First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a368ce817a9514150da02f5b62ff88e6d012a63afb5253a88f87f262c29f33
-size 1420238
+oid sha256:c42875006a265618084eaa1107cfda9829db38c60e466b8cee33be1ed86ba7af
+size 13331249

Pyramids/Pyramids-1000205.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42875006a265618084eaa1107cfda9829db38c60e466b8cee33be1ed86ba7af
+size 13331249

Pyramids/Pyramids-1000205.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8a56b6eb5e7c76c716c2a05ab4cd25427380c4f474853a74e2a427649738853
+size 81354563

Pyramids/Pyramids-18048.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb0dc767dea51e6a5f7eebf1c0f07749bb8c42468e5b46555bd4958f695561fc
+size 1420238

Pyramids/Pyramids-18048.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ccfd40fcefe8f4562dcec7351c42a483f149f39fe19a931bad2ae87ff42e2ff
+size 8656094

Pyramids/Pyramids-499833.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2150ab42f768b7e941fffe4bed5707d36102814b94c40dd99a13ec77370b36a8
+size 13331249

Pyramids/Pyramids-499833.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af67ce1a8bf2abf0b71a38c19bc53e2ee4ca7e2b1ccc5e24572ac7139dee7dd6
+size 81354452

Pyramids/Pyramids-999949.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42875006a265618084eaa1107cfda9829db38c60e466b8cee33be1ed86ba7af
+size 13331249

Pyramids/Pyramids-999949.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed69e29fb598e29093e08cf5bac1e81c988d7e8f2d32ac4bcade57e7f4b31f1
+size 81354452

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2427d705b2f06ee7f16737983ed8e021c5fb391b56a5352e58bebf5c53f36fe6
-size 8656181
+oid sha256:70b2ee2d03566577fee2eb985231ed373d9e9ec85fb6498b2b52908d6c26f95d
+size 81353897

Pyramids/events.out.tfevents.1751019578.Office.96172.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36fccdb50a34ba86c61d294ddf44cdb75a2ab3ccc2d243519ce1e54ba187252
+size 323891

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 8192, "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": 8, "num_areas": 4, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cuda"}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 8192, "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": 1024, "num_layers": 4, "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": 0.02, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 256, "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": "PyramidsTraining", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cuda"}, "debug": false}

configuration.yaml

@@ -17,8 +17,8 @@ behaviors:
     checkpoint_interval: 500000
     network_settings:
       normalize: false
-      hidden_units: 512
-      num_layers: 2
+      hidden_units: 1024
+      num_layers: 4
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
@@ -37,22 +37,22 @@ behaviors:
           deterministic: false
       rnd:
         gamma: 0.99
-        strength: 0.01
+        strength: 0.02
         network_settings:
           normalize: false
-          hidden_units: 64
+          hidden_units: 256
           num_layers: 3
           vis_encode_type: simple
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
-        learning_rate: 0.0001
+        learning_rate: 0.0003
         encoding_size: null
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
     max_steps: 1000000
-    time_horizon: 128
+    time_horizon: 256
     summary_freq: 30000
     threaded: false
     self_play: null
@@ -61,8 +61,8 @@ env_settings:
   env_path: ./training-envs-executables/linux/Pyramids/Pyramids
   env_args: null
   base_port: 5005
-  num_envs: 8
-  num_areas: 4
+  num_envs: 1
+  num_areas: 1
   timeout_wait: 60
   seed: -1
   max_lifetime_restarts: 10
@@ -79,7 +79,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: PyramidsTraining
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/home/mtn/rl_course/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/home/mtn/rl_course/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 4 interfaces on host : 0) 172.31.77.83 1) 172.17.0.1 2) 172.18.0.1 3) 172.19.0.1
-Multi-casting "[IP] 172.31.77.83 [Port] 55508 [Flags] 2 [Guid] 3794615371 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.31.77.83) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.31.77.83 [Port] 55414 [Flags] 2 [Guid] 856950676 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.31.77.83) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -13,7 +13,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.101 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)
@@ -45,7 +45,7 @@ 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: 1.166100 ms
+UnloadTime: 1.158300 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 16 worker threads for Enlighten.
@@ -53,7 +53,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 1419 frames, [32.0 KB-64.0 KB]: 1010 frames, [64.0 KB-128.0 KB]: 171 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3974 frames, [32.0 KB-64.0 KB]: 11567 frames, [64.0 KB-128.0 KB]: 3238 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
@@ -151,12 +151,12 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 3]
       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_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 3.8 KB
+      Peak Allocated Bytes 7.5 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 17]
       Initial Block Size 256.0 KB
@@ -176,14 +176,14 @@ 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_Job.Worker 11]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 6]
+    [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -193,7 +193,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 0]
+    [ALLOC_TEMP_Job.Worker 6]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -248,12 +248,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 26]
+    [ALLOC_TEMP_Job.Worker 30]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 30]
+    [ALLOC_TEMP_Job.Worker 26]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -278,12 +278,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 1]
+    [ALLOC_TEMP_Job.Worker 23]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 23]
+    [ALLOC_TEMP_Job.Worker 1]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -334,28 +334,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 2302 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18481 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 11314
+  Peak main deferred allocation count 12820
     [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]: 2600 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18779 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.8 MB
+      Peak Allocated memory 29.5 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 2601 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 866 frames, [32.0 MB-64.0 MB]: 17914 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 31.1 MB
+      Peak Block count 2
+      Peak Allocated memory 32.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -384,13 +384,13 @@ 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]: 2600 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18779 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]: 2601 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18780 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -402,13 +402,13 @@ 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]: 2302 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18481 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]: 2600 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18779 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
@@ -420,25 +420,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 2601 frames
+      Peak usage frame count: [0-1.0 KB]: 18780 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]: 2601 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18780 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: [32.0 KB-64.0 KB]: 2601 frames
+  Peak usage frame count: [32.0 KB-64.0 KB]: 18780 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 54.4 KB
+  Peak Allocated memory 54.0 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1751006063236,"processId":32579,"allocatedMemory":2066841,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":73418},{"Thread":35300},{"Manager":33551},{"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":3510},{"DynamicArray":30868},{"HashMap":7680},{"Utility":13600},{"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":1751021795019,"processId":96288,"allocatedMemory":2066841,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":73418},{"Thread":35300},{"Manager":33551},{"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":3510},{"DynamicArray":30868},{"HashMap":7680},{"Utility":13600},{"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": 0.8122937679290771,
-            "min": 0.800395667552948,
-            "max": 1.600343942642212,
+            "value": 0.3244781792163849,
+            "min": 0.3244781792163849,
+            "max": 1.5903981924057007,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 25434.54296875,
-            "min": 23299.17578125,
-            "max": 57945.25390625,
+            "value": 9848.5615234375,
+            "min": 9590.873046875,
+            "max": 50892.7421875,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989944.0,
-            "min": 29952.0,
-            "max": 989944.0,
+            "value": 989759.0,
+            "min": 29912.0,
+            "max": 989759.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989944.0,
-            "min": 29952.0,
-            "max": 989944.0,
+            "value": 989759.0,
+            "min": 29912.0,
+            "max": 989759.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.09227124601602554,
-            "min": -0.11709148436784744,
-            "max": 0.09227124601602554,
+            "value": 0.6161084175109863,
+            "min": -0.10594413429498672,
+            "max": 0.6525713205337524,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 23.16008186340332,
-            "min": -28.453229904174805,
-            "max": 23.16008186340332,
+            "value": 96.72901916503906,
+            "min": -12.92518424987793,
+            "max": 106.36912536621094,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.03637566417455673,
-            "min": 0.03291725367307663,
-            "max": 0.3873744308948517,
+            "value": 0.09512469917535782,
+            "min": 0.09512469917535782,
+            "max": 1.7360094785690308,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 9.130291938781738,
-            "min": 8.16347885131836,
-            "max": 90.64561462402344,
+            "value": 14.934577941894531,
+            "min": 14.934577941894531,
+            "max": 210.05714416503906,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.030458570157255355,
-            "min": 0.030458570157255355,
-            "max": 0.03825497998493827,
+            "value": 0.03433183225327714,
+            "min": 0.03087187964249299,
+            "max": 0.0407908167351197,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.09137571047176607,
-            "min": 0.0758109817126145,
-            "max": 0.1493182438499906,
+            "value": 0.13732732901310857,
+            "min": 0.0732553819473383,
+            "max": 0.15278395361383446,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.007013522824207839,
-            "min": 0.0007838843017372166,
-            "max": 0.011578807605352872,
+            "value": 0.013738000093629429,
+            "min": 0.0026074347727747713,
+            "max": 0.28497444244398584,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.021040568472623516,
-            "min": 0.0023516529052116496,
-            "max": 0.03202543730731122,
+            "value": 0.054952000374517716,
+            "min": 0.007822304318324313,
+            "max": 0.5699488848879717,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.944897351733329e-06,
-            "min": 7.944897351733329e-06,
-            "max": 0.00029539200153599985,
+            "value": 7.688272437274996e-06,
+            "min": 7.688272437274996e-06,
+            "max": 0.000294528001824,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 2.3834692055199987e-05,
-            "min": 2.3834692055199987e-05,
-            "max": 0.0010740060419979999,
+            "value": 3.0753089749099986e-05,
+            "min": 3.0753089749099986e-05,
+            "max": 0.0010400658533114,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10264826666666667,
-            "min": 0.10264826666666667,
-            "max": 0.19846400000000003,
+            "value": 0.10256272500000001,
+            "min": 0.10256272500000001,
+            "max": 0.19817600000000002,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 0.3079448,
-            "min": 0.3079448,
-            "max": 0.7580020000000001,
+            "value": 0.41025090000000003,
+            "min": 0.31636060000000005,
+            "max": 0.7466886,
             "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00027456183999999994,
-            "min": 0.00027456183999999994,
-            "max": 0.009846553599999997,
+            "value": 0.0002660162274999999,
+            "min": 0.0002660162274999999,
+            "max": 0.0098177824,
             "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0008236855199999998,
-            "min": 0.0008236855199999998,
-            "max": 0.0358043998,
+            "value": 0.0010640649099999996,
+            "min": 0.0010640649099999996,
+            "max": 0.034674191140000005,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.030197588726878166,
-            "min": 0.030197588726878166,
-            "max": 0.7899608016014099,
+            "value": 0.04288814589381218,
+            "min": 0.04288814589381218,
+            "max": 0.8643540740013123,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.09059276431798935,
-            "min": 0.09059276431798935,
-            "max": 1.5799216032028198,
-            "count": 33
-        },
-        "Pyramids.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 33
-        },
-        "Pyramids.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
+            "value": 0.17155258357524872,
+            "min": 0.1336830109357834,
+            "max": 1.7287081480026245,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 743.6428571428571,
-            "min": 298.0,
+            "value": 346.12048192771084,
+            "min": 309.2826086956522,
             "max": 999.0,
-            "count": 31
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31233.0,
-            "min": 298.0,
-            "max": 78921.0,
-            "count": 31
+            "value": 28728.0,
+            "min": 17218.0,
+            "max": 32546.0,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 0.39893329196742605,
-            "min": -1.0000000521540642,
-            "max": 1.7019999325275421,
-            "count": 31
+            "value": 1.6056626216474785,
+            "min": -1.0000000596046448,
+            "max": 1.6702257910723328,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 16.755198262631893,
-            "min": -79.00000412017107,
-            "max": 19.641998454928398,
-            "count": 31
+            "value": 133.26999759674072,
+            "min": -30.575601875782013,
+            "max": 155.33099856972694,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 0.39893329196742605,
-            "min": -1.0000000521540642,
-            "max": 1.7019999325275421,
-            "count": 31
+            "value": 1.6056626216474785,
+            "min": -1.0000000596046448,
+            "max": 1.6702257910723328,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 16.755198262631893,
-            "min": -79.00000412017107,
-            "max": 19.641998454928398,
-            "count": 31
+            "value": 133.26999759674072,
+            "min": -30.575601875782013,
+            "max": 155.33099856972694,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.24297304781863377,
-            "min": 0.24297304781863377,
-            "max": 5.09961189267536,
-            "count": 31
+            "value": 0.2978080925363374,
+            "min": 0.2877048087823722,
+            "max": 67.48608592800473,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 10.204868008382618,
-            "min": 0.5913975909352303,
-            "max": 298.7930725812912,
-            "count": 31
+            "value": 24.718071680516005,
+            "min": 24.718071680516005,
+            "max": 1552.1799763441086,
+            "count": 33
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1751005356",
+        "start_time_seconds": "1751019577",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/home/mtn/miniconda3/envs/mlagents310/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --torch-device=cuda --num-envs=8 --num-areas=4 --force",
+        "command_line_arguments": "/home/mtn/miniconda3/envs/mlagents310/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics --torch-device=cuda --force",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
-        "pytorch_version": "2.7.1+cu126",
+        "pytorch_version": "2.4.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1751006063"
+        "end_time_seconds": "1751021795"
     },
-    "total": 672.8325766039998,
+    "total": 2074.831323061,
     "count": 1,
-    "self": 0.5223009729988917,
+    "self": 0.37082345000089845,
     "children": {
         "run_training.setup": {
-            "total": 0.08271814300042024,
+            "total": 0.024627888000395615,
             "count": 1,
-            "self": 0.08271814300042024
+            "self": 0.024627888000395615
         },
         "TrainerController.start_learning": {
-            "total": 672.2275574880005,
+            "total": 2074.435871722999,
             "count": 1,
-            "self": 0.6520584409117873,
+            "self": 1.446699069107126,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.1321000990001266,
+                    "total": 2.0366845190001186,
                     "count": 1,
-                    "self": 3.1321000990001266
+                    "self": 2.0366845190001186
                 },
                 "TrainerController.advance": {
-                    "total": 668.3502092720883,
-                    "count": 21483,
-                    "self": 0.5728113499144456,
+                    "total": 2070.4728784398903,
+                    "count": 64031,
+                    "self": 1.260445219126268,
                     "children": {
                         "env_step": {
-                            "total": 292.7903589910793,
-                            "count": 21483,
-                            "self": 67.77903544710898,
+                            "total": 1631.274576708718,
+                            "count": 64031,
+                            "self": 1323.6688548305065,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 224.53989962097603,
-                                    "count": 63320,
-                                    "self": 5.430243703059205,
+                                    "total": 306.5815242494609,
+                                    "count": 64031,
+                                    "self": 4.715514139163133,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 219.10965591791683,
-                                            "count": 62967,
-                                            "self": 219.10965591791683
+                                            "total": 301.8660101102978,
+                                            "count": 62598,
+                                            "self": 301.8660101102978
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.4714239229942905,
-                                    "count": 21483,
+                                    "total": 1.0241976287506986,
+                                    "count": 64031,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 5373.128690633984,
-                                            "count": 63314,
+                                            "total": 2070.367175787116,
+                                            "count": 64031,
                                             "is_parallel": true,
-                                            "self": 4037.3823520730066,
+                                            "self": 845.199130731391,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.015397202999338333,
-                                                            "count": 8,
+                                                            "total": 0.0016963509988272563,
+                                                            "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00528224599929672,
+                                                            "self": 0.0006021059962222353,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.010114957000041613,
-                                                                    "count": 64,
+                                                                    "total": 0.001094245002605021,
+                                                                    "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.010114957000041613
+                                                                    "self": 0.001094245002605021
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.3963580390009156,
-                                                            "count": 8,
+                                                            "total": 0.03879922299893224,
+                                                            "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0024451020017295377,
+                                                            "self": 0.00028681799813057296,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0019348830001035822,
-                                                                    "count": 8,
+                                                                    "total": 0.00028495800142991357,
+                                                                    "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0019348830001035822
+                                                                    "self": 0.00028495800142991357
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.38390339499801485,
-                                                                    "count": 8,
+                                                                    "total": 0.03746504700029618,
+                                                                    "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.38390339499801485
+                                                                    "self": 0.03746504700029618
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.00807465900106763,
-                                                                    "count": 8,
+                                                                    "total": 0.0007623999990755692,
+                                                                    "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.002123424005731067,
+                                                                    "self": 0.00017964399376069196,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.005951234995336563,
-                                                                            "count": 64,
+                                                                            "total": 0.0005827560053148773,
+                                                                            "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.005951234995336563
+                                                                            "self": 0.0005827560053148773
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1335.7463385609772,
-                                                    "count": 63306,
+                                                    "total": 1225.168045055725,
+                                                    "count": 64030,
                                                     "is_parallel": true,
-                                                    "self": 19.611213464248976,
+                                                    "self": 18.322320682211284,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 13.362481814992861,
-                                                            "count": 63306,
+                                                            "total": 13.272767867289076,
+                                                            "count": 64030,
                                                             "is_parallel": true,
-                                                            "self": 13.362481814992861
+                                                            "self": 13.272767867289076
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1252.148522283871,
-                                                            "count": 63306,
+                                                            "total": 1146.5050576348476,
+                                                            "count": 64030,
                                                             "is_parallel": true,
-                                                            "self": 1252.148522283871
+                                                            "self": 1146.5050576348476
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 50.62412099786434,
-                                                            "count": 63306,
+                                                            "total": 47.06789887137711,
+                                                            "count": 64030,
                                                             "is_parallel": true,
-                                                            "self": 11.552173915520143,
+                                                            "self": 10.681787790766975,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 39.071947082344195,
-                                                                    "count": 506448,
+                                                                    "total": 36.386111080610135,
+                                                                    "count": 512240,
                                                                     "is_parallel": true,
-                                                                    "self": 39.071947082344195
+                                                                    "self": 36.386111080610135
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 374.9870389310945,
-                            "count": 21483,
-                            "self": 1.362361584030623,
+                            "total": 437.937856512046,
+                            "count": 64031,
+                            "self": 3.2250884741552,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 119.61589934906442,
-                                    "count": 21483,
-                                    "self": 119.41855172706437,
+                                    "total": 111.30187467289943,
+                                    "count": 64031,
+                                    "self": 110.20551355089992,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.19734762200005207,
+                                            "total": 1.0963611219995073,
                                             "count": 2,
-                                            "self": 0.19734762200005207
+                                            "self": 1.0963611219995073
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 254.00877799799946,
-                                    "count": 112,
-                                    "self": 171.2955985979761,
+                                    "total": 323.41089336499135,
+                                    "count": 117,
+                                    "self": 193.420435253076,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 82.71317940002336,
-                                            "count": 5736,
-                                            "self": 82.71317940002336
+                                            "total": 129.99045811191536,
+                                            "count": 5739,
+                                            "self": 129.99045811191536
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 7.620001269970089e-07,
+                    "total": 5.62002242077142e-07,
                     "count": 1,
-                    "self": 7.620001269970089e-07
+                    "self": 5.62002242077142e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09318891400016582,
+                    "total": 0.4796091329990304,
                     "count": 1,
-                    "self": 0.0029602129998238524,
+                    "self": 0.023650801998883253,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09022870100034197,
+                            "total": 0.45595833100014715,
                             "count": 1,
-                            "self": 0.09022870100034197
+                            "self": 0.45595833100014715
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,46 +2,46 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499898,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499898.onnx",
-                "reward": 0.17369995266199112,
-                "creation_time": 1751005709.398971,
+                "steps": 499833,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-499833.onnx",
+                "reward": 0.7626571186951229,
+                "creation_time": 1751020640.7455657,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499898.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-499833.pt"
                 ]
             },
             {
-                "steps": 999964,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999964.onnx",
-                "reward": 0.46353329221407574,
-                "creation_time": 1751006062.7178452,
+                "steps": 999949,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-999949.onnx",
+                "reward": 1.5865428405148643,
+                "creation_time": 1751021794.1971548,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999964.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-999949.pt"
                 ]
             },
             {
-                "steps": 1000092,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000092.onnx",
-                "reward": 0.46353329221407574,
-                "creation_time": 1751006062.8196437,
+                "steps": 1000205,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1000205.onnx",
+                "reward": 1.5865428405148643,
+                "creation_time": 1751021794.6736128,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000092.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-1000205.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000092,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 0.46353329221407574,
-            "creation_time": 1751006062.8196437,
+            "steps": 1000205,
+            "file_path": "results/PyramidsTraining/Pyramids.onnx",
+            "reward": 1.5865428405148643,
+            "creation_time": 1751021794.6736128,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000092.pt"
+                "results/PyramidsTraining/Pyramids/Pyramids-1000205.pt"
             ]
         }
     },
     "metadata": {
         "stats_format_version": "0.3.0",
         "mlagents_version": "1.2.0.dev0",
-        "torch_version": "2.7.1+cu126"
+        "torch_version": "2.4.0+cu121"
     }
 }