second push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd886f33298552e9e969e262c0bd6d6ef8983ab35df404580baa5442b9119943
-size 1420238
+oid sha256:f86c3767cc400d8118d034c5402bad70a9729caf9ee2a2f3aa2eb60e98b861d8
+size 2476652

Pyramids/Pyramids-1000123.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86c3767cc400d8118d034c5402bad70a9729caf9ee2a2f3aa2eb60e98b861d8
+size 2476652

Pyramids/Pyramids-1000123.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b2bd113152f30ba350876593add8a00e0ecb6c65ef35ae8aeea6313011c5be
+size 14980859

Pyramids/Pyramids-499981.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0bc0e8c01efeef01a6a0fcdfff8a59be674190c79cef65ab9cb22a09dee2cdd
+size 2476652

Pyramids/Pyramids-499981.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:badd7f83bca7dacea23521410368e33b532626d0b4132dffb286be26007f7d21
+size 14980740

Pyramids/Pyramids-999995.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f009e4a71af2ccdedd4f2fa9aeaa9fd64fcd5ea9c1f91a0a0d46f7260038988f
+size 2476652

Pyramids/Pyramids-999995.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b580bb4d2fdd73b89316a76a79ba730cbfc43468be2f40402649ca933b184222
+size 14980740

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef866ac36a67615b9c61d1e77a69bcc4bc0801cce7cb278ce56f12282824503e
-size 8655778
+oid sha256:a01484c821f9a851b1eb661e51bec7f96cff2b5d84936125014f171cbbd5c4bf
+size 14980145

Pyramids/events.out.tfevents.1736906554.19aa2fa544cb.39002.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f29d1bf10fa5afd0e829d75cbbb3214eb80e76de330f9d5127cfc12bacd635
+size 333538

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, "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": 30000, "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": "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": 256, "buffer_size": 4096, "learning_rate": 0.0002, "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": true, "hidden_units": 512, "num_layers": 3, "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": 30000, "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": "Pyramids Training v2", "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

@@ -3,9 +3,9 @@ behaviors:
   Pyramids:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 128
-      buffer_size: 2048
-      learning_rate: 0.0003
+      batch_size: 256
+      buffer_size: 4096
+      learning_rate: 0.0002
       beta: 0.01
       epsilon: 0.2
       lambd: 0.95
@@ -16,9 +16,9 @@ behaviors:
       epsilon_schedule: linear
     checkpoint_interval: 500000
     network_settings:
-      normalize: false
+      normalize: true
       hidden_units: 512
-      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: Pyramids Training
+  run_id: Pyramids Training v2
   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) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55502 [Flags] 2 [Guid] 929253325 [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] 55412 [Flags] 2 [Guid] 3649472815 [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
-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
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2664:(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  0.091 seconds
+- Completed reload, in  0.090 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 +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: 0.826042 ms
+UnloadTime: 0.789946 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 4 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]: 7075 frames, [32.0 KB-64.0 KB]: 9445 frames, [64.0 KB-128.0 KB]: 2246 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 6023 frames, [32.0 KB-64.0 KB]: 8466 frames, [64.0 KB-128.0 KB]: 4281 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
@@ -94,7 +91,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 4]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 6]
       Initial Block Size 32.0 KB
@@ -189,7 +186,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 2]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
@@ -237,28 +234,28 @@ 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]: 18468 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 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 12853
+  Peak main deferred allocation count 12212
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       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]: 18766 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18770 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 29.9 MB
+      Peak Allocated memory 30.5 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18767 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 26.5 MB
+      Peak Allocated memory 25.9 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -287,13 +284,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18766 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18770 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]: 18767 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -305,13 +302,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       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]: 18468 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 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]: 18766 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18770 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
@@ -323,19 +320,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18767 frames
+      Peak usage frame count: [0-1.0 KB]: 18771 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]: 18767 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18771 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]: 18767 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18771 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 31.4 KB
@@ -344,4 +341,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1736904890930,"processId":25582,"allocatedMemory":1976109,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34628},{"Manager":13963},{"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":3808},{"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":1736908191587,"processId":39066,"allocatedMemory":1976109,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34628},{"Manager":13963},{"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":3808},{"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

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.43187403678894043,
-            "min": 0.43187403678894043,
-            "max": 1.391715168952942,
+            "value": 0.23151110112667084,
+            "min": 0.2050740122795105,
+            "max": 1.5532217025756836,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 12907.8515625,
-            "min": 12907.8515625,
-            "max": 42219.0703125,
+            "value": 6949.037109375,
+            "min": 6132.533203125,
+            "max": 47118.53515625,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989903.0,
+            "value": 989920.0,
             "min": 29952.0,
-            "max": 989903.0,
+            "max": 989920.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989903.0,
+            "value": 989920.0,
             "min": 29952.0,
-            "max": 989903.0,
+            "max": 989920.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.30247893929481506,
-            "min": -0.08212973922491074,
-            "max": 0.35921433568000793,
+            "value": 0.7582598924636841,
+            "min": -0.06903452426195145,
+            "max": 0.7582598924636841,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 78.94700622558594,
-            "min": -19.875396728515625,
-            "max": 94.47337341308594,
+            "value": 223.68667602539062,
+            "min": -16.775388717651367,
+            "max": 223.68667602539062,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.009340688586235046,
-            "min": -0.04220491275191307,
-            "max": 0.2274199277162552,
+            "value": -0.012867028824985027,
+            "min": -0.019352532923221588,
+            "max": 0.34787997603416443,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 2.4379196166992188,
-            "min": -10.67784309387207,
-            "max": 54.58078384399414,
+            "value": -3.795773506164551,
+            "min": -5.631587028503418,
+            "max": 83.83907318115234,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06729751450932651,
-            "min": 0.06561639717700488,
-            "max": 0.074308342815909,
+            "value": 0.04638090478034602,
+            "min": 0.04580706963038427,
+            "max": 0.054533920542900266,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9421652031305712,
-            "min": 0.4898390478846596,
-            "max": 1.0755080279389708,
+            "value": 0.32466633346242213,
+            "min": 0.21813568217160106,
+            "max": 0.40144404525441735,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.012101668819793432,
-            "min": 0.00015621855073405665,
-            "max": 0.012749765474013875,
+            "value": 0.016195195291878742,
+            "min": 0.0005721494158679969,
+            "max": 0.01691421440530879,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.16942336347710804,
-            "min": 0.0020308411595427365,
-            "max": 0.17849671663619424,
+            "value": 0.1133663670431512,
+            "min": 0.004005045911075978,
+            "max": 0.13531371524247032,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.4878403612285675e-06,
-            "min": 7.4878403612285675e-06,
-            "max": 0.00029515063018788575,
+            "value": 4.68944051247143e-06,
+            "min": 4.68944051247143e-06,
+            "max": 0.00019696640151679998,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010482976505719995,
-            "min": 0.00010482976505719995,
-            "max": 0.0036333499888833998,
+            "value": 3.2826083587300005e-05,
+            "min": 3.2826083587300005e-05,
+            "max": 0.0012954962522519,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10249591428571428,
-            "min": 0.10249591428571428,
-            "max": 0.19838354285714285,
+            "value": 0.10234467142857144,
+            "min": 0.10234467142857144,
+            "max": 0.1984832,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4349428,
-            "min": 1.3691136000000002,
-            "max": 2.611116600000001,
+            "value": 0.7164127000000001,
+            "min": 0.7164127000000001,
+            "max": 1.4199037,
             "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002593418371428571,
-            "min": 0.0002593418371428571,
-            "max": 0.00983851593142857,
+            "value": 0.0002442326757142858,
+            "min": 0.0002442326757142858,
+            "max": 0.00984847168,
             "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0036307857199999994,
-            "min": 0.0036307857199999994,
-            "max": 0.12113054834000002,
+            "value": 0.0017096287300000005,
+            "min": 0.0017096287300000005,
+            "max": 0.06478003519,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.008994733914732933,
-            "min": 0.008994733914732933,
-            "max": 0.4135468304157257,
+            "value": 0.017597027122974396,
+            "min": 0.01752258650958538,
+            "max": 0.4774644672870636,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.12592627108097076,
-            "min": 0.12592627108097076,
-            "max": 2.8948278427124023,
+            "value": 0.12317918986082077,
+            "min": 0.12317918986082077,
+            "max": 1.9098578691482544,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 531.3898305084746,
-            "min": 478.0806451612903,
+            "value": 238.57142857142858,
+            "min": 238.57142857142858,
             "max": 999.0,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31352.0,
+            "value": 28390.0,
             "min": 15984.0,
-            "max": 32261.0,
+            "max": 33440.0,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.1295152211845931,
+            "value": 1.7278016608427553,
             "min": -1.0000000521540642,
-            "max": 1.247175406468542,
+            "max": 1.7278016608427553,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 66.641398049891,
-            "min": -32.000001668930054,
-            "max": 72.35399839282036,
+            "value": 205.60839764028788,
+            "min": -26.72820170223713,
+            "max": 205.60839764028788,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.1295152211845931,
+            "value": 1.7278016608427553,
             "min": -1.0000000521540642,
-            "max": 1.247175406468542,
+            "max": 1.7278016608427553,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 66.641398049891,
-            "min": -32.000001668930054,
-            "max": 72.35399839282036,
+            "value": 205.60839764028788,
+            "min": -26.72820170223713,
+            "max": 205.60839764028788,
             "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.05053446098562267,
-            "min": 0.048023742093186404,
-            "max": 8.126080268993974,
+            "value": 0.043072443318498486,
+            "min": 0.043072443318498486,
+            "max": 7.647814229130745,
             "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 2.9815331981517375,
-            "min": 2.977472009777557,
-            "max": 130.01728430390358,
+            "value": 5.12562075490132,
+            "min": 5.12562075490132,
+            "max": 122.36502766609192,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +184,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1736903316",
+        "start_time_seconds": "1736906554",
         "python_version": "3.10.12 (main, Nov  6 2024, 20:22:13) [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=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training v2 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.5.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1736904890"
+        "end_time_seconds": "1736908191"
     },
-    "total": 1574.5144424239998,
+    "total": 1637.4332560559997,
     "count": 1,
-    "self": 0.32207940299940674,
+    "self": 0.3726813309986028,
     "children": {
         "run_training.setup": {
-            "total": 0.054595546999735234,
+            "total": 0.05243285300093703,
             "count": 1,
-            "self": 0.054595546999735234
+            "self": 0.05243285300093703
         },
         "TrainerController.start_learning": {
-            "total": 1574.1377674740006,
+            "total": 1637.0081418720001,
             "count": 1,
-            "self": 1.1657887360097448,
+            "self": 1.3389622588965722,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.034048982999593,
+                    "total": 2.0597453669997776,
                     "count": 1,
-                    "self": 2.034048982999593
+                    "self": 2.0597453669997776
                 },
                 "TrainerController.advance": {
-                    "total": 1570.8574966099923,
-                    "count": 63480,
-                    "self": 1.1759522830734568,
+                    "total": 1633.4746749021033,
+                    "count": 64544,
+                    "self": 1.3699907985101163,
                     "children": {
                         "env_step": {
-                            "total": 984.2788708609678,
-                            "count": 63480,
-                            "self": 853.0373787290073,
+                            "total": 1110.7506296606953,
+                            "count": 64544,
+                            "self": 950.6295410709135,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 130.51944839393764,
-                                    "count": 63480,
-                                    "self": 4.1716386990156025,
+                                    "total": 159.32951414784839,
+                                    "count": 64544,
+                                    "self": 4.257317192050323,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 126.34780969492203,
-                                            "count": 62556,
-                                            "self": 126.34780969492203
+                                            "total": 155.07219695579806,
+                                            "count": 62568,
+                                            "self": 155.07219695579806
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7220437380228759,
-                                    "count": 63480,
+                                    "total": 0.791574441933335,
+                                    "count": 64544,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1572.1892510139514,
-                                            "count": 63480,
+                                            "total": 1634.748297106682,
+                                            "count": 64544,
                                             "is_parallel": true,
-                                            "self": 807.8737398078783,
+                                            "self": 778.1429072288938,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0020529049998003757,
+                                                            "total": 0.0021020109998062253,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007027480005490361,
+                                                            "self": 0.0006570600016857497,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013501569992513396,
+                                                                    "total": 0.0014449509981204756,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013501569992513396
+                                                                    "self": 0.0014449509981204756
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03405813300014415,
+                                                            "total": 0.034486802000174066,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00048459600020578364,
+                                                            "self": 0.0004902340024273144,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00028952299999218667,
+                                                                    "total": 0.0003525119991536485,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00028952299999218667
+                                                                    "self": 0.0003525119991536485
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03201261199956207,
+                                                                    "total": 0.03256886300005135,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03201261199956207
+                                                                    "self": 0.03256886300005135
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0012714020003841142,
+                                                                    "total": 0.0010751929985417519,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002964670002256753,
+                                                                    "self": 0.00027766600032919087,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0009749350001584389,
+                                                                            "total": 0.000797526998212561,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0009749350001584389
+                                                                            "self": 0.000797526998212561
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 764.3155112060731,
-                                                    "count": 63479,
+                                                    "total": 856.6053898777882,
+                                                    "count": 64543,
                                                     "is_parallel": true,
-                                                    "self": 20.84254747104478,
+                                                    "self": 21.948420730692305,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 13.970572044018809,
-                                                            "count": 63479,
+                                                            "total": 14.445217680186033,
+                                                            "count": 64543,
                                                             "is_parallel": true,
-                                                            "self": 13.970572044018809
+                                                            "self": 14.445217680186033
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 667.0999962330197,
-                                                            "count": 63479,
+                                                            "total": 755.844714435978,
+                                                            "count": 64543,
                                                             "is_parallel": true,
-                                                            "self": 667.0999962330197
+                                                            "self": 755.844714435978
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 62.40239545798977,
-                                                            "count": 63479,
+                                                            "total": 64.3670370309319,
+                                                            "count": 64543,
                                                             "is_parallel": true,
-                                                            "self": 13.187877370239221,
+                                                            "self": 13.829491690054056,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 49.21451808775055,
-                                                                    "count": 507832,
+                                                                    "total": 50.53754534087784,
+                                                                    "count": 516344,
                                                                     "is_parallel": true,
-                                                                    "self": 49.21451808775055
+                                                                    "self": 50.53754534087784
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 585.402673465951,
-                            "count": 63480,
-                            "self": 2.1966554031023406,
+                            "total": 521.3540544428979,
+                            "count": 64544,
+                            "self": 2.623787207505302,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 114.25299750286013,
-                                    "count": 63480,
-                                    "self": 114.06045811086005,
+                                    "total": 155.0387132753949,
+                                    "count": 64544,
+                                    "self": 154.73925613139545,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.19253939200007153,
+                                            "total": 0.29945714399946155,
                                             "count": 2,
-                                            "self": 0.19253939200007153
+                                            "self": 0.29945714399946155
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 468.95302055998854,
-                                    "count": 448,
-                                    "self": 257.0993368249601,
+                                    "total": 363.6915539599977,
+                                    "count": 235,
+                                    "self": 229.08884048613982,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 211.85368373502843,
-                                            "count": 22803,
-                                            "self": 211.85368373502843
+                                            "total": 134.60271347385788,
+                                            "count": 11493,
+                                            "self": 134.60271347385788
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0039993867394514e-06,
+                    "total": 1.0290004865964875e-06,
                     "count": 1,
-                    "self": 1.0039993867394514e-06
+                    "self": 1.0290004865964875e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08043214099961915,
+                    "total": 0.13475831499999913,
                     "count": 1,
-                    "self": 0.0014224249998733285,
+                    "self": 0.0021120139990671305,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.07900971599974582,
+                            "total": 0.132646301000932,
                             "count": 1,
-                            "self": 0.07900971599974582
+                            "self": 0.132646301000932
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499934,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499934.onnx",
-                "reward": null,
-                "creation_time": 1736904088.2868867,
+                "steps": 499981,
+                "file_path": "results/Pyramids Training v2/Pyramids/Pyramids-499981.onnx",
+                "reward": 1.7431250009685755,
+                "creation_time": 1736907333.6355994,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499934.pt"
+                    "results/Pyramids Training v2/Pyramids/Pyramids-499981.pt"
                 ]
             },
             {
-                "steps": 999928,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999928.onnx",
-                "reward": null,
-                "creation_time": 1736904890.541584,
+                "steps": 999995,
+                "file_path": "results/Pyramids Training v2/Pyramids/Pyramids-999995.onnx",
+                "reward": 1.7041428344590324,
+                "creation_time": 1736908191.122991,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999928.pt"
+                    "results/Pyramids Training v2/Pyramids/Pyramids-999995.pt"
                 ]
             },
             {
-                "steps": 1000048,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000048.onnx",
-                "reward": 1.6249999105930328,
-                "creation_time": 1736904890.6319647,
+                "steps": 1000123,
+                "file_path": "results/Pyramids Training v2/Pyramids/Pyramids-1000123.onnx",
+                "reward": 1.7041428344590324,
+                "creation_time": 1736908191.271462,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000048.pt"
+                    "results/Pyramids Training v2/Pyramids/Pyramids-1000123.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000048,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.6249999105930328,
-            "creation_time": 1736904890.6319647,
+            "steps": 1000123,
+            "file_path": "results/Pyramids Training v2/Pyramids.onnx",
+            "reward": 1.7041428344590324,
+            "creation_time": 1736908191.271462,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000048.pt"
+                "results/Pyramids Training v2/Pyramids/Pyramids-1000123.pt"
             ]
         }
     },