
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0037099265000000016,
-            "min": 0.0037099265000000016,
-            "max": 0.11694996311000001,
-            "count": 33
+            "value": 0.002633913590000001,
+            "min": 0.002633913590000001,
+            "max": 0.128470376165,
+            "count": 66
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.009012033231556416,
-            "min": 0.009012033231556416,
-            "max": 0.5463701486587524,
-            "count": 33
+            "value": 0.014539936557412148,
+            "min": 0.013399133458733559,
+            "max": 0.5337237119674683,
+            "count": 66
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.12616845965385437,
-            "min": 0.12616845965385437,
-            "max": 3.8245911598205566,
-            "count": 33
+            "value": 0.20355911552906036,
+            "min": 0.18758787214756012,
+            "max": 4.269789695739746,
+            "count": 66
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 486.0169491525424,
-            "min": 434.28985507246375,
+            "value": 256.12213740458014,
+            "min": 236.38053097345133,
             "max": 999.0,
-            "count": 33
+            "count": 66
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 28675.0,
-            "min": 15984.0,
-            "max": 33317.0,
-            "count": 33
+            "value": 33552.0,
+            "min": 16879.0,
+            "max": 33552.0,
+            "count": 66
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.3156633096436658,
-            "min": -1.0000000521540642,
-            "max": 1.4542828294847692,
-            "count": 33
+            "value": 1.6987461390976721,
+            "min": -0.9998800521095593,
+            "max": 1.7459185708940557,
+            "count": 66
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 78.93979857861996,
-            "min": -31.992801651358604,
-            "max": 101.79979806393385,
-            "count": 33
+            "value": 220.8369980826974,
+            "min": -30.67660166323185,
+            "max": 220.8369980826974,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.3156633096436658,
-            "min": -1.0000000521540642,
-            "max": 1.4542828294847692,
-            "count": 33
+            "value": 1.6987461390976721,
+            "min": -0.9998800521095593,
+            "max": 1.7459185708940557,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 78.93979857861996,
-            "min": -31.992801651358604,
-            "max": 101.79979806393385,
-            "count": 33
+            "value": 220.8369980826974,
+            "min": -30.67660166323185,
+            "max": 220.8369980826974,
+            "count": 66
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.0455802654454601,
-            "min": 0.04320424944323479,
-            "max": 12.436921145766973,
-            "count": 33
+            "value": 0.0380367309284898,
+            "min": 0.03531887073330458,
+            "max": 10.794082702959285,
+            "count": 66
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 2.734815926727606,
-            "min": 2.734815926727606,
-            "max": 198.99073833227158,
-            "count": 33
+            "value": 4.944775020703673,
+            "min": 3.991032392863417,
+            "max": 183.49940595030785,
+            "count": 66
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 66
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 66
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1658988362",
+        "start_time_seconds": "1658995504",
         "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": "1658990412"
+        "end_time_seconds": "1658999863"
     },
-    "total": 2050.333355068,
+    "total": 4358.502690823,
     "count": 1,
-    "self": 0.48244012299983297,
+    "self": 0.4326148780000949,
     "children": {
         "run_training.setup": {
-            "total": 0.045549928999889744,
+            "total": 0.04722142499997517,
             "count": 1,
-            "self": 0.045549928999889744
+            "self": 0.04722142499997517
         },
         "TrainerController.start_learning": {
-            "total": 2049.805365016,
+            "total": 4358.02285452,
             "count": 1,
-            "self": 1.3576895269975466,
+            "self": 2.8589677472173207,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 10.276445191999983,
+                    "total": 9.919946798999945,
                     "count": 1,
-                    "self": 10.276445191999983
+                    "self": 9.919946798999945
                 },
                 "TrainerController.advance": {
-                    "total": 2038.072568757002,
-                    "count": 63535,
-                    "self": 1.463854486995615,
+                    "total": 4345.146914172782,
+                    "count": 129049,
+                    "self": 2.9716973377680915,
                     "children": {
                         "env_step": {
-                            "total": 1303.0495930189945,
-                            "count": 63535,
-                            "self": 1194.6274865239152,
+                            "total": 2925.3026828039883,
+                            "count": 129049,
+                            "self": 2714.06150484997,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 107.70092588006867,
-                                    "count": 63535,
-                                    "self": 4.590606086016464,
+                                    "total": 209.71796717096026,
+                                    "count": 129049,
+                                    "self": 9.249887337981932,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 103.1103197940522,
-                                            "count": 62576,
-                                            "self": 35.43870386903279,
+                                            "total": 200.46807983297833,
+                                            "count": 125070,
+                                            "self": 69.11174669599723,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 67.67161592501941,
-                                                    "count": 62576,
-                                                    "self": 67.67161592501941
+                                                    "total": 131.3563331369811,
+                                                    "count": 125070,
+                                                    "self": 131.3563331369811
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7211806150107805,
-                                    "count": 63535,
+                                    "total": 1.5232107830581754,
+                                    "count": 129049,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2045.8289891430084,
-                                            "count": 63535,
+                                            "total": 4350.3912791900975,
+                                            "count": 129049,
                                             "is_parallel": true,
-                                            "self": 951.8585412830455,
+                                            "self": 1841.0555276002588,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005277987999988909,
+                                                            "total": 0.004918567000004259,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003992724000113412,
+                                                            "self": 0.0037248590000444892,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0012852639998754967,
+                                                                    "total": 0.00119370799995977,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0012852639998754967
+                                                                    "self": 0.00119370799995977
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.052235718000019915,
+                                                            "total": 0.04730065600006128,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000574067999991712,
+                                                            "self": 0.00048253400007070013,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004943810000668236,
+                                                                    "total": 0.0004758110000011584,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004943810000668236
+                                                                    "self": 0.0004758110000011584
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04933667199998126,
+                                                                    "total": 0.044645900999967125,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04933667199998126
+                                                                    "self": 0.044645900999967125
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018305969999801164,
+                                                                    "total": 0.001696410000022297,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004934720000164816,
+                                                                    "self": 0.0004122689999803697,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013371249999636348,
+                                                                            "total": 0.0012841410000419273,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013371249999636348
+                                                                            "self": 0.0012841410000419273
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1093.9704478599629,
-                                                    "count": 63534,
+                                                    "total": 2509.3357515898388,
+                                                    "count": 129048,
                                                     "is_parallel": true,
-                                                    "self": 28.027807311935703,
+                                                    "self": 55.232047675888225,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 23.418423961032204,
-                                                            "count": 63534,
+                                                            "total": 45.146936263945236,
+                                                            "count": 129048,
                                                             "is_parallel": true,
-                                                            "self": 23.418423961032204
+                                                            "self": 45.146936263945236
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 948.0988161160222,
-                                                            "count": 63534,
+                                                            "total": 2223.640614896024,
+                                                            "count": 129048,
                                                             "is_parallel": true,
-                                                            "self": 948.0988161160222
+                                                            "self": 2223.640614896024
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 94.4254004709727,
-                                                            "count": 63534,
+                                                            "total": 185.31615275398087,
+                                                            "count": 129048,
                                                             "is_parallel": true,
-                                                            "self": 23.034110384859332,
+                                                            "self": 46.08055515370859,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 71.39129008611337,
-                                                                    "count": 508272,
+                                                                    "total": 139.23559760027229,
+                                                                    "count": 1032384,
                                                                     "is_parallel": true,
-                                                                    "self": 71.39129008611337
+                                                                    "self": 139.23559760027229
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 733.5591212510119,
-                            "count": 63535,
-                            "self": 2.460579467997036,
+                            "total": 1416.8725340310255,
+                            "count": 129049,
+                            "self": 5.430656277142589,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 165.45096842401574,
-                                    "count": 63535,
-                                    "self": 165.23889287801592,
+                                    "total": 328.12923190288507,
+                                    "count": 129049,
+                                    "self": 327.74463720988524,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.2120755459998236,
-                                            "count": 2,
-                                            "self": 0.2120755459998236
+                                            "total": 0.3845946929998263,
+                                            "count": 4,
+                                            "self": 0.3845946929998263
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 565.6475733589991,
-                                    "count": 450,
-                                    "self": 222.9515593279782,
+                                    "total": 1083.3126458509978,
+                                    "count": 929,
+                                    "self": 425.476061513079,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 342.6960140310209,
-                                            "count": 22806,
-                                            "self": 342.6960140310209
+                                            "total": 657.8365843379188,
+                                            "count": 45591,
+                                            "self": 657.8365843379188
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.1679999261104967e-06,
+                    "total": 1.3310000213095918e-06,
                     "count": 1,
-                    "self": 1.1679999261104967e-06
+                    "self": 1.3310000213095918e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09866037200026767,
+                    "total": 0.09702447000017855,
                     "count": 1,
-                    "self": 0.001551199000004999,
+                    "self": 0.0016013799995562294,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09710917300026267,
+                            "total": 0.09542309000062232,
                             "count": 1,
-                            "self": 0.09710917300026267
+                            "self": 0.09542309000062232
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499914,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499914.onnx",
-                "reward": 1.2359998971223831,
-                "creation_time": 1658989344.3153174,
+                "steps": 499999,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499999.onnx",
+                "reward": 1.645499974489212,
+                "creation_time": 1658996452.4237454,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499914.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499999.pt"
                 ]
             },
             {
-                "steps": 999950,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999950.onnx",
-                "reward": 1.763999953866005,
-                "creation_time": 1658990412.2561576,
+                "steps": 999938,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999938.onnx",
+                "reward": 1.6199999650319417,
+                "creation_time": 1658997536.5221515,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999950.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999938.pt"
                 ]
             },
             {
-                "steps": 1000078,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000078.onnx",
-                "reward": 1.763999953866005,
-                "creation_time": 1658990412.3705745,
+                "steps": 1499939,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499939.onnx",
+                "reward": 1.8122499734163284,
+                "creation_time": 1658998679.7563295,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000078.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1499939.pt"
+                ]
+            },
+            {
+                "steps": 1999996,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999996.onnx",
+                "reward": 1.7933333069086075,
+                "creation_time": 1658999862.5503507,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999996.pt"
+                ]
+            },
+            {
+                "steps": 2000252,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2000252.onnx",
+                "reward": 1.7933333069086075,
+                "creation_time": 1658999862.6818442,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2000252.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000078,
+            "steps": 2000252,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.763999953866005,
-            "creation_time": 1658990412.3705745,
+            "reward": 1.7933333069086075,
+            "creation_time": 1658999862.6818442,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000078.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-2000252.pt"
             ]
         }
     },