continue another 1M

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dfe082c29afb25d93ef3312caf78e4d768125f095ed489e097466d1ec033ebd
+oid sha256:e3283343e69365de6eb7ec705cb67d4efb0ea9a060791d7db5144262d7bd5386
 size 1420238

Pyramids/Pyramids-1499874.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:735346c03e40f6ef871e6e1c11483809d701e07c8b6f6c719a94af77f8daf07c
+size 1420238

Pyramids/Pyramids-1499874.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f302bfa4710e4202f07c0cccb25de4fd7a36f76774c16497b50d95cbb5e1f1
+size 8656252

Pyramids/Pyramids-1999949.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3283343e69365de6eb7ec705cb67d4efb0ea9a060791d7db5144262d7bd5386
+size 1420238

Pyramids/Pyramids-1999949.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb4c74c6384ebe41e9e06ed35525c3252a56de0c96bd9a5e366767fd0e058b0
+size 8656252

Pyramids/Pyramids-2000205.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3283343e69365de6eb7ec705cb67d4efb0ea9a060791d7db5144262d7bd5386
+size 1420238

Pyramids/Pyramids-2000205.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ada01c970cabab56bec694d66f4f2a85336d4c869875793e27e6bbb87b1c737
+size 8656252

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04b6bcbd3222ea923b179995619fcdc2271592dbfd233b32f9ee1b642db98735
+oid sha256:61dd5010eae58f7db3bbc54652d20591c0a0d995b0204a4e3d2742872444cc63
 size 8655778

Pyramids/events.out.tfevents.1732214110.02aa6a4a6e33.12887.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1245e09e753eb1c828cc8ef9ca6ce8272fff70549ea402ca3c772016bf1975e1
+size 1423

Pyramids/events.out.tfevents.1732214158.02aa6a4a6e33.13148.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7379e38386c4527f378940802db41e0b395f48a8b3d0437f748c5ad05d2cfe2
+size 1423

Pyramids/events.out.tfevents.1732214210.02aa6a4a6e33.13421.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26779a78c9f3205e1bd4422ecedb7f728ad83bdf41c425e1145f6f3ca28088d5
+size 342856

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": 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": 2000000, "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": "PyramidsTraining", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 2000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -79,10 +79,10 @@ 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
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55072 [Flags] 2 [Guid] 2339587004 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55435 [Flags] 2 [Guid] 1748520219 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -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  0.092 seconds
+- Completed reload, in  0.095 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: 1.340017 ms
+UnloadTime: 0.782758 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 5231 frames, [32.0 KB-64.0 KB]: 11961 frames, [64.0 KB-128.0 KB]: 1574 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2615 frames, [32.0 KB-64.0 KB]: 12789 frames, [64.0 KB-128.0 KB]: 3361 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
@@ -149,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18468 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 90 frames, [1.0 MB-2.0 MB]: 18676 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.3 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 13352
+  Peak main deferred allocation count 13122
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18766 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18765 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 30.5 MB
+      Peak Block count 2
+      Peak Allocated memory 27.4 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]: 18766 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.5 MB
+      Peak Allocated memory 21.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 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]: 18765 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 18767 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18766 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18468 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 198 frames, [1.0 MB-2.0 MB]: 18568 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]: 18765 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -291,27 +288,27 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18767 frames
+      Peak usage frame count: [0-1.0 KB]: 18766 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 18767 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18766 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 18767 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18766 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 29.0 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1732213690568,"processId":1975,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1732216563188,"processId":13461,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.6236155033111572,
-            "min": 0.6111069321632385,
-            "max": 1.509022831916809,
+            "value": 0.3288368880748749,
+            "min": 0.3288368880748749,
+            "max": 0.6374443173408508,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 18618.6640625,
-            "min": 18303.875,
-            "max": 45777.71484375,
+            "value": 10007.1640625,
+            "min": 10007.1640625,
+            "max": 19357.908203125,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989943.0,
-            "min": 29952.0,
-            "max": 989943.0,
+            "value": 1979997.0,
+            "min": 1019958.0,
+            "max": 1979997.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989943.0,
-            "min": 29952.0,
-            "max": 989943.0,
+            "value": 1979997.0,
+            "min": 1019958.0,
+            "max": 1979997.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.006052304059267044,
-            "min": -0.10627507418394089,
-            "max": 0.06861069798469543,
+            "value": 0.3879289925098419,
+            "min": 0.022524673491716385,
+            "max": 0.49204227328300476,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1.4707099199295044,
-            "min": -25.612293243408203,
-            "max": 16.878231048583984,
+            "value": 105.90461730957031,
+            "min": 3.6715216636657715,
+            "max": 132.85140991210938,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.010854288935661316,
-            "min": 0.00927999522536993,
-            "max": 0.15973161160945892,
+            "value": 0.025791283696889877,
+            "min": -0.005343945696949959,
+            "max": 0.03500159829854965,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 2.637592315673828,
-            "min": 2.282878875732422,
-            "max": 38.33558654785156,
+            "value": 7.041020393371582,
+            "min": -1.400113821029663,
+            "max": 9.520434379577637,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06804533713812391,
-            "min": 0.06463535242632137,
-            "max": 0.07381134586330741,
+            "value": 0.06406410573509955,
+            "min": 0.06406410573509955,
+            "max": 0.07185494447238182,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9526347199337347,
-            "min": 0.49431228521731596,
-            "max": 1.0423397045815364,
+            "value": 0.9609615860264932,
+            "min": 0.5398511573303993,
+            "max": 1.0491777876433095,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0033981642682982373,
-            "min": 0.00012793582912984754,
-            "max": 0.008450206071857895,
+            "value": 0.01642818447567954,
+            "min": 0.0045277437953204925,
+            "max": 0.01642818447567954,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.047574299756175324,
-            "min": 0.001663165778688018,
-            "max": 0.12675309107786842,
+            "value": 0.2464227671351931,
+            "min": 0.04714187418616633,
+            "max": 0.2464227671351931,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.302161851692857e-06,
-            "min": 7.302161851692857e-06,
-            "max": 0.00029515063018788575,
+            "value": 5.2679782440400025e-06,
+            "min": 5.2679782440400025e-06,
+            "max": 0.0001482286630904625,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0001022302659237,
-            "min": 0.0001022302659237,
-            "max": 0.0033829004723665997,
+            "value": 7.901967366060004e-05,
+            "min": 7.901967366060004e-05,
+            "max": 0.0020250700249769,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10243402142857143,
-            "min": 0.10243402142857143,
-            "max": 0.19838354285714285,
+            "value": 0.10175595999999999,
+            "min": 0.10175595999999999,
+            "max": 0.14940953750000002,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4340763,
-            "min": 1.3691136000000002,
-            "max": 2.5276334,
+            "value": 1.5263394,
+            "min": 1.1952763000000002,
+            "max": 2.11113025,
             "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002531587407142857,
-            "min": 0.0002531587407142857,
-            "max": 0.00983851593142857,
+            "value": 0.00018542040400000006,
+            "min": 0.00018542040400000006,
+            "max": 0.00494601279625,
             "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0035442223700000003,
-            "min": 0.0035442223700000003,
-            "max": 0.11279057666000002,
+            "value": 0.002781306060000001,
+            "min": 0.002781306060000001,
+            "max": 0.06757480769,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.00954583939164877,
-            "min": 0.00954583939164877,
-            "max": 0.31258949637413025,
+            "value": 0.004714569076895714,
+            "min": 0.004656789358705282,
+            "max": 0.010158630087971687,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.13364174962043762,
-            "min": 0.13364174962043762,
-            "max": 2.188126564025879,
+            "value": 0.07071853429079056,
+            "min": 0.06519505381584167,
+            "max": 0.1343543529510498,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 862.3870967741935,
-            "min": 775.0,
-            "max": 999.0,
+            "value": 424.28169014084506,
+            "min": 377.63513513513516,
+            "max": 853.5714285714286,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 26734.0,
-            "min": 15984.0,
-            "max": 32716.0,
+            "value": 30124.0,
+            "min": 13971.0,
+            "max": 34643.0,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.21764520723973552,
-            "min": -1.0000000521540642,
-            "max": 0.3747749594971538,
+            "value": 1.4348365983492892,
+            "min": -0.054011474975517816,
+            "max": 1.5696026442448299,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -6.747001424431801,
-            "min": -32.000001668930054,
-            "max": 14.99099837988615,
+            "value": 101.87339848279953,
+            "min": -1.8904016241431236,
+            "max": 117.72019831836224,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.21764520723973552,
-            "min": -1.0000000521540642,
-            "max": 0.3747749594971538,
+            "value": 1.4348365983492892,
+            "min": -0.054011474975517816,
+            "max": 1.5696026442448299,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -6.747001424431801,
-            "min": -32.000001668930054,
-            "max": 14.99099837988615,
+            "value": 101.87339848279953,
+            "min": -1.8904016241431236,
+            "max": 117.72019831836224,
             "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.08653244257138501,
-            "min": 0.08558558726945194,
-            "max": 5.97111224103719,
+            "value": 0.02140662624151446,
+            "min": 0.019622120888851822,
+            "max": 0.08475303877743759,
             "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 2.6825057197129354,
-            "min": 2.6825057197129354,
-            "max": 95.53779585659504,
+            "value": 1.5198704631475266,
+            "min": 1.4520369457750348,
+            "max": 3.013041902362602,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +184,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1732211459",
+        "start_time_seconds": "1732214209",
         "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=PyramidsTraining --no-graphics --resume",
         "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": "1732213690"
+        "end_time_seconds": "1732216563"
     },
-    "total": 2231.017183911,
+    "total": 2353.9807636950004,
     "count": 1,
-    "self": 0.4774309749996064,
+    "self": 0.47639820800031885,
     "children": {
         "run_training.setup": {
-            "total": 0.05915233600001102,
+            "total": 0.05796810199990432,
             "count": 1,
-            "self": 0.05915233600001102
+            "self": 0.05796810199990432
         },
         "TrainerController.start_learning": {
-            "total": 2230.4806006000003,
+            "total": 2353.446397385,
             "count": 1,
-            "self": 1.6490224700132785,
+            "self": 1.526080958845796,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.182302188999984,
+                    "total": 2.201755490999858,
                     "count": 1,
-                    "self": 5.182302188999984
+                    "self": 2.201755490999858
                 },
                 "TrainerController.advance": {
-                    "total": 2223.509423870987,
-                    "count": 63193,
-                    "self": 1.5849350469898127,
+                    "total": 2349.6323508541545,
+                    "count": 64052,
+                    "self": 1.5457315301337076,
                     "children": {
                         "env_step": {
-                            "total": 1521.5521052910058,
-                            "count": 63193,
-                            "self": 1354.9088622860656,
+                            "total": 1653.2551761230015,
+                            "count": 64052,
+                            "self": 1495.9177507449986,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 165.70288789595384,
-                                    "count": 63193,
-                                    "self": 4.935155225945266,
+                                    "total": 156.4607022899918,
+                                    "count": 64052,
+                                    "self": 4.826967040053205,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 160.76773267000857,
-                                            "count": 62556,
-                                            "self": 160.76773267000857
+                                            "total": 151.63373524993858,
+                                            "count": 62552,
+                                            "self": 151.63373524993858
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.9403551089862958,
-                                    "count": 63193,
+                                    "total": 0.8767230880112038,
+                                    "count": 64052,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2224.946078920029,
-                                            "count": 63193,
+                                            "total": 2347.9183412740263,
+                                            "count": 64052,
                                             "is_parallel": true,
-                                            "self": 996.7587547030205,
+                                            "self": 974.4295465497976,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0021780620000413364,
+                                                            "total": 0.0025034629998117452,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006785610000292763,
+                                                            "self": 0.0007505519997721422,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.00149950100001206,
+                                                                    "total": 0.001752911000039603,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00149950100001206
+                                                                    "self": 0.001752911000039603
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.046659530999988874,
+                                                            "total": 0.04789147600013166,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006504909999307529,
+                                                            "self": 0.0006273240001064551,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00044769100003350104,
+                                                                    "total": 0.0004943559997627744,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00044769100003350104
+                                                                    "self": 0.0004943559997627744
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04392933600001925,
+                                                                    "total": 0.045079006000378286,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04392933600001925
+                                                                    "self": 0.045079006000378286
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016320130000053723,
+                                                                    "total": 0.0016907899998841458,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00035081899989108933,
+                                                                    "self": 0.0003641870002866199,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001281194000114283,
+                                                                            "total": 0.001326602999597526,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001281194000114283
+                                                                            "self": 0.001326602999597526
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1228.1873242170084,
-                                                    "count": 63192,
+                                                    "total": 1373.4887947242287,
+                                                    "count": 64051,
                                                     "is_parallel": true,
-                                                    "self": 34.66797322007392,
+                                                    "self": 34.013932495060544,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 23.25568454397046,
-                                                            "count": 63192,
+                                                            "total": 23.274413845092567,
+                                                            "count": 64051,
                                                             "is_parallel": true,
-                                                            "self": 23.25568454397046
+                                                            "self": 23.274413845092567
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1069.5026539679711,
-                                                            "count": 63192,
+                                                            "total": 1216.0480809410578,
+                                                            "count": 64051,
                                                             "is_parallel": true,
-                                                            "self": 1069.5026539679711
+                                                            "self": 1216.0480809410578
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 100.76101248499288,
-                                                            "count": 63192,
+                                                            "total": 100.15236744301774,
+                                                            "count": 64051,
                                                             "is_parallel": true,
-                                                            "self": 21.181555794011558,
+                                                            "self": 20.97420131192439,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 79.57945669098132,
-                                                                    "count": 505536,
+                                                                    "total": 79.17816613109335,
+                                                                    "count": 512408,
                                                                     "is_parallel": true,
-                                                                    "self": 79.57945669098132
+                                                                    "self": 79.17816613109335
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 700.3723835329914,
-                            "count": 63193,
-                            "self": 3.107676413997183,
+                            "total": 694.8314432010193,
+                            "count": 64052,
+                            "self": 3.041502776978632,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 134.29692811499632,
-                                    "count": 63193,
-                                    "self": 133.93126858699662,
+                                    "total": 136.84945755504305,
+                                    "count": 64052,
+                                    "self": 136.64514838304422,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.36565952799969637,
+                                            "total": 0.2043091719988297,
                                             "count": 2,
-                                            "self": 0.36565952799969637
+                                            "self": 0.2043091719988297
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 562.967779003998,
-                                    "count": 442,
-                                    "self": 314.27313607299186,
+                                    "total": 554.9404828689976,
+                                    "count": 470,
+                                    "self": 310.48992824498146,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 248.69464293100611,
-                                            "count": 22809,
-                                            "self": 248.69464293100611
+                                            "total": 244.45055462401615,
+                                            "count": 22734,
+                                            "self": 244.45055462401615
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.3429998944047838e-06,
+                    "total": 1.0469993867445737e-06,
                     "count": 1,
-                    "self": 1.3429998944047838e-06
+                    "self": 1.0469993867445737e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1398507270000664,
+                    "total": 0.08620903400060342,
                     "count": 1,
-                    "self": 0.00224192799987577,
+                    "self": 0.0018989680011145538,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.13760879900019063,
+                            "total": 0.08431006599948887,
                             "count": 1,
-                            "self": 0.13760879900019063
+                            "self": 0.08431006599948887
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499994,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499994.onnx",
-                "reward": -0.9992000460624695,
-                "creation_time": 1732212525.3271976,
+                "steps": 1000080,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1000080.onnx",
+                "reward": null,
+                "creation_time": 1732214112.7854717,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499994.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-1000080.pt"
                 ]
             },
             {
-                "steps": 999952,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999952.onnx",
-                "reward": -0.999800056219101,
-                "creation_time": 1732213689.993845,
+                "steps": 1000080,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1000080.onnx",
+                "reward": null,
+                "creation_time": 1732214161.2930307,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999952.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-1000080.pt"
                 ]
             },
             {
-                "steps": 1000080,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000080.onnx",
-                "reward": -0.999800056219101,
-                "creation_time": 1732213690.1529999,
+                "steps": 1499874,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1499874.onnx",
+                "reward": 0.8958499506115913,
+                "creation_time": 1732215342.4006295,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-1499874.pt"
+                ]
+            },
+            {
+                "steps": 1999949,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1999949.onnx",
+                "reward": null,
+                "creation_time": 1732216562.6483617,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-1999949.pt"
+                ]
+            },
+            {
+                "steps": 2000205,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-2000205.onnx",
+                "reward": null,
+                "creation_time": 1732216562.7638965,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000080.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-2000205.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000080,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": -0.999800056219101,
-            "creation_time": 1732213690.1529999,
+            "steps": 2000205,
+            "file_path": "results/PyramidsTraining/Pyramids.onnx",
+            "reward": null,
+            "creation_time": 1732216562.7638965,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000080.pt"
+                "results/PyramidsTraining/Pyramids/Pyramids-2000205.pt"
             ]
         }
     },