First Pyramids

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:212004a171de41ab3f763d51d6bb2d2b6efeaf04eb67b5f5bfd8d03ccb47057e
+oid sha256:88f1483b49f6181a0a731ee0fe2995d777138143ee726dc5659f581f776172fc
 size 1417437

Pyramids/{Pyramids-349900.onnx → Pyramids-1000021.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccfce8132bcfcd5ebb90d553bcc34a814778b630bd549e6f5f30f5c72cbb4305
+oid sha256:88f1483b49f6181a0a731ee0fe2995d777138143ee726dc5659f581f776172fc
 size 1417437

Pyramids/{Pyramids-449924.pt → Pyramids-1000021.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42e9741e4b4f697cc2dc637d0b2dfd2df4f31985d0a2b91b000aff01066983d
+oid sha256:f565c5971eb664363970c27f1937cc5058e845d05587f9c88151cb46b2d222b3
 size 8652382

Pyramids/Pyramids-399987.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:42e5508a866fea9568c99bcaff5208187a7516738860d0db28427227ad6b80cf
-size 8652382

Pyramids/Pyramids-499955.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:212004a171de41ab3f763d51d6bb2d2b6efeaf04eb67b5f5bfd8d03ccb47057e
-size 1417437

Pyramids/{Pyramids-449924.onnx → Pyramids-499984.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ba0b27a232a75ba74121cdddc910067c61ae3ebf6cdea3b64dd173e6bf7fd7a
+oid sha256:6778787b997b4d39ac50a8e4ee790c09c4b83822c8a064af1dea5376d5d4838c
 size 1417437

Pyramids/{Pyramids-349900.pt → Pyramids-499984.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ab88e30d0c1ac977d46a47cf1f2629ac3e14702b495e0d960f2926f9cad8926
+oid sha256:5259a384b7a2358f3a9464500514bb0175abd127fa8b778c5296044a957c07cd
 size 8652382

Pyramids/Pyramids-500083.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:212004a171de41ab3f763d51d6bb2d2b6efeaf04eb67b5f5bfd8d03ccb47057e
-size 1417437

Pyramids/Pyramids-500083.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6878211392fdb91097324181936c87510dc1288cab7a21adc8ee51b74c6e25f8
-size 8652382

Pyramids/{Pyramids-399987.onnx → Pyramids-999992.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeaecdd407e38c23c24dea7207fa79a840485068ed3c5534dc48a0a4cd745aba
+oid sha256:88f1483b49f6181a0a731ee0fe2995d777138143ee726dc5659f581f776172fc
 size 1417437

Pyramids/{Pyramids-499955.pt → Pyramids-999992.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45bf75707fb8df43df4abc38a0131d660e351f18c6fa0825104d171ad711868f
+oid sha256:352bd814fb5bbc8c6367eedcf86b0c63507e2a3a57d9a1d463f7792089127243
 size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6878211392fdb91097324181936c87510dc1288cab7a21adc8ee51b74c6e25f8
+oid sha256:f565c5971eb664363970c27f1937cc5058e845d05587f9c88151cb46b2d222b3
 size 8652382

Pyramids/{events.out.tfevents.1660874738.404d6b244f9f.911.0 → events.out.tfevents.1661038635.bddec9ab02fc.326.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0110ab0d1f1b6400857fdcbcc7a505d378509b62ebe35bf60fa2e77f7219522
-size 138141
+oid sha256:70d302958c7d736154794a65f0d7b2c549161361be544f2414823ba1cbe83a41
+size 208098

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": 50000, "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": 1000000, "time_horizon": 128, "summary_freq": 50000, "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

@@ -48,10 +48,10 @@ behaviors:
         encoding_size: null
     init_path: null
     keep_checkpoints: 5
-    checkpoint_interval: 50000
-    max_steps: 500000
+    checkpoint_interval: 500000
+    max_steps: 1000000
     time_horizon: 128
-    summary_freq: 30000
+    summary_freq: 50000
     threaded: false
     self_play: null
     behavioral_cloning: null

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] 55332 [Flags] 2 [Guid] 202125757 [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] 55110 [Flags] 2 [Guid] 1621460397 [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  0.107 seconds
+- Completed reload, in  0.083 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: 0.890430 ms
+UnloadTime: 1.080084 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]: 4773 frames, [32.0 KB-64.0 KB]: 4032 frames, [64.0 KB-128.0 KB]: 593 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 4441 frames, [32.0 KB-64.0 KB]: 11705 frames, [64.0 KB-128.0 KB]: 2621 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
@@ -126,17 +126,17 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [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
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -149,7 +149,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 480 B
+      Peak Allocated Bytes 240 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -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]: 9100 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18469 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 12457
+  Peak main deferred allocation count 11955
     [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]: 9398 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18767 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.8 MB
+      Peak Allocated memory 29.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9399 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18768 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 21.9 MB
+      Peak Allocated memory 23.7 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]: 9398 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18767 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]: 9399 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18768 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]: 9100 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18469 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]: 9398 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18767 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]: 9399 frames
+      Peak usage frame count: [0-1.0 KB]: 18768 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]: 9399 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18768 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]: 9399 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18768 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 28.5 KB
+  Peak Allocated memory 27.4 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":1660875895201,"processId":922,"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":1661040597076,"processId":337,"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": 0.7434133887290955,
-            "min": 0.7434133887290955,
-            "max": 1.4159648418426514,
-            "count": 16
+            "value": 0.4242943525314331,
+            "min": 0.4242943525314331,
+            "max": 1.4093272686004639,
+            "count": 20
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 22314.296875,
-            "min": 22314.296875,
-            "max": 42954.7109375,
-            "count": 16
+            "value": 21235.083984375,
+            "min": 21235.083984375,
+            "max": 71909.515625,
+            "count": 20
         },
         "Pyramids.Step.mean": {
-            "value": 479963.0,
-            "min": 29952.0,
-            "max": 479963.0,
-            "count": 16
+            "value": 999992.0,
+            "min": 49981.0,
+            "max": 999992.0,
+            "count": 20
         },
         "Pyramids.Step.sum": {
-            "value": 479963.0,
-            "min": 29952.0,
-            "max": 479963.0,
-            "count": 16
+            "value": 999992.0,
+            "min": 49981.0,
+            "max": 999992.0,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.06252362579107285,
-            "min": -0.09519326686859131,
-            "max": 0.12882977724075317,
-            "count": 16
+            "value": 0.5126861333847046,
+            "min": -0.1227642223238945,
+            "max": 0.5126861333847046,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -15.193241119384766,
-            "min": -22.941577911376953,
-            "max": 30.532657623291016,
-            "count": 16
+            "value": 231.734130859375,
+            "min": -49.105690002441406,
+            "max": 231.734130859375,
+            "count": 20
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.016554778441786766,
-            "min": 0.016554778441786766,
-            "max": 0.2520255148410797,
-            "count": 16
+            "value": 0.03463253006339073,
+            "min": 0.003584560938179493,
+            "max": 0.40515077114105225,
+            "count": 20
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 4.022810935974121,
-            "min": 4.022810935974121,
-            "max": 60.486122131347656,
-            "count": 16
+            "value": 15.65390396118164,
+            "min": 1.466085433959961,
+            "max": 162.060302734375,
+            "count": 20
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06603587224326153,
-            "min": 0.06573693719203783,
-            "max": 0.07239651848596565,
-            "count": 16
+            "value": 0.06863634869942971,
+            "min": 0.06615531648147355,
+            "max": 0.07220145481884185,
+            "count": 20
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9245022114056614,
-            "min": 0.4986174256414049,
-            "max": 0.9765913942373746,
-            "count": 16
+            "value": 1.6472723687863131,
+            "min": 0.9265794129222367,
+            "max": 1.7328349156522045,
+            "count": 20
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0033305518411907826,
-            "min": 9.622271728143443e-05,
-            "max": 0.004109752835040264,
-            "count": 16
+            "value": 0.014418069885828623,
+            "min": 0.000880262116700447,
+            "max": 0.015187545013985405,
+            "count": 20
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.04662772577667096,
-            "min": 0.001347118041940082,
-            "max": 0.04662772577667096,
-            "count": 16
+            "value": 0.34603367725988693,
+            "min": 0.019365766567409834,
+            "max": 0.3645010803356497,
+            "count": 20
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.09514930162e-05,
-            "min": 2.09514930162e-05,
-            "max": 0.00029030126037577137,
-            "count": 16
+            "value": 7.340372553241669e-06,
+            "min": 7.340372553241669e-06,
+            "max": 0.0002916442643237077,
+            "count": 20
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0002933209022268,
-            "min": 0.0002933209022268,
-            "max": 0.0030625369791543993,
-            "count": 16
+            "value": 0.00017616894127780005,
+            "min": 0.00017616894127780005,
+            "max": 0.005452137382620999,
+            "count": 20
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1069838,
-            "min": 0.1069838,
-            "max": 0.19676708571428575,
-            "count": 16
+            "value": 0.10244675833333335,
+            "min": 0.10244675833333335,
+            "max": 0.19721475384615386,
+            "count": 20
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4977732000000001,
-            "min": 1.3382272,
-            "max": 2.254682,
-            "count": 16
+            "value": 2.4587222000000004,
+            "min": 2.4587222000000004,
+            "max": 4.0837108,
+            "count": 20
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0007076816200000001,
-            "min": 0.0007076816200000001,
-            "max": 0.00967703186285714,
-            "count": 16
+            "value": 0.0002544311575000001,
+            "min": 0.0002544311575000001,
+            "max": 0.00972175390923077,
+            "count": 20
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.00990754268,
-            "min": 0.00990754268,
-            "max": 0.10210247543999999,
-            "count": 16
+            "value": 0.006106347780000002,
+            "min": 0.006106347780000002,
+            "max": 0.1817761621,
+            "count": 20
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.01608044095337391,
-            "min": 0.01608044095337391,
-            "max": 0.2806084454059601,
-            "count": 16
+            "value": 0.012546318583190441,
+            "min": 0.012509429827332497,
+            "max": 0.2747448980808258,
+            "count": 20
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.22512616217136383,
-            "min": 0.22512616217136383,
-            "max": 1.9642590284347534,
-            "count": 16
+            "value": 0.30111163854599,
+            "min": 0.28771689534187317,
+            "max": 3.571683645248413,
+            "count": 20
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 936.4242424242424,
-            "min": 903.9411764705883,
-            "max": 999.0,
-            "count": 16
+            "value": 363.55,
+            "min": 363.55,
+            "max": 997.6041666666666,
+            "count": 20
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30902.0,
-            "min": 15984.0,
-            "max": 32644.0,
-            "count": 16
+            "value": 50897.0,
+            "min": 47044.0,
+            "max": 53410.0,
+            "count": 20
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.5126788327188203,
-            "min": -1.0000000521540642,
-            "max": -0.5126788327188203,
-            "count": 16
+            "value": 1.5332891867636778,
+            "min": -0.9569167188989619,
+            "max": 1.5332891867636778,
+            "count": 20
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -16.91840147972107,
-            "min": -32.000001668930054,
-            "max": -13.530801147222519,
-            "count": 16
+            "value": 213.1271969601512,
+            "min": -45.93200250715017,
+            "max": 213.1271969601512,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.5126788327188203,
-            "min": -1.0000000521540642,
-            "max": -0.5126788327188203,
-            "count": 16
+            "value": 1.5332891867636778,
+            "min": -0.9569167188989619,
+            "max": 1.5332891867636778,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -16.91840147972107,
-            "min": -32.000001668930054,
-            "max": -13.530801147222519,
-            "count": 16
+            "value": 213.1271969601512,
+            "min": -45.93200250715017,
+            "max": 213.1271969601512,
+            "count": 20
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.15698340889348678,
-            "min": 0.15698340889348678,
-            "max": 5.1650382513180375,
-            "count": 16
+            "value": 0.0480055328456035,
+            "min": 0.0480055328456035,
+            "max": 3.7991478253776827,
+            "count": 20
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 5.180452493485063,
-            "min": 5.180452493485063,
-            "max": 82.6406120210886,
-            "count": 16
+            "value": 6.672769065538887,
+            "min": 6.190021476068068,
+            "max": 182.35909561812878,
+            "count": 20
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
+            "count": 20
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
+            "count": 20
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1660874730",
+        "start_time_seconds": "1661038628",
         "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": "1660875895"
+        "end_time_seconds": "1661040597"
     },
-    "total": 1164.9212725590005,
+    "total": 1968.2627793349998,
     "count": 1,
-    "self": 0.53649120900036,
+    "self": 0.47653668299972196,
     "children": {
         "run_training.setup": {
-            "total": 0.0632450059997609,
+            "total": 0.04291885099996762,
             "count": 1,
-            "self": 0.0632450059997609
+            "self": 0.04291885099996762
         },
         "TrainerController.start_learning": {
-            "total": 1164.3215363440004,
+            "total": 1967.743323801,
             "count": 1,
-            "self": 0.8257684760678785,
+            "self": 1.329606279989548,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 10.570688660000087,
+                    "total": 9.354747836000115,
                     "count": 1,
-                    "self": 10.570688660000087
+                    "self": 9.354747836000115
                 },
                 "TrainerController.advance": {
-                    "total": 1152.8096506279321,
-                    "count": 31520,
-                    "self": 0.9037352339619247,
+                    "total": 1956.9653390600104,
+                    "count": 63631,
+                    "self": 1.3999839279820208,
                     "children": {
                         "env_step": {
-                            "total": 706.6603270160099,
-                            "count": 31520,
-                            "self": 633.3907426699984,
+                            "total": 1263.8576822490381,
+                            "count": 63631,
+                            "self": 1162.9751128650016,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 72.84539202202359,
-                                    "count": 31520,
-                                    "self": 3.012815553167002,
+                                    "total": 100.17732810501343,
+                                    "count": 63631,
+                                    "self": 4.5819465401159505,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 69.83257646885659,
-                                            "count": 31330,
-                                            "self": 24.59598348594318,
+                                            "total": 95.59538156489748,
+                                            "count": 62558,
+                                            "self": 34.02026225591794,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 45.23659298291341,
-                                                    "count": 31330,
-                                                    "self": 45.23659298291341
+                                                    "total": 61.57511930897954,
+                                                    "count": 62558,
+                                                    "self": 61.57511930897954
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.42419232398788154,
-                                    "count": 31520,
+                                    "total": 0.7052412790230846,
+                                    "count": 63631,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1161.9478368390428,
-                                            "count": 31520,
+                                            "total": 1963.731069005034,
+                                            "count": 63631,
                                             "is_parallel": true,
-                                            "self": 592.0339420101022,
+                                            "self": 900.5146379980501,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0063251360002141155,
+                                                            "total": 0.006084160000000338,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.004704239001057431,
+                                                            "self": 0.004933731999926749,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0016208969991566846,
+                                                                    "total": 0.001150428000073589,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0016208969991566846
+                                                                    "self": 0.001150428000073589
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06018109600017851,
+                                                            "total": 0.04638965399999506,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006120319999354251,
+                                                            "self": 0.0005272749999676307,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.000661209000099916,
+                                                                    "total": 0.00044776000004276284,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000661209000099916
+                                                                    "self": 0.00044776000004276284
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.05644909800003006,
+                                                                    "total": 0.0438198189999639,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.05644909800003006
+                                                                    "self": 0.0438198189999639
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.00245875700011311,
+                                                                    "total": 0.0015948000000207685,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008858399996825028,
+                                                                    "self": 0.00040331900004275667,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001572917000430607,
+                                                                            "total": 0.0011914809999780118,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001572917000430607
+                                                                            "self": 0.0011914809999780118
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 569.9138948289406,
-                                                    "count": 31519,
+                                                    "total": 1063.2164310069838,
+                                                    "count": 63630,
                                                     "is_parallel": true,
-                                                    "self": 16.649241480894034,
+                                                    "self": 26.995305528965446,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 15.647940984973502,
-                                                            "count": 31519,
+                                                            "total": 22.210597863977227,
+                                                            "count": 63630,
                                                             "is_parallel": true,
-                                                            "self": 15.647940984973502
+                                                            "self": 22.210597863977227
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 476.543193222029,
-                                                            "count": 31519,
+                                                            "total": 923.5843695849821,
+                                                            "count": 63630,
                                                             "is_parallel": true,
-                                                            "self": 476.543193222029
+                                                            "self": 923.5843695849821
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 61.07351914104402,
-                                                            "count": 31519,
+                                                            "total": 90.42615802905902,
+                                                            "count": 63630,
                                                             "is_parallel": true,
-                                                            "self": 16.48834020427512,
+                                                            "self": 22.29651465890629,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 44.5851789367689,
-                                                                    "count": 252152,
+                                                                    "total": 68.12964337015273,
+                                                                    "count": 509040,
                                                                     "is_parallel": true,
-                                                                    "self": 44.5851789367689
+                                                                    "self": 68.12964337015273
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 445.2455883779603,
-                            "count": 31520,
-                            "self": 1.1812028509043557,
+                            "total": 691.7076728829902,
+                            "count": 63631,
+                            "self": 2.4560120970388652,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 99.40918557506484,
-                                    "count": 31520,
-                                    "self": 98.2335272090645,
+                                    "total": 158.03512920394815,
+                                    "count": 63631,
+                                    "self": 157.71700489194836,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.1756583660003344,
-                                            "count": 10,
-                                            "self": 1.1756583660003344
+                                            "total": 0.31812431199978164,
+                                            "count": 2,
+                                            "self": 0.31812431199978164
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 344.6551999519911,
-                                    "count": 207,
-                                    "self": 124.77479632408995,
+                                    "total": 531.2165315820032,
+                                    "count": 449,
+                                    "self": 212.32515604799391,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 219.88040362790116,
-                                            "count": 11472,
-                                            "self": 219.88040362790116
+                                            "total": 318.8913755340093,
+                                            "count": 22854,
+                                            "self": 318.8913755340093
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.1670008461805992e-06,
+                    "total": 1.190000148199033e-06,
                     "count": 1,
-                    "self": 1.1670008461805992e-06
+                    "self": 1.190000148199033e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.11542741299945192,
+                    "total": 0.09362943499991161,
                     "count": 1,
-                    "self": 0.0018925759986814228,
+                    "self": 0.001927646999774879,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1135348370007705,
+                            "total": 0.09170178800013673,
                             "count": 1,
-                            "self": 0.1135348370007705
+                            "self": 0.09170178800013673
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 349900,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-349900.onnx",
+                "steps": 499984,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499984.onnx",
                 "reward": null,
-                "creation_time": 1660875543.8485994,
+                "creation_time": 1661039580.6132777,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-349900.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499984.pt"
                 ]
             },
             {
-                "steps": 399987,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-399987.onnx",
-                "reward": -1.0000000521540642,
-                "creation_time": 1660875660.5164857,
+                "steps": 999992,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999992.onnx",
+                "reward": 1.105999916791916,
+                "creation_time": 1661040596.5589402,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-399987.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999992.pt"
                 ]
             },
             {
-                "steps": 449924,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-449924.onnx",
-                "reward": null,
-                "creation_time": 1660875777.845972,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-449924.pt"
-                ]
-            },
-            {
-                "steps": 499955,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499955.onnx",
-                "reward": -0.09846669187148412,
-                "creation_time": 1660875894.5800695,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499955.pt"
-                ]
-            },
-            {
-                "steps": 500083,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-500083.onnx",
-                "reward": -0.09846669187148412,
-                "creation_time": 1660875894.7253795,
+                "steps": 1000021,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000021.onnx",
+                "reward": 1.5389999598264694,
+                "creation_time": 1661040596.6572416,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-500083.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000021.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 500083,
+            "steps": 1000021,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": -0.09846669187148412,
-            "creation_time": 1660875894.7253795,
+            "reward": 1.5389999598264694,
+            "creation_time": 1661040596.6572416,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-500083.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000021.pt"
             ]
         }
     },