Second Pyramids

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3134eeac4c02947ddd5c232438929b3faf410bdcfadc5db37110451c2925d1
+oid sha256:35fcc597fa08be212fe14033e0859399eaa75c82b3bc425c7fe0886fa4d1a2c3
 size 1417437

Pyramids/{Pyramids-499967.onnx → Pyramids-1000102.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3134eeac4c02947ddd5c232438929b3faf410bdcfadc5db37110451c2925d1
+oid sha256:35fcc597fa08be212fe14033e0859399eaa75c82b3bc425c7fe0886fa4d1a2c3
 size 1417437

Pyramids/{Pyramids-499967.pt → Pyramids-1000102.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53438470f69828951a3db85aca6bde8ad9643b34da0acae6429263787d008292
+oid sha256:0489c2dd56deedbc38733bb885a6e8e884d9846926b18d783a696c3d7b3ff298
 size 8652382

Pyramids/{Pyramids-500095.onnx → Pyramids-499872.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3134eeac4c02947ddd5c232438929b3faf410bdcfadc5db37110451c2925d1
+oid sha256:5cbb197991a4292ad7ff4fe905096d59592db4f452467d441927b04d34fa56e0
 size 1417437

Pyramids/{Pyramids-500095.pt → Pyramids-499872.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f879357c4b9408db6bba6b84d994d5aae4bc2510f0575cd224ab27b5dfd79f44
+oid sha256:7c59cbde1b1503981637552d024a46ea3c1c4615c76e3523c106d8dd71b28f30
 size 8652382

Pyramids/Pyramids-999974.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fcc597fa08be212fe14033e0859399eaa75c82b3bc425c7fe0886fa4d1a2c3
+size 1417437

Pyramids/Pyramids-999974.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3b442d646272acbd707a480af43fd4ff637ce0b0d41b46b8a887ad7a2764ec
+size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f879357c4b9408db6bba6b84d994d5aae4bc2510f0575cd224ab27b5dfd79f44
+oid sha256:0489c2dd56deedbc38733bb885a6e8e884d9846926b18d783a696c3d7b3ff298
 size 8652382

Pyramids/{events.out.tfevents.1658534120.4d5e1c6b049b.263.0 → events.out.tfevents.1659090169.0d6510d11b97.253.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0bf630d374a6c10cb2be8d61bbb90a858f458735c6f955b7755b93c071c54a4
-size 157208
+oid sha256:cb0131523565156c15785a4fd93271102f4c683992ec81f4a90cadb3d790a0d5
+size 323757

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 500000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 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}

configuration.yaml

@@ -49,7 +49,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 500000
-    max_steps: 500000
+    max_steps: 1000000
     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] 55332 [Flags] 2 [Guid] 1234792767 [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] 55148 [Flags] 2 [Guid] 437851300 [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  0.082 seconds
+- Completed reload, in  0.079 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: 0.798349 ms
+UnloadTime: 0.835685 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]: 3918 frames, [32.0 KB-64.0 KB]: 4753 frames, [64.0 KB-128.0 KB]: 726 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3130 frames, [32.0 KB-64.0 KB]: 12329 frames, [64.0 KB-128.0 KB]: 3309 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 240 B
+      Peak Allocated Bytes 480 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -186,12 +186,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       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 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       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]: 9099 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 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 12856
+  Peak main deferred allocation count 13086
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 9397 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18768 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.4 MB
+      Peak Allocated memory 31.1 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9398 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.7 MB
+      Peak Allocated memory 22.9 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 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 9397 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18768 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]: 9398 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18769 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 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 9099 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 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]: 9397 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18768 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 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9398 frames
+      Peak usage frame count: [0-1.0 KB]: 18769 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]: 9398 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18769 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]: 9398 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18769 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 27.4 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":1658535073398,"processId":276,"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":1659092162955,"processId":264,"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": 1.110069751739502,
-            "min": 0.9890919923782349,
-            "max": 1.4185805320739746,
-            "count": 16
+            "value": 0.5430715680122375,
+            "min": 0.5403998494148254,
+            "max": 1.5356767177581787,
+            "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 33302.09375,
-            "min": 29475.595703125,
-            "max": 43034.05859375,
-            "count": 16
+            "value": 16396.416015625,
+            "min": 16226.873046875,
+            "max": 46586.2890625,
+            "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 479954.0,
-            "min": 29943.0,
-            "max": 479954.0,
-            "count": 16
+            "value": 989972.0,
+            "min": 29952.0,
+            "max": 989972.0,
+            "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 479954.0,
-            "min": 29943.0,
-            "max": 479954.0,
-            "count": 16
+            "value": 989972.0,
+            "min": 29952.0,
+            "max": 989972.0,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.06036869063973427,
-            "min": -0.10721182823181152,
-            "max": 0.06036869063973427,
-            "count": 16
+            "value": 0.6008288860321045,
+            "min": -0.15741822123527527,
+            "max": 0.6525148153305054,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 14.85069751739502,
-            "min": -25.945262908935547,
-            "max": 14.85069751739502,
-            "count": 16
+            "value": 169.43374633789062,
+            "min": -37.3081169128418,
+            "max": 185.314208984375,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.014573533087968826,
-            "min": 0.013385391794145107,
-            "max": 0.2983815670013428,
-            "count": 16
+            "value": 0.017631975933909416,
+            "min": -0.015849707648158073,
+            "max": 0.1572844386100769,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 3.5850892066955566,
-            "min": 3.3061916828155518,
-            "max": 70.7164306640625,
-            "count": 16
+            "value": 4.972217082977295,
+            "min": -4.231872081756592,
+            "max": 37.905548095703125,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06925801912940424,
-            "min": 0.06414966257095026,
-            "max": 0.07345774902005434,
-            "count": 16
+            "value": 0.06644938790885221,
+            "min": 0.06539722719937054,
+            "max": 0.07244533984800403,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9696122678116593,
-            "min": 0.5142042431403804,
-            "max": 1.0128582429509456,
-            "count": 16
+            "value": 0.930291430723931,
+            "min": 0.4938564800510809,
+            "max": 1.0481661860608522,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.008042843648456931,
-            "min": 0.0013420449094047363,
-            "max": 0.012665419527132118,
-            "count": 16
+            "value": 0.01443157536587456,
+            "min": 0.0007922115109313758,
+            "max": 0.015847796152229417,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.11259981107839705,
-            "min": 0.0152194621134393,
-            "max": 0.11259981107839705,
-            "count": 16
+            "value": 0.20204205512224385,
+            "min": 0.010000805916912088,
+            "max": 0.23771694228344128,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.115797866165714e-05,
-            "min": 2.115797866165714e-05,
-            "max": 0.0002904658317494857,
-            "count": 16
+            "value": 7.487583218457144e-06,
+            "min": 7.487583218457144e-06,
+            "max": 0.00029515063018788575,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00029621170126319996,
-            "min": 0.00029621170126319996,
-            "max": 0.0030650017783327996,
-            "count": 16
+            "value": 0.00010482616505840001,
+            "min": 0.00010482616505840001,
+            "max": 0.0035088803303732993,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10705262857142858,
-            "min": 0.10705262857142858,
-            "max": 0.19682194285714288,
-            "count": 16
+            "value": 0.10249582857142857,
+            "min": 0.10249582857142857,
+            "max": 0.19838354285714285,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4987368,
-            "min": 1.3777536000000001,
-            "max": 2.2216672,
-            "count": 16
+            "value": 1.4349416,
+            "min": 1.3691136000000002,
+            "max": 2.5696267,
+            "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0007145575942857144,
-            "min": 0.0007145575942857144,
-            "max": 0.009682512091428569,
-            "count": 16
+            "value": 0.00025933327428571436,
+            "min": 0.00025933327428571436,
+            "max": 0.00983851593142857,
+            "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.010003806320000001,
-            "min": 0.010003806320000001,
-            "max": 0.10218455328,
-            "count": 16
+            "value": 0.003630665840000001,
+            "min": 0.003630665840000001,
+            "max": 0.11698570733,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.01777505688369274,
-            "min": 0.01757083460688591,
-            "max": 0.47891396284103394,
-            "count": 16
+            "value": 0.009175741113722324,
+            "min": 0.009175741113722324,
+            "max": 0.28511667251586914,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.24885079264640808,
-            "min": 0.24599169194698334,
-            "max": 3.3523976802825928,
-            "count": 16
+            "value": 0.1284603774547577,
+            "min": 0.1284603774547577,
+            "max": 1.995816707611084,
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 729.8780487804878,
-            "min": 729.8780487804878,
+            "value": 333.7340425531915,
+            "min": 290.4270833333333,
             "max": 999.0,
-            "count": 16
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29925.0,
-            "min": 17637.0,
-            "max": 32597.0,
-            "count": 16
+            "value": 31371.0,
+            "min": 15984.0,
+            "max": 33222.0,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 0.3765449644997716,
-            "min": -0.9999355356539449,
-            "max": 0.3765449644997716,
-            "count": 16
+            "value": 1.5844595529773133,
+            "min": -1.0000000521540642,
+            "max": 1.684756231494248,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 15.061798579990864,
-            "min": -30.998001605272293,
-            "max": 15.061798579990864,
-            "count": 16
+            "value": 148.93919797986746,
+            "min": -32.000001668930054,
+            "max": 161.7365982234478,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 0.3765449644997716,
-            "min": -0.9999355356539449,
-            "max": 0.3765449644997716,
-            "count": 16
+            "value": 1.5844595529773133,
+            "min": -1.0000000521540642,
+            "max": 1.684756231494248,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 15.061798579990864,
-            "min": -30.998001605272293,
-            "max": 15.061798579990864,
-            "count": 16
+            "value": 148.93919797986746,
+            "min": -32.000001668930054,
+            "max": 161.7365982234478,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.13490533595904708,
-            "min": 0.13490533595904708,
-            "max": 9.629465585781467,
-            "count": 16
+            "value": 0.030938343851185563,
+            "min": 0.0281731246329097,
+            "max": 5.722280306741595,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 5.396213438361883,
-            "min": 5.396213438361883,
-            "max": 173.33038054406643,
-            "count": 16
+            "value": 2.908204322011443,
+            "min": 2.704619964759331,
+            "max": 91.55648490786552,
+            "count": 33
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
+            "count": 33
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1658534113",
+        "start_time_seconds": "1659090163",
         "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": "1658535073"
+        "end_time_seconds": "1659092163"
     },
-    "total": 959.837579001,
+    "total": 1999.7478218160002,
     "count": 1,
-    "self": 0.4784033299998782,
+    "self": 0.48119585200038273,
     "children": {
         "run_training.setup": {
-            "total": 0.044108525000069676,
+            "total": 0.041433439999991606,
             "count": 1,
-            "self": 0.044108525000069676
+            "self": 0.041433439999991606
         },
         "TrainerController.start_learning": {
-            "total": 959.315067146,
+            "total": 1999.2251925239998,
             "count": 1,
-            "self": 0.6496283370137235,
+            "self": 1.2952241349653377,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 10.115987765,
+                    "total": 9.982592898999997,
                     "count": 1,
-                    "self": 10.115987765
+                    "self": 9.982592898999997
                 },
                 "TrainerController.advance": {
-                    "total": 948.4505773079862,
-                    "count": 31573,
-                    "self": 0.6665557859664659,
+                    "total": 1987.8559386770344,
+                    "count": 63958,
+                    "self": 1.3849396150685607,
                     "children": {
                         "env_step": {
-                            "total": 595.5843231390123,
-                            "count": 31573,
-                            "self": 543.600106348993,
+                            "total": 1292.910904829967,
+                            "count": 63958,
+                            "self": 1190.3789859030132,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 51.64141654901027,
-                                    "count": 31573,
-                                    "self": 2.2549263910054833,
+                                    "total": 101.8549709739774,
+                                    "count": 63958,
+                                    "self": 4.619035221993272,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 49.38649015800479,
-                                            "count": 31324,
-                                            "self": 17.122582015006515,
+                                            "total": 97.23593575198413,
+                                            "count": 62561,
+                                            "self": 33.399556241014466,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 32.263908142998275,
-                                                    "count": 31324,
-                                                    "self": 32.263908142998275
+                                                    "total": 63.836379510969664,
+                                                    "count": 62561,
+                                                    "self": 63.836379510969664
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.3428002410090585,
-                                    "count": 31573,
+                                    "total": 0.6769479529763203,
+                                    "count": 63958,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 957.2519895239935,
-                                            "count": 31573,
+                                            "total": 1995.360890769995,
+                                            "count": 63958,
                                             "is_parallel": true,
-                                            "self": 463.14957732999153,
+                                            "self": 901.4789255730395,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.007501446999981454,
+                                                            "total": 0.009251977999952032,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0038994669998828613,
+                                                            "self": 0.004771930999822871,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0036019800000985924,
+                                                                    "total": 0.0044800470001291615,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0036019800000985924
+                                                                    "self": 0.0044800470001291615
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.051372203000028094,
+                                                            "total": 0.05625449799993021,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0004975159999958123,
+                                                            "self": 0.0004985639999404157,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004392399999915142,
+                                                                    "total": 0.0004578549999223469,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004392399999915142
+                                                                    "self": 0.0004578549999223469
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04877651200001765,
+                                                                    "total": 0.04546531599999071,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04877651200001765
+                                                                    "self": 0.04546531599999071
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016589350000231207,
+                                                                    "total": 0.009832763000076739,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004377389998353465,
+                                                                    "self": 0.008097870000028706,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0012211960001877742,
+                                                                            "total": 0.0017348930000480323,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0012211960001877742
+                                                                            "self": 0.0017348930000480323
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 494.102412194002,
-                                                    "count": 31572,
+                                                    "total": 1093.8819651969554,
+                                                    "count": 63957,
                                                     "is_parallel": true,
-                                                    "self": 13.708569552023846,
+                                                    "self": 26.574679885016167,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 11.308705718979922,
-                                                            "count": 31572,
+                                                            "total": 22.38909954195435,
+                                                            "count": 63957,
                                                             "is_parallel": true,
-                                                            "self": 11.308705718979922
+                                                            "self": 22.38909954195435
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 422.9623061369907,
-                                                            "count": 31572,
+                                                            "total": 955.0587233659969,
+                                                            "count": 63957,
                                                             "is_parallel": true,
-                                                            "self": 422.9623061369907
+                                                            "self": 955.0587233659969
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 46.12283078600751,
-                                                            "count": 31572,
+                                                            "total": 89.85946240398789,
+                                                            "count": 63957,
                                                             "is_parallel": true,
-                                                            "self": 11.19316903005165,
+                                                            "self": 21.967423703942586,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 34.92966175595586,
-                                                                    "count": 252576,
+                                                                    "total": 67.8920387000453,
+                                                                    "count": 511656,
                                                                     "is_parallel": true,
-                                                                    "self": 34.92966175595586
+                                                                    "self": 67.8920387000453
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 352.19969838300744,
-                            "count": 31573,
-                            "self": 1.0786593059991674,
+                            "total": 693.5600942319987,
+                            "count": 63958,
+                            "self": 2.400740247999238,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 80.24381155500885,
-                                    "count": 31573,
-                                    "self": 80.13814475000879,
+                                    "total": 157.28593802299974,
+                                    "count": 63958,
+                                    "self": 157.08765719199982,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.10566680500005532,
-                                            "count": 1,
-                                            "self": 0.10566680500005532
+                                            "total": 0.19828083099992,
+                                            "count": 2,
+                                            "self": 0.19828083099992
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 270.87722752199943,
-                                    "count": 215,
-                                    "self": 105.82948779499452,
+                                    "total": 533.8734159609998,
+                                    "count": 448,
+                                    "self": 211.780137931009,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 165.0477397270049,
-                                            "count": 11418,
-                                            "self": 165.0477397270049
+                                            "total": 322.09327802999076,
+                                            "count": 22812,
+                                            "self": 322.09327802999076
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.3720000424655154e-06,
+                    "total": 1.294999947276665e-06,
                     "count": 1,
-                    "self": 1.3720000424655154e-06
+                    "self": 1.294999947276665e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0988723640000444,
+                    "total": 0.09143551800025307,
                     "count": 1,
-                    "self": 0.0016030980000323325,
+                    "self": 0.0015524960003858723,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09726926600001207,
+                            "total": 0.0898830219998672,
                             "count": 1,
-                            "self": 0.09726926600001207
+                            "self": 0.0898830219998672
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,31 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499967,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499967.onnx",
-                "reward": null,
-                "creation_time": 1658535072.7503042,
+                "steps": 499872,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499872.onnx",
+                "reward": 1.6604999676346779,
+                "creation_time": 1659091097.722221,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499967.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499872.pt"
                 ]
             },
             {
-                "steps": 500095,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-500095.onnx",
-                "reward": null,
-                "creation_time": 1658535072.9872127,
+                "steps": 999974,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999974.onnx",
+                "reward": 1.774599975347519,
+                "creation_time": 1659092162.4214103,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-500095.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999974.pt"
+                ]
+            },
+            {
+                "steps": 1000102,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000102.onnx",
+                "reward": 1.774599975347519,
+                "creation_time": 1659092162.5284414,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000102.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 500095,
+            "steps": 1000102,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1658535072.9872127,
+            "reward": 1.774599975347519,
+            "creation_time": 1659092162.5284414,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-500095.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000102.pt"
             ]
         }
     },