First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6335dacbfe6d7a982447693d66215ec64a86b0f99d9d9d304889cc8267a7a70f
+oid sha256:77a3c634b7c8aff01d2182cc91e30a4bed530c0f0e338c2bc970dba6cb3e5963
 size 1420238

Pyramids/Pyramids-1499910.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283589c24c1546c2ac7bf5ee5953cee81a901f8e95e2a2f75249f6e12f34003b
+size 1420238

Pyramids/Pyramids-1499910.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e66129d513759de168a5e74aeb2508f782ffbbf8652c7d96eb32695b16e01bb
+size 8656731

Pyramids/Pyramids-1999888.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a3c634b7c8aff01d2182cc91e30a4bed530c0f0e338c2bc970dba6cb3e5963
+size 1420238

Pyramids/Pyramids-1999888.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a88c47a5af2c8a83d465eda1fd96d849007a1eb63895e78075e0dab16afc698c
+size 8656731

Pyramids/Pyramids-2000016.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a3c634b7c8aff01d2182cc91e30a4bed530c0f0e338c2bc970dba6cb3e5963
+size 1420238

Pyramids/Pyramids-2000016.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c0af4581a85dc2650725251bf76653778dcb0c7bc2a2f39eac01d5fca7cb93
+size 8656731

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a30528b3fae122476e8c9f486849563a37f9647aba1034ef6304ef25d4931265
+oid sha256:8d88d36c1bb27a52ef52542386ae94134c96d55c1ce88caa7a2fc464f7c0aee4
 size 8656181

Pyramids/events.out.tfevents.1753090984.1b7113565678.15313.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b21fbd346310e819124129b8729326e727075b16e66539e903d43b770819630
+size 1423

Pyramids/events.out.tfevents.1753091010.1b7113565678.15479.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce6f52a54345407de9486b0996bb6e3ebd32ca36146f60fedd746e0766b573f8
+size 277674

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": "Pyramids Training", "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
@@ -82,7 +82,7 @@ checkpoint_settings:
   run_id: Pyramids Training
   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] 55457 [Flags] 2 [Guid] 2212698113 [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] 55315 [Flags] 2 [Guid] 845203319 [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
@@ -36,17 +33,10 @@ 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  0.089 seconds
+- Completed reload, in  0.121 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)
-WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
-ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
 WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - 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?
@@ -68,7 +58,14 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.788954 ms
+WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.977024 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]: 7350 frames, [32.0 KB-64.0 KB]: 9270 frames, [64.0 KB-128.0 KB]: 2147 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1736 frames, [32.0 KB-64.0 KB]: 11406 frames, [64.0 KB-128.0 KB]: 5620 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 480 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -207,29 +204,29 @@ 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]: 18469 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 96 frames, [1.0 MB-2.0 MB]: 18667 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12351
+  Peak main deferred allocation count 8843
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18767 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames, [32.0 MB-64.0 MB]: 18762 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 30.3 MB
-      Peak Large allocation bytes 0 B
+      Peak Block count 2
+      Peak Allocated memory 40.1 MB
+      Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18768 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames, [4.0 MB-8.0 MB]: 18762 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.3 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 6.9 MB
+      Peak Large allocation bytes 0 B
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -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 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18767 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18762 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]: 18768 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18763 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 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18469 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 65 frames, [1.0 MB-2.0 MB]: 18698 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]: 18767 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18762 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 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18768 frames
+      Peak usage frame count: [0-1.0 KB]: 18763 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]: 18768 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18763 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]: 18768 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18763 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 28.6 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":1753090120670,"processId":3420,"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":1753093376100,"processId":15501,"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": 0.6258723735809326,
-            "min": 0.6258723735809326,
-            "max": 1.493878722190857,
+            "value": 0.2890987992286682,
+            "min": 0.27647459506988525,
+            "max": 0.6194453239440918,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 18736.115234375,
-            "min": 18736.115234375,
-            "max": 45318.3046875,
+            "value": 8659.0869140625,
+            "min": 8219.037109375,
+            "max": 18583.359375,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 257.4909090909091,
+            "min": 241.78861788617886,
+            "max": 405.61538461538464,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 28324.0,
+            "min": 16056.0,
+            "max": 32783.0,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989951.0,
-            "min": 29952.0,
-            "max": 989951.0,
+            "value": 1979917.0,
+            "min": 1019944.0,
+            "max": 1979917.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989951.0,
-            "min": 29952.0,
-            "max": 989951.0,
+            "value": 1979917.0,
+            "min": 1019944.0,
+            "max": 1979917.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.3962373733520508,
-            "min": -0.17148473858833313,
-            "max": 0.49647629261016846,
+            "value": 0.7219787836074829,
+            "min": 0.4005979597568512,
+            "max": 0.7771360874176025,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 105.39913940429688,
-            "min": -40.641883850097656,
-            "max": 135.53802490234375,
+            "value": 207.9298858642578,
+            "min": 70.10464477539062,
+            "max": 231.5865478515625,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.012462032027542591,
-            "min": -0.04205678775906563,
-            "max": 0.17255885899066925,
+            "value": -0.001356392283923924,
+            "min": -0.058055855333805084,
+            "max": 0.040079277008771896,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 3.3149003982543945,
-            "min": -10.7665376663208,
-            "max": 44.38331604003906,
-            "count": 33
-        },
-        "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.07073828480982533,
-            "min": 0.06600874070136344,
-            "max": 0.07331723686752961,
-            "count": 33
-        },
-        "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9903359873375546,
-            "min": 0.4918467017310811,
-            "max": 1.0981092178844845,
+            "value": -0.3906409740447998,
+            "min": -10.159774780273438,
+            "max": 10.86148452758789,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.012875019058247698,
-            "min": 0.00020211451108625712,
-            "max": 0.015077118822955527,
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7246900772726215,
+            "min": 1.5020584418223455,
+            "max": 1.7582113700426691,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.18025026681546777,
-            "min": 0.0026274886441213425,
-            "max": 0.2261567823443329,
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 191.44059857726097,
+            "min": 64.26859942823648,
+            "max": 216.2599985152483,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.45734751425e-06,
-            "min": 7.45734751425e-06,
-            "max": 0.00029515063018788575,
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7246900772726215,
+            "min": 1.5020584418223455,
+            "max": 1.7582113700426691,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0001044028651995,
-            "min": 0.0001044028651995,
-            "max": 0.0033322638892454006,
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 191.44059857726097,
+            "min": 64.26859942823648,
+            "max": 216.2599985152483,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10248575,
-            "min": 0.10248575,
-            "max": 0.19838354285714285,
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.015308689450230796,
+            "min": 0.014581127780086429,
+            "max": 0.03442884677671827,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4348005,
-            "min": 1.3886848,
-            "max": 2.3843876,
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 1.6992645289756183,
+            "min": 1.4310290696739685,
+            "max": 2.7959636427112855,
             "count": 33
         },
-        "Pyramids.Policy.Beta.mean": {
-            "value": 0.00025832642500000006,
-            "min": 0.00025832642500000006,
-            "max": 0.00983851593142857,
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.0723181798887349,
+            "min": 0.06344992305301797,
+            "max": 0.07534196404380697,
             "count": 33
         },
-        "Pyramids.Policy.Beta.sum": {
-            "value": 0.003616569950000001,
-            "min": 0.003616569950000001,
-            "max": 0.11108438454,
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 1.0124545184422886,
+            "min": 0.6105756317071306,
+            "max": 1.0547874966132975,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.009103099815547466,
-            "min": 0.00905714649707079,
-            "max": 0.33082839846611023,
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.014281555990680678,
+            "min": 0.009865218712851249,
+            "max": 0.016138729900062994,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.12744340300559998,
-            "min": 0.1268000453710556,
-            "max": 2.315798759460449,
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.1999417838695295,
+            "min": 0.11269369220584242,
+            "max": 0.23955682700262496,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 452.6825396825397,
-            "min": 398.5,
-            "max": 999.0,
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 5.123509006482144e-06,
+            "min": 5.123509006482144e-06,
+            "max": 0.00014839028386992223,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 28519.0,
-            "min": 15984.0,
-            "max": 32678.0,
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 7.172912609075001e-05,
+            "min": 7.172912609075001e-05,
+            "max": 0.0020262253245917996,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.3567587023689633,
-            "min": -1.0000000521540642,
-            "max": 1.575567095451159,
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.1017078035714286,
+            "min": 0.1017078035714286,
+            "max": 0.14946341111111114,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 85.47579824924469,
-            "min": -30.99620160460472,
-            "max": 115.01639796793461,
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4239092500000003,
+            "min": 1.3451707000000002,
+            "max": 2.1337129999999997,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.3567587023689633,
-            "min": -1.0000000521540642,
-            "max": 1.575567095451159,
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.0001806095767857143,
+            "min": 0.0001806095767857143,
+            "max": 0.00495139477,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 85.47579824924469,
-            "min": -30.99620160460472,
-            "max": 115.01639796793461,
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0025285340750000004,
+            "min": 0.0025285340750000004,
+            "max": 0.06761327917999999,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.043027212541173435,
-            "min": 0.038817922278125576,
-            "max": 6.524227114394307,
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.0057084821164608,
+            "min": 0.0057084821164608,
+            "max": 0.00873806793242693,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 2.7107143900939263,
-            "min": 2.7107143900939263,
-            "max": 104.38763383030891,
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.0799187496304512,
+            "min": 0.07864261418581009,
+            "max": 0.11764119565486908,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +184,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1753088106",
+        "start_time_seconds": "1753091009",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.7.1+cu126",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1753090120"
+        "end_time_seconds": "1753093376"
     },
-    "total": 2014.395287059,
+    "total": 2366.2507866389997,
     "count": 1,
-    "self": 0.4928251620001447,
+    "self": 0.8770031709996147,
     "children": {
         "run_training.setup": {
-            "total": 0.0229950689999896,
+            "total": 0.02639951099990867,
             "count": 1,
-            "self": 0.0229950689999896
+            "self": 0.02639951099990867
         },
         "TrainerController.start_learning": {
-            "total": 2013.879466828,
+            "total": 2365.347383957,
             "count": 1,
-            "self": 1.1845215490063765,
+            "self": 1.1934797169806188,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.3944229109999924,
+                    "total": 2.717111567000302,
                     "count": 1,
-                    "self": 3.3944229109999924
+                    "self": 2.717111567000302
                 },
                 "TrainerController.advance": {
-                    "total": 2009.2212582349937,
-                    "count": 63464,
-                    "self": 1.3282216199995673,
+                    "total": 2361.3261606300193,
+                    "count": 65163,
+                    "self": 1.3624014600236478,
                     "children": {
                         "env_step": {
-                            "total": 1365.133349135988,
-                            "count": 63464,
-                            "self": 1224.3914712129558,
+                            "total": 1711.4332194609997,
+                            "count": 65163,
+                            "self": 1573.457499761866,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 140.0263466900052,
-                                    "count": 63464,
-                                    "self": 4.351994245987385,
+                                    "total": 137.24458744205276,
+                                    "count": 65163,
+                                    "self": 4.234710036889737,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 135.6743524440178,
-                                            "count": 62558,
-                                            "self": 135.6743524440178
+                                            "total": 133.00987740516302,
+                                            "count": 62541,
+                                            "self": 133.00987740516302
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7155312330269226,
-                                    "count": 63464,
+                                    "total": 0.7311322570808443,
+                                    "count": 65163,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2009.834524898007,
-                                            "count": 63464,
+                                            "total": 2360.3488373919376,
+                                            "count": 65163,
                                             "is_parallel": true,
-                                            "self": 888.4514993610253,
+                                            "self": 894.4140760919768,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0065317480000430805,
+                                                            "total": 0.0024430629996459174,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.005313931999921806,
+                                                            "self": 0.0007260339998538257,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0012178160001212746,
+                                                                    "total": 0.0017170289997920918,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0012178160001212746
+                                                                    "self": 0.0017170289997920918
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.07911459700005707,
+                                                            "total": 0.06627171300033297,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005785880000530597,
+                                                            "self": 0.0005250780004644184,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004726820000087173,
+                                                                    "total": 0.00043442600008347654,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004726820000087173
+                                                                    "self": 0.00043442600008347654
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.07652270799997041,
+                                                                    "total": 0.06376828800011936,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.07652270799997041
+                                                                    "self": 0.06376828800011936
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0015406190000248898,
+                                                                    "total": 0.0015439209996657155,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003182640000432002,
+                                                                    "self": 0.0003323669993733347,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0012223549999816896,
+                                                                            "total": 0.0012115540002923808,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0012223549999816896
+                                                                            "self": 0.0012115540002923808
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1121.3830255369817,
-                                                    "count": 63463,
+                                                    "total": 1465.9347612999609,
+                                                    "count": 65162,
                                                     "is_parallel": true,
-                                                    "self": 31.42306082900427,
+                                                    "self": 30.592568646956806,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 21.76974554394542,
-                                                            "count": 63463,
+                                                            "total": 21.612736951007264,
+                                                            "count": 65162,
                                                             "is_parallel": true,
-                                                            "self": 21.76974554394542
+                                                            "self": 21.612736951007264
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 977.756829051031,
-                                                            "count": 63463,
+                                                            "total": 1323.0864241190093,
+                                                            "count": 65162,
                                                             "is_parallel": true,
-                                                            "self": 977.756829051031
+                                                            "self": 1323.0864241190093
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 90.433390113001,
-                                                            "count": 63463,
+                                                            "total": 90.64303158298753,
+                                                            "count": 65162,
                                                             "is_parallel": true,
-                                                            "self": 17.490054715752876,
+                                                            "self": 17.69570631912211,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 72.94333539724812,
-                                                                    "count": 507704,
+                                                                    "total": 72.94732526386542,
+                                                                    "count": 521296,
                                                                     "is_parallel": true,
-                                                                    "self": 72.94333539724812
+                                                                    "self": 72.94732526386542
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 642.7596874790061,
-                            "count": 63464,
-                            "self": 2.1830072290449607,
+                            "total": 648.530539708996,
+                            "count": 65163,
+                            "self": 2.5051592239342426,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 118.35168604096339,
-                                    "count": 63464,
-                                    "self": 118.0542658789634,
+                                    "total": 125.09708008505959,
+                                    "count": 65163,
+                                    "self": 124.86934269105996,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.29742016199998034,
+                                            "total": 0.22773739399963233,
                                             "count": 2,
-                                            "self": 0.29742016199998034
+                                            "self": 0.22773739399963233
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 522.2249942089977,
-                                    "count": 448,
-                                    "self": 292.05658608699946,
+                                    "total": 520.9283004000022,
+                                    "count": 473,
+                                    "self": 290.31461967394443,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 230.16840812199825,
-                                            "count": 22758,
-                                            "self": 230.16840812199825
+                                            "total": 230.61368072605774,
+                                            "count": 22767,
+                                            "self": 230.61368072605774
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.920001164369751e-07,
+                    "total": 1.202000021294225e-06,
                     "count": 1,
-                    "self": 8.920001164369751e-07
+                    "self": 1.202000021294225e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.07926324099980775,
+                    "total": 0.11063084099987464,
                     "count": 1,
-                    "self": 0.0011627019998741162,
+                    "self": 0.002327762000277289,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.07810053899993363,
+                            "total": 0.10830307899959735,
                             "count": 1,
-                            "self": 0.07810053899993363
+                            "self": 0.10830307899959735
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499979,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499979.onnx",
-                "reward": 0.1994999684393406,
-                "creation_time": 1753089077.4553988,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499979.pt"
-                ]
-            },
-            {
-                "steps": 999948,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999948.onnx",
+                "steps": 1000204,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000204.onnx",
                 "reward": null,
-                "creation_time": 1753090120.115797,
+                "creation_time": 1753090120.216176,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999948.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000204.pt"
                 ]
             },
             {
                 "steps": 1000204,
                 "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000204.onnx",
                 "reward": null,
-                "creation_time": 1753090120.216176,
+                "creation_time": 1753090986.0941153,
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1000204.pt"
                 ]
+            },
+            {
+                "steps": 1499910,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499910.onnx",
+                "reward": 0.8047999739646912,
+                "creation_time": 1753092159.6534793,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499910.pt"
+                ]
+            },
+            {
+                "steps": 1999888,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999888.onnx",
+                "reward": 1.8024999722838402,
+                "creation_time": 1753093375.148163,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999888.pt"
+                ]
+            },
+            {
+                "steps": 2000016,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2000016.onnx",
+                "reward": 1.8024999722838402,
+                "creation_time": 1753093375.2740035,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2000016.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000204,
+            "steps": 2000016,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1753090120.216176,
+            "reward": 1.8024999722838402,
+            "creation_time": 1753093375.2740035,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000204.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-2000016.pt"
             ]
         }
     },