First Pyramids

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf05f7c4357065abaf77fe768eb793c40208cf3214832de1f240ed7687df6b7
+oid sha256:63ab8604365ffe917726021830c64dad7034e575d7a18417e747768311dbacfc
 size 1417437

Pyramids/{Pyramids-499996.onnx → Pyramids-1000191.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf05f7c4357065abaf77fe768eb793c40208cf3214832de1f240ed7687df6b7
+oid sha256:63ab8604365ffe917726021830c64dad7034e575d7a18417e747768311dbacfc
 size 1417437

Pyramids/{Pyramids-499996.pt → Pyramids-1000191.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:725587a0babfa4e7fdf0a7c28bde298ab675dfdc587305158dd43e7357175837
+oid sha256:cbc01dd36e53867e02067adbb6f2a820480db078f7f8a63c9d459d04ab07cfb8
 size 8652382

Pyramids/{Pyramids-500124.onnx → Pyramids-499971.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf05f7c4357065abaf77fe768eb793c40208cf3214832de1f240ed7687df6b7
+oid sha256:1b60b550d6192d7582c6f5d95ff2d5e3d788b4eaaaa910af5459ae8db7d14724
 size 1417437

Pyramids/{Pyramids-500124.pt → Pyramids-499971.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:480dd48637434f094074750eccff8f212930ddb1bd8a92291100e3b16be0ba81
+oid sha256:12a5762fb19bcc1d66b9d94a65537ff8d2f361cc617412916e52a23490d190ff
 size 8652382

Pyramids/Pyramids-999935.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ab8604365ffe917726021830c64dad7034e575d7a18417e747768311dbacfc
+size 1417437

Pyramids/Pyramids-999935.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a520c6ade052ada8b6625d4211951f8ad1d1c1e92abd63be5202811ee43c9cd
+size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:480dd48637434f094074750eccff8f212930ddb1bd8a92291100e3b16be0ba81
+oid sha256:cbc01dd36e53867e02067adbb6f2a820480db078f7f8a63c9d459d04ab07cfb8
 size 8652382

Pyramids/{events.out.tfevents.1659530119.96b0650db64c.286.0 → events.out.tfevents.1659592077.9226e9a318a5.434.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e7d6f4be9a2765261776d618459ed4b7257decd4968e52f686cf7db82d85d6
-size 138366
+oid sha256:da1c8ed821480b8ba01ef888545ec10c4023ca84bf35b0bcb4a20ada720d1e56
+size 323501

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] 55324 [Flags] 2 [Guid] 215435024 [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] 55297 [Flags] 2 [Guid] 3208015492 [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  0.089 seconds
+- Completed reload, in  0.081 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: 0.758757 ms
+UnloadTime: 0.974869 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]: 3124 frames, [32.0 KB-64.0 KB]: 5465 frames, [64.0 KB-128.0 KB]: 806 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 4237 frames, [32.0 KB-64.0 KB]: 11733 frames, [64.0 KB-128.0 KB]: 2796 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 15]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -207,28 +207,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 9097 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18468 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 12983
+  Peak main deferred allocation count 12989
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 9395 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18766 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.4 MB
+      Peak Allocated memory 30.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9396 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18767 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.1 MB
+      Peak Allocated memory 22.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +257,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 9395 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18766 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]: 9396 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18767 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,13 +275,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 9097 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18468 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]: 9395 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18766 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
@@ -293,25 +293,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9396 frames
+      Peak usage frame count: [0-1.0 KB]: 18767 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]: 9396 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18767 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]: 9396 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18767 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 27.4 KB
+  Peak Allocated memory 29.2 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1659531123205,"processId":297,"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":1659594078436,"processId":445,"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": 0.6424892544746399,
-            "min": 0.6424892544746399,
-            "max": 1.4669122695922852,
-            "count": 16
+            "value": 0.3959227204322815,
+            "min": 0.3956947326660156,
+            "max": 1.3033586740493774,
+            "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 19233.55859375,
-            "min": 19233.55859375,
-            "max": 44500.25,
-            "count": 16
+            "value": 11896.685546875,
+            "min": 11845.517578125,
+            "max": 39538.6875,
+            "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 479921.0,
-            "min": 29952.0,
-            "max": 479921.0,
-            "count": 16
+            "value": 989981.0,
+            "min": 29962.0,
+            "max": 989981.0,
+            "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 479921.0,
-            "min": 29952.0,
-            "max": 479921.0,
-            "count": 16
+            "value": 989981.0,
+            "min": 29962.0,
+            "max": 989981.0,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.10952070355415344,
-            "min": -0.11337810009717941,
-            "max": 0.17591866850852966,
-            "count": 16
+            "value": 0.6083003282546997,
+            "min": -0.09428735822439194,
+            "max": 0.6083003282546997,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 27.380176544189453,
-            "min": -27.324121475219727,
-            "max": 43.627830505371094,
-            "count": 16
+            "value": 172.14898681640625,
+            "min": -22.628965377807617,
+            "max": 172.14898681640625,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.030589576810598373,
-            "min": 0.03009730763733387,
-            "max": 0.2966145873069763,
-            "count": 16
+            "value": 0.03633543476462364,
+            "min": -0.006452896632254124,
+            "max": 0.39466044306755066,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 7.647394180297852,
-            "min": 7.494229793548584,
-            "max": 71.48411560058594,
-            "count": 16
+            "value": 10.282927513122559,
+            "min": -1.6067712306976318,
+            "max": 93.92918395996094,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06665724948106798,
-            "min": 0.06665724948106798,
-            "max": 0.07536791683661549,
-            "count": 16
+            "value": 0.07021421850437211,
+            "min": 0.06626262217501386,
+            "max": 0.07306854674248149,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9332014927349518,
-            "min": 0.5275754178563085,
-            "max": 1.0514537015468723,
-            "count": 16
+            "value": 0.9829990590612095,
+            "min": 0.5114798271973704,
+            "max": 1.0276094241028961,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.010487714579843061,
-            "min": 0.00019159560872533104,
-            "max": 0.010487714579843061,
-            "count": 16
+            "value": 0.015208654033250196,
+            "min": 0.00016666482889740735,
+            "max": 0.016403746657159584,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.14682800411780286,
-            "min": 0.0017243604785279795,
-            "max": 0.14682800411780286,
-            "count": 16
+            "value": 0.21292115646550275,
+            "min": 0.002333307604563703,
+            "max": 0.2296524532002342,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.09343930219e-05,
-            "min": 2.09343930219e-05,
-            "max": 0.00029030126037577137,
-            "count": 16
+            "value": 7.2693975769e-06,
+            "min": 7.2693975769e-06,
+            "max": 0.00029523797301591427,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0002930815023066,
-            "min": 0.0002930815023066,
-            "max": 0.0025672583442474,
-            "count": 16
+            "value": 0.00010177156607660001,
+            "min": 0.00010177156607660001,
+            "max": 0.0037583095472302,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10697809999999999,
-            "min": 0.10697809999999999,
-            "max": 0.19676708571428575,
-            "count": 16
+            "value": 0.1024231,
+            "min": 0.1024231,
+            "max": 0.19841265714285714,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4976934,
-            "min": 1.3773696000000002,
-            "max": 2.2557526000000006,
-            "count": 16
+            "value": 1.4339234,
+            "min": 1.3888886,
+            "max": 2.6527698000000006,
+            "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00070711219,
-            "min": 0.00070711219,
-            "max": 0.00967703186285714,
-            "count": 16
+            "value": 0.0002520676900000001,
+            "min": 0.0002520676900000001,
+            "max": 0.009841424448571428,
+            "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.009899570659999999,
-            "min": 0.009899570659999999,
-            "max": 0.08562968474,
-            "count": 16
+            "value": 0.003528947660000001,
+            "min": 0.003528947660000001,
+            "max": 0.12529170302,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.026312928646802902,
-            "min": 0.026312928646802902,
-            "max": 0.4624808430671692,
-            "count": 16
+            "value": 0.01084090955555439,
+            "min": 0.01084090955555439,
+            "max": 0.4875030815601349,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.36838099360466003,
-            "min": 0.36838099360466003,
-            "max": 3.237365961074829,
-            "count": 16
+            "value": 0.15177273750305176,
+            "min": 0.15177273750305176,
+            "max": 3.4125216007232666,
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 724.5777777777778,
-            "min": 724.5777777777778,
+            "value": 312.35051546391753,
+            "min": 312.35051546391753,
             "max": 999.0,
-            "count": 16
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 32606.0,
-            "min": 15984.0,
-            "max": 32606.0,
-            "count": 16
+            "value": 30298.0,
+            "min": 16505.0,
+            "max": 33363.0,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 0.47519107427861956,
-            "min": -1.0000000521540642,
-            "max": 0.6358157517878633,
-            "count": 16
+            "value": 1.646395854651928,
+            "min": -0.9999000519514084,
+            "max": 1.646395854651928,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 21.38359834253788,
-            "min": -31.99920167028904,
-            "max": 24.160998567938805,
-            "count": 16
+            "value": 159.700397901237,
+            "min": -31.990801632404327,
+            "max": 159.700397901237,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 0.47519107427861956,
-            "min": -1.0000000521540642,
-            "max": 0.6358157517878633,
-            "count": 16
+            "value": 1.646395854651928,
+            "min": -0.9999000519514084,
+            "max": 1.646395854651928,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 21.38359834253788,
-            "min": -31.99920167028904,
-            "max": 24.160998567938805,
-            "count": 16
+            "value": 159.700397901237,
+            "min": -31.990801632404327,
+            "max": 159.700397901237,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.1987997126325758,
-            "min": 0.1987997126325758,
-            "max": 9.305791547521949,
-            "count": 16
+            "value": 0.03513942491734213,
+            "min": 0.03513942491734213,
+            "max": 9.231398548711748,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 8.94598706846591,
-            "min": 7.678771013743244,
-            "max": 148.89266476035118,
-            "count": 16
+            "value": 3.4085242169821868,
+            "min": 3.4085242169821868,
+            "max": 156.93377532809973,
+            "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": "1659530113",
+        "start_time_seconds": "1659592070",
         "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": "1659531123"
+        "end_time_seconds": "1659594078"
     },
-    "total": 1010.0291081169999,
+    "total": 2007.5318096520002,
     "count": 1,
-    "self": 0.47682036699984565,
+    "self": 0.48957221800037587,
     "children": {
         "run_training.setup": {
-            "total": 0.043104706000008264,
+            "total": 0.0421327219999057,
             "count": 1,
-            "self": 0.043104706000008264
+            "self": 0.0421327219999057
         },
         "TrainerController.start_learning": {
-            "total": 1009.509183044,
+            "total": 2007.000104712,
             "count": 1,
-            "self": 0.8239632060057147,
+            "self": 1.4993759690148636,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 9.664915161999943,
+                    "total": 10.0311922530002,
                     "count": 1,
-                    "self": 9.664915161999943
+                    "self": 10.0311922530002
                 },
                 "TrainerController.advance": {
-                    "total": 998.9219368069946,
-                    "count": 31627,
-                    "self": 0.8772083609968604,
+                    "total": 1995.374332324985,
+                    "count": 63781,
+                    "self": 1.567754683008161,
                     "children": {
                         "env_step": {
-                            "total": 643.551915622001,
-                            "count": 31627,
-                            "self": 584.7234124049968,
+                            "total": 1288.257647457958,
+                            "count": 63781,
+                            "self": 1177.8270495018912,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 58.40473673298766,
-                                    "count": 31627,
-                                    "self": 2.551366940016237,
+                                    "total": 109.66772927997977,
+                                    "count": 63781,
+                                    "self": 4.620089453012497,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 55.85336979297142,
-                                            "count": 31318,
-                                            "self": 18.501444193954853,
+                                            "total": 105.04763982696727,
+                                            "count": 62555,
+                                            "self": 35.11235773191311,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 37.35192559901657,
-                                                    "count": 31318,
-                                                    "self": 37.35192559901657
+                                                    "total": 69.93528209505416,
+                                                    "count": 62555,
+                                                    "self": 69.93528209505416
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.4237664840165962,
-                                    "count": 31627,
+                                    "total": 0.7628686760870096,
+                                    "count": 63781,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1007.2384630349961,
-                                            "count": 31627,
+                                            "total": 2002.8385946890774,
+                                            "count": 63781,
                                             "is_parallel": true,
-                                            "self": 476.7345370150002,
+                                            "self": 928.9100540310365,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.008617938000043068,
+                                                            "total": 0.0048538969999754045,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.004054311999993843,
+                                                            "self": 0.003629778000231454,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.004563626000049226,
+                                                                    "total": 0.0012241189997439506,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.004563626000049226
+                                                                    "self": 0.0012241189997439506
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04992056700007197,
+                                                            "total": 0.05409481299989238,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006310890000804648,
+                                                            "self": 0.0006059029997231846,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004778899999564601,
+                                                                    "total": 0.00045909900018159533,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004778899999564601
+                                                                    "self": 0.00045909900018159533
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.046993884000016806,
+                                                                    "total": 0.05142970699989746,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.046993884000016806
+                                                                    "self": 0.05142970699989746
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018177040000182387,
+                                                                    "total": 0.0016001040000901412,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004541820001122687,
+                                                                    "self": 0.00044480900032795034,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.00136352199990597,
+                                                                            "total": 0.0011552949997621909,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.00136352199990597
+                                                                            "self": 0.0011552949997621909
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 530.5039260199959,
-                                                    "count": 31626,
+                                                    "total": 1073.928540658041,
+                                                    "count": 63780,
                                                     "is_parallel": true,
-                                                    "self": 14.404039232020295,
+                                                    "self": 28.259136330020738,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 11.919230893969939,
-                                                            "count": 31626,
+                                                            "total": 23.05626712801154,
+                                                            "count": 63780,
                                                             "is_parallel": true,
-                                                            "self": 11.919230893969939
+                                                            "self": 23.05626712801154
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 456.7268685080145,
-                                                            "count": 31626,
+                                                            "total": 930.6556645219666,
+                                                            "count": 63780,
                                                             "is_parallel": true,
-                                                            "self": 456.7268685080145
+                                                            "self": 930.6556645219666
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 47.45378738599118,
-                                                            "count": 31626,
+                                                            "total": 91.957472678042,
+                                                            "count": 63780,
                                                             "is_parallel": true,
-                                                            "self": 12.229282883994983,
+                                                            "self": 23.131462866221455,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 35.22450450199619,
-                                                                    "count": 253008,
+                                                                    "total": 68.82600981182054,
+                                                                    "count": 510240,
                                                                     "is_parallel": true,
-                                                                    "self": 35.22450450199619
+                                                                    "self": 68.82600981182054
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 354.4928128239967,
-                            "count": 31627,
-                            "self": 1.4526024430047073,
+                            "total": 705.5489301840189,
+                            "count": 63781,
+                            "self": 2.7469812010599526,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 80.3340138409909,
-                                    "count": 31627,
-                                    "self": 80.22803446499086,
+                                    "total": 159.51870520796047,
+                                    "count": 63781,
+                                    "self": 159.3186803999606,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.10597937600005025,
-                                            "count": 1,
-                                            "self": 0.10597937600005025
+                                            "total": 0.20002480799985278,
+                                            "count": 2,
+                                            "self": 0.20002480799985278
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 272.7061965400011,
-                                    "count": 206,
-                                    "self": 105.87156306000634,
+                                    "total": 543.2832437749985,
+                                    "count": 455,
+                                    "self": 213.72379247898812,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 166.83463347999475,
-                                            "count": 11427,
-                                            "self": 166.83463347999475
+                                            "total": 329.55945129601037,
+                                            "count": 22806,
+                                            "self": 329.55945129601037
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.1499998890940333e-06,
+                    "total": 1.3769999895885121e-06,
                     "count": 1,
-                    "self": 1.1499998890940333e-06
+                    "self": 1.3769999895885121e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0983667189998414,
+                    "total": 0.09520278799982407,
                     "count": 1,
-                    "self": 0.001680786999713746,
+                    "self": 0.0015716439997959242,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09668593200012765,
+                            "total": 0.09363114400002814,
                             "count": 1,
-                            "self": 0.09668593200012765
+                            "self": 0.09363114400002814
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,31 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499996,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499996.onnx",
-                "reward": 0.914999949435393,
-                "creation_time": 1659531122.6672769,
+                "steps": 499971,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499971.onnx",
+                "reward": null,
+                "creation_time": 1659593010.0412805,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499996.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499971.pt"
                 ]
             },
             {
-                "steps": 500124,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-500124.onnx",
-                "reward": 0.914999949435393,
-                "creation_time": 1659531122.7879,
+                "steps": 999935,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999935.onnx",
+                "reward": null,
+                "creation_time": 1659594077.8690488,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-500124.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999935.pt"
+                ]
+            },
+            {
+                "steps": 1000191,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000191.onnx",
+                "reward": null,
+                "creation_time": 1659594077.9989939,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000191.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 500124,
+            "steps": 1000191,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 0.914999949435393,
-            "creation_time": 1659531122.7879,
+            "reward": null,
+            "creation_time": 1659594077.9989939,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-500124.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000191.pt"
             ]
         }
     },