First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01cb5ca673c449f966de304bbc3a4674f8c8d0cba8e1564c1ba70e62e0f55a23
+size 1420238

Pyramids/Pyramids-1000075.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01cb5ca673c449f966de304bbc3a4674f8c8d0cba8e1564c1ba70e62e0f55a23
+size 1420238

Pyramids/Pyramids-1000075.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:587024bb73572057cb9634943979d8f8133dd35d099ec3e9cf92aa19de30d742
+size 8656252

Pyramids/Pyramids-499936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:460da8d8a29c001c85970b51014116a145ef4be6a8219f77f55690f20ce74484
+size 1420238

Pyramids/Pyramids-499936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:811e905e8856f854b24761c9f02219ea34187caaf0e299b9898166b66d360cf9
+size 8656173

Pyramids/Pyramids-999947.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01cb5ca673c449f966de304bbc3a4674f8c8d0cba8e1564c1ba70e62e0f55a23
+size 1420238

Pyramids/Pyramids-999947.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3409f18caa4f1d7fdaefeb60d5c33ac2a8d5aec555df1083c92f265600138662
+size 8656173

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96049ece15be274903b4d14a21eaa400b7ed6ae60592f1bd9c55029bcc64a44b
-size 2811810
+oid sha256:b1fc60a938745e84571bd0d267417b531b48478748f5cdb11e8002c24aba322c
+size 8655778

Pyramids/events.out.tfevents.1716730012.ad17dbadb9c1.11317.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:467037761417a85665303eae78ac562fc71998de2b2120968cb626ae75df3c8c
+size 396365

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 64, "buffer_size": 1024, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "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": 2, "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, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 25000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids2", "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, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "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, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 25000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids3", "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

@@ -3,8 +3,8 @@ behaviors:
   Pyramids:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 64
-      buffer_size: 1024
+      batch_size: 128
+      buffer_size: 2048
       learning_rate: 0.0003
       beta: 0.01
       epsilon: 0.2
@@ -17,7 +17,7 @@ behaviors:
     checkpoint_interval: 500000
     network_settings:
       normalize: false
-      hidden_units: 256
+      hidden_units: 512
       num_layers: 2
       vis_encode_type: simple
       memory: null
@@ -41,7 +41,7 @@ behaviors:
         network_settings:
           normalize: false
           hidden_units: 64
-          num_layers: 2
+          num_layers: 3
           vis_encode_type: simple
           memory: null
           goal_conditioning_type: hyper
@@ -79,7 +79,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids2
+  run_id: Pyramids3
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55503 [Flags] 2 [Guid] 3317623884 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55424 [Flags] 2 [Guid] 3703047348 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [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
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -68,7 +65,7 @@ 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: 0.926680 ms
+UnloadTime: 1.072183 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 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 7013 frames, [32.0 KB-64.0 KB]: 5450 frames, [64.0 KB-128.0 KB]: 1078 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2814 frames, [32.0 KB-64.0 KB]: 12429 frames, [64.0 KB-128.0 KB]: 3522 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -207,28 +204,28 @@ 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]: 13243 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18467 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.5 MB
+  Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 10921
+  Peak main deferred allocation count 12989
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.6 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 13541 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18765 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.9 MB
+      Peak Allocated memory 30.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 13542 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18766 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.3 MB
+      Peak Allocated memory 24.0 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.6 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 13541 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18765 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]: 13542 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18766 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.6 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 13243 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18467 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]: 13541 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18765 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 +288,27 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.6 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 13542 frames
+      Peak usage frame count: [0-1.0 KB]: 18766 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]: 13542 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18766 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]: 13542 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18766 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 27.4 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1716729795409,"processId":3928,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"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":3447},{"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":1716732293205,"processId":11356,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"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":3447},{"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

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.2877061665058136,
-            "min": 0.1402215212583542,
-            "max": 1.114737868309021,
-            "count": 28
+            "value": 0.39161038398742676,
+            "min": 0.3892679512500763,
+            "max": 1.4873254299163818,
+            "count": 40
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 7319.2451171875,
-            "min": 3475.250244140625,
-            "max": 29250.720703125,
-            "count": 28
+            "value": 9837.2529296875,
+            "min": 9660.0732421875,
+            "max": 39027.41796875,
+            "count": 40
         },
         "Pyramids.Step.mean": {
-            "value": 699940.0,
-            "min": 24984.0,
-            "max": 699940.0,
-            "count": 28
+            "value": 999947.0,
+            "min": 24960.0,
+            "max": 999947.0,
+            "count": 40
         },
         "Pyramids.Step.sum": {
-            "value": 699940.0,
-            "min": 24984.0,
-            "max": 699940.0,
-            "count": 28
+            "value": 999947.0,
+            "min": 24960.0,
+            "max": 999947.0,
+            "count": 40
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.08140786737203598,
-            "min": -0.09098301827907562,
-            "max": -0.0028870480600744486,
-            "count": 28
+            "value": 0.5577706098556519,
+            "min": -0.10050802677869797,
+            "max": 0.6519138216972351,
+            "count": 40
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -16.36298179626465,
-            "min": -18.287586212158203,
-            "max": -0.5889577865600586,
-            "count": 28
+            "value": 128.28724670410156,
+            "min": -20.302621841430664,
+            "max": 154.50357055664062,
+            "count": 40
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.17388638854026794,
-            "min": 0.09390256553888321,
-            "max": 1.580267071723938,
-            "count": 28
+            "value": 0.012868339195847511,
+            "min": 0.005618416238576174,
+            "max": 0.4353194832801819,
+            "count": 40
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 34.95116424560547,
-            "min": 18.780513763427734,
-            "max": 314.47314453125,
-            "count": 28
+            "value": 2.9597179889678955,
+            "min": 1.18548583984375,
+            "max": 86.1932601928711,
+            "count": 40
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.09654322728319026,
-            "min": 0.09273399738697696,
-            "max": 0.10286375738508972,
-            "count": 28
+            "value": 0.07048654987496168,
+            "min": 0.06373778805896614,
+            "max": 0.07526202773604179,
+            "count": 40
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 2.1239510002301856,
-            "min": 1.184038855566713,
-            "max": 2.263689750263494,
-            "count": 28
+            "value": 0.8458385984995402,
+            "min": 0.3981097612286458,
+            "max": 0.9031443328325015,
+            "count": 40
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0010831545318544537,
-            "min": 0.0003513862261868492,
-            "max": 0.03384953957981957,
-            "count": 28
+            "value": 0.015799540449532086,
+            "min": 0.0018626144759534152,
+            "max": 0.015799540449532086,
+            "count": 40
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.023829399700797983,
-            "min": 0.0077304969761106835,
-            "max": 0.40619447495783484,
-            "count": 28
+            "value": 0.18959448539438503,
+            "min": 0.013386984317590738,
+            "max": 0.18959448539438503,
+            "count": 40
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 9.384786871739999e-05,
-            "min": 9.384786871739999e-05,
-            "max": 0.0002960580263139916,
-            "count": 28
+            "value": 3.6753987749000005e-06,
+            "min": 3.6753987749000005e-06,
+            "max": 0.0002957568014144,
+            "count": 40
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0020646531117827997,
-            "min": 0.0020646531117827997,
-            "max": 0.0051968563677147,
-            "count": 28
+            "value": 4.4104785298800004e-05,
+            "min": 4.4104785298800004e-05,
+            "max": 0.0029269388243538,
+            "count": 40
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.13128260000000003,
-            "min": 0.13128260000000003,
-            "max": 0.19868600833333336,
-            "count": 28
+            "value": 0.1012251,
+            "min": 0.1012251,
+            "max": 0.1985856,
+            "count": 40
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 2.8882172000000006,
-            "min": 2.2646426,
-            "max": 3.9322852999999998,
-            "count": 28
+            "value": 1.2147012,
+            "min": 1.1771136000000002,
+            "max": 2.1756462,
+            "count": 40
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0031351317400000007,
-            "min": 0.0031351317400000007,
-            "max": 0.0098687322325,
-            "count": 28
+            "value": 0.00013238749,
+            "min": 0.00013238749,
+            "max": 0.00985870144,
+            "count": 40
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.06897289828000001,
-            "min": 0.06897289828000001,
-            "max": 0.17327530146999998,
-            "count": 28
+            "value": 0.00158864988,
+            "min": 0.00158864988,
+            "max": 0.09758705538,
+            "count": 40
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.1717197299003601,
-            "min": 0.08479351550340652,
-            "max": 1.796221137046814,
-            "count": 28
+            "value": 0.008755751885473728,
+            "min": 0.008497790433466434,
+            "max": 0.5597033500671387,
+            "count": 40
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 3.777834177017212,
-            "min": 1.8654574155807495,
-            "max": 21.55465316772461,
-            "count": 28
+            "value": 0.10506902635097504,
+            "min": 0.09569065272808075,
+            "max": 3.358220100402832,
+            "count": 40
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 957.4230769230769,
-            "min": 863.8,
-            "max": 989.9166666666666,
-            "count": 28
+            "value": 328.0133333333333,
+            "min": 296.6024096385542,
+            "max": 999.0,
+            "count": 40
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 24893.0,
-            "min": 16519.0,
-            "max": 30028.0,
-            "count": 28
+            "value": 24601.0,
+            "min": 15984.0,
+            "max": 31968.0,
+            "count": 40
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.8042154355117908,
-            "min": -0.9072500516970953,
-            "max": -0.28687337959806125,
-            "count": 28
+            "value": 1.5919653083880743,
+            "min": -1.0000000521540642,
+            "max": 1.6551903460219681,
+            "count": 40
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -20.90960132330656,
-            "min": -24.108001351356506,
-            "max": -8.606201387941837,
-            "count": 28
+            "value": 119.39739812910557,
+            "min": -32.000001668930054,
+            "max": 137.38079871982336,
+            "count": 40
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.8042154355117908,
-            "min": -0.9072500516970953,
-            "max": -0.28687337959806125,
-            "count": 28
+            "value": 1.5919653083880743,
+            "min": -1.0000000521540642,
+            "max": 1.6551903460219681,
+            "count": 40
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -20.90960132330656,
-            "min": -24.108001351356506,
-            "max": -8.606201387941837,
-            "count": 28
+            "value": 119.39739812910557,
+            "min": -32.000001668930054,
+            "max": 137.38079871982336,
+            "count": 40
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 1.6807586969091342,
-            "min": 0.7546649801411799,
-            "max": 27.484460483579074,
-            "count": 28
+            "value": 0.029587139872989308,
+            "min": 0.027370002108606666,
+            "max": 10.958400049246848,
+            "count": 40
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 43.69972611963749,
-            "min": 21.130619443953037,
-            "max": 467.23582822084427,
-            "count": 28
+            "value": 2.219035490474198,
+            "min": 2.0833714419277385,
+            "max": 175.33440078794956,
+            "count": 40
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 28
+            "count": 40
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 28
+            "count": 40
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1716728213",
+        "start_time_seconds": "1716730011",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids2 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids3 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1716729795"
+        "end_time_seconds": "1716732293"
     },
-    "total": 1581.5100792830003,
+    "total": 2281.9890105399995,
     "count": 1,
-    "self": 0.4965109770005256,
+    "self": 0.48976659899926744,
     "children": {
         "run_training.setup": {
-            "total": 0.057788167000012436,
+            "total": 0.05181883299974288,
             "count": 1,
-            "self": 0.057788167000012436
+            "self": 0.05181883299974288
         },
         "TrainerController.start_learning": {
-            "total": 1580.955780139,
+            "total": 2281.4474251080005,
             "count": 1,
-            "self": 0.9749380329992618,
+            "self": 1.397449222970863,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.1688041089998933,
+                    "total": 2.4167706079997515,
                     "count": 1,
-                    "self": 3.1688041089998933
+                    "self": 2.4167706079997515
                 },
                 "TrainerController.advance": {
-                    "total": 1576.8120366170008,
-                    "count": 45598,
-                    "self": 0.9657081809909869,
+                    "total": 2277.54545750003,
+                    "count": 63983,
+                    "self": 1.414589613111275,
                     "children": {
                         "env_step": {
-                            "total": 940.3703066370166,
-                            "count": 45598,
-                            "self": 846.9019296710388,
+                            "total": 1637.3200555290337,
+                            "count": 63983,
+                            "self": 1504.1230797850653,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 92.90949026297847,
-                                    "count": 45598,
-                                    "self": 3.2695961059821457,
+                                    "total": 132.3463596849656,
+                                    "count": 63983,
+                                    "self": 4.706007048048832,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 89.63989415699632,
-                                            "count": 45139,
-                                            "self": 89.63989415699632
+                                            "total": 127.64035263691676,
+                                            "count": 62552,
+                                            "self": 127.64035263691676
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.5588867029993025,
-                                    "count": 45598,
+                                    "total": 0.8506160590027321,
+                                    "count": 63983,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1576.9947408299886,
-                                            "count": 45598,
+                                            "total": 2276.1567987270205,
+                                            "count": 63983,
                                             "is_parallel": true,
-                                            "self": 815.6175068249756,
+                                            "self": 895.521353034901,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005266228999971645,
+                                                            "total": 0.0020543230002658674,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003854729999943629,
+                                                            "self": 0.0005948570001237385,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014114990000280159,
+                                                                    "total": 0.001459466000142129,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014114990000280159
+                                                                    "self": 0.001459466000142129
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.048231131000079586,
+                                                            "total": 0.04804656100031934,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006732860000511209,
+                                                            "self": 0.0006337940008052101,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004798480000545169,
+                                                                    "total": 0.0005115260000820854,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004798480000545169
+                                                                    "self": 0.0005115260000820854
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04546109900002193,
+                                                                    "total": 0.0452873549998003,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04546109900002193
+                                                                    "self": 0.0452873549998003
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001616897999952016,
+                                                                    "total": 0.0016138859996317478,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003409130000591176,
+                                                                    "self": 0.0003391109994481667,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0012759849998928985,
+                                                                            "total": 0.0012747750001835811,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0012759849998928985
+                                                                            "self": 0.0012747750001835811
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 761.377234005013,
-                                                    "count": 45597,
+                                                    "total": 1380.6354456921194,
+                                                    "count": 63982,
                                                     "is_parallel": true,
-                                                    "self": 24.04186556498371,
+                                                    "self": 34.525767212177016,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 16.667416598989803,
-                                                            "count": 45597,
+                                                            "total": 23.840742276008314,
+                                                            "count": 63982,
                                                             "is_parallel": true,
-                                                            "self": 16.667416598989803
+                                                            "self": 23.840742276008314
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 651.8973624300207,
-                                                            "count": 45597,
+                                                            "total": 1223.704609926931,
+                                                            "count": 63982,
                                                             "is_parallel": true,
-                                                            "self": 651.8973624300207
+                                                            "self": 1223.704609926931
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 68.7705894110187,
-                                                            "count": 45597,
+                                                            "total": 98.56432627700315,
+                                                            "count": 63982,
                                                             "is_parallel": true,
-                                                            "self": 13.553141017025837,
+                                                            "self": 20.079214052069347,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 55.21744839399287,
-                                                                    "count": 364776,
+                                                                    "total": 78.4851122249338,
+                                                                    "count": 511856,
                                                                     "is_parallel": true,
-                                                                    "self": 55.21744839399287
+                                                                    "self": 78.4851122249338
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 635.4760217989932,
-                            "count": 45598,
-                            "self": 1.8462093260284291,
+                            "total": 638.810812357885,
+                            "count": 63983,
+                            "self": 2.6279607609471896,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 87.12409853696431,
-                                    "count": 45598,
-                                    "self": 86.95403889796421,
+                                    "total": 129.42429262893575,
+                                    "count": 63983,
+                                    "self": 129.22864745593552,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.17005963900010101,
-                                            "count": 1,
-                                            "self": 0.17005963900010101
+                                            "total": 0.19564517300023,
+                                            "count": 2,
+                                            "self": 0.19564517300023
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 546.5057139360005,
-                                    "count": 576,
-                                    "self": 259.07786362501736,
+                                    "total": 506.75855896800203,
+                                    "count": 454,
+                                    "self": 297.20957183900373,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 287.4278503109831,
-                                            "count": 33132,
-                                            "self": 287.4278503109831
+                                            "total": 209.5489871289983,
+                                            "count": 22839,
+                                            "self": 209.5489871289983
                                         }
                                     }
                                 }
@@ -376,9 +376,21 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.3799999578623101e-06,
+                    "total": 8.770002750679851e-07,
                     "count": 1,
-                    "self": 1.3799999578623101e-06
+                    "self": 8.770002750679851e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.08774689999972907,
+                    "count": 1,
+                    "self": 0.0014895069998601684,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.0862573929998689,
+                            "count": 1,
+                            "self": 0.0862573929998689
+                        }
+                    }
                 }
             }
         }

run_logs/training_status.json

@@ -2,15 +2,42 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499895,
-                "file_path": "results/Pyramids2/Pyramids/Pyramids-499895.onnx",
-                "reward": -0.9992000460624695,
-                "creation_time": 1716729300.8713949,
+                "steps": 499936,
+                "file_path": "results/Pyramids3/Pyramids/Pyramids-499936.onnx",
+                "reward": 1.8350000530481339,
+                "creation_time": 1716731065.9763486,
                 "auxillary_file_paths": [
-                    "results/Pyramids2/Pyramids/Pyramids-499895.pt"
+                    "results/Pyramids3/Pyramids/Pyramids-499936.pt"
+                ]
+            },
+            {
+                "steps": 999947,
+                "file_path": "results/Pyramids3/Pyramids/Pyramids-999947.onnx",
+                "reward": null,
+                "creation_time": 1716732292.6647134,
+                "auxillary_file_paths": [
+                    "results/Pyramids3/Pyramids/Pyramids-999947.pt"
+                ]
+            },
+            {
+                "steps": 1000075,
+                "file_path": "results/Pyramids3/Pyramids/Pyramids-1000075.onnx",
+                "reward": null,
+                "creation_time": 1716732292.7633982,
+                "auxillary_file_paths": [
+                    "results/Pyramids3/Pyramids/Pyramids-1000075.pt"
                 ]
             }
-        ]
+        ],
+        "final_checkpoint": {
+            "steps": 1000075,
+            "file_path": "results/Pyramids3/Pyramids.onnx",
+            "reward": null,
+            "creation_time": 1716732292.7633982,
+            "auxillary_file_paths": [
+                "results/Pyramids3/Pyramids/Pyramids-1000075.pt"
+            ]
+        }
     },
     "metadata": {
         "stats_format_version": "0.3.0",