First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5657dd11d793be8f08ad03849786bcb661d537afa0e77c9a22d1817b0732457e
+oid sha256:953a62e094e1e902018efdd58ab6b6c34a557fd84d3174f25e4dedf94b652629
 size 1420238

Pyramids/Pyramids-1499998.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:633dbe0af378c5c952a70c344e685c155afb9d48814d251b9d7d51e8c0ca45fc
+size 1420238

Pyramids/Pyramids-1499998.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53251e25195452e5689d4fff5738b1793a4a6b8910e934a080c0e956dbe87edb
+size 8656252

Pyramids/Pyramids-1999875.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89455a384a69d6a6fbbea18a85c3067564b4efc76f0c6adcee1102de7397847
+size 1420238

Pyramids/Pyramids-1999875.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b1216f7d8aeecd290bc0c24945c20bba55849d775fa02124165db30efd06a3
+size 8656252

Pyramids/Pyramids-2499905.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:340c7d1d7cdc5ef8bd1b70686286ff4ebcdf6ad0c8ab4950de411d3870db5a0c
+size 1420238

Pyramids/Pyramids-2499905.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e7275a7ba5f6c532754ecdcb335584ab0b4ec7cb838cbd564ff1738357df966
+size 8656252

Pyramids/Pyramids-2999900.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953a62e094e1e902018efdd58ab6b6c34a557fd84d3174f25e4dedf94b652629
+size 1420238

Pyramids/Pyramids-2999900.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b8b9b95945e614ccc6303701e92193bc325283ad9efb57032776e0b768c319e
+size 8656252

Pyramids/Pyramids-3000028.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953a62e094e1e902018efdd58ab6b6c34a557fd84d3174f25e4dedf94b652629
+size 1420238

Pyramids/Pyramids-3000028.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d92f410833e31711d3d9b6f5da80e75d26179b2122fb6945d9dcd1208d68d0
+size 8656252

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7af7a45070c39613dd3f972e0678c100414711c7ae9267afc083eb3675c60f49
+oid sha256:1207fcd358f85054efb840a804fb362854c8dd87a3f442eb03fa8740c26e87e9
 size 8655778

Pyramids/events.out.tfevents.1698957741.754d5c06d734.10747.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8493206ab6af12fc6b4a36157504ac84a2818b78627f792541111eadbc2edf55
+size 620828

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}, "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": 3000000, "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}, "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: 3000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -81,7 +81,7 @@ 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] 55002 [Flags] 2 [Guid] 3492285433 [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] 55155 [Flags] 2 [Guid] 4223520717 [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  0.086 seconds
+- Completed reload, in  0.083 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -68,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.771309 ms
+UnloadTime: 0.768611 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 4 worker threads for Enlighten.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 2418 frames, [32.0 KB-64.0 KB]: 13653 frames, [64.0 KB-128.0 KB]: 2697 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 610 frames, [32.0 KB-64.0 KB]: 25047 frames, [64.0 KB-128.0 KB]: 11857 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
@@ -131,7 +128,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -141,7 +138,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -189,7 +186,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 2]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
@@ -206,24 +203,19 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 0]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
     [ALLOC_TEMP_Job.Worker 5]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_EnlightenWorker] x 4
@@ -231,34 +223,39 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       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]: 18470 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 59 frames, [1.0 MB-2.0 MB]: 37456 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 11447
+  Peak main deferred allocation count 1806
     [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]: 18768 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37514 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 30.3 MB
+      Peak Block count 2
+      Peak Allocated memory 24.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37515 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 25.9 MB
+      Peak Allocated memory 23.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -285,15 +282,15 @@ 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]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37514 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]: 18769 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 37515 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -303,15 +300,15 @@ 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]: 18470 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 71 frames, [1.0 MB-2.0 MB]: 37444 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]: 18768 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 37514 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
@@ -321,21 +318,21 @@ 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]: 18769 frames
+      Peak usage frame count: [0-1.0 KB]: 37515 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]: 18769 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37515 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]: 18769 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 37515 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 31.4 KB
@@ -344,4 +341,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1698957682624,"processId":4279,"allocatedMemory":1976109,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34628},{"Manager":13963},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":3808},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1698960820128,"processId":10784,"allocatedMemory":1976109,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34628},{"Manager":13963},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":3808},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.537469208240509,
-            "min": 0.537469208240509,
-            "max": 1.4602720737457275,
-            "count": 33
+            "value": 0.16631320118904114,
+            "min": 0.15615378320217133,
+            "max": 0.5242581367492676,
+            "count": 67
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 16081.078125,
-            "min": 16081.078125,
-            "max": 44298.8125,
-            "count": 33
+            "value": 4960.125,
+            "min": 4648.802734375,
+            "max": 15685.8037109375,
+            "count": 67
         },
         "Pyramids.Step.mean": {
-            "value": 989939.0,
-            "min": 29952.0,
-            "max": 989939.0,
-            "count": 33
+            "value": 2999900.0,
+            "min": 1019969.0,
+            "max": 2999900.0,
+            "count": 67
         },
         "Pyramids.Step.sum": {
-            "value": 989939.0,
-            "min": 29952.0,
-            "max": 989939.0,
-            "count": 33
+            "value": 2999900.0,
+            "min": 1019969.0,
+            "max": 2999900.0,
+            "count": 67
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.5477339625358582,
-            "min": -0.1155085414648056,
-            "max": 0.5477339625358582,
-            "count": 33
+            "value": 0.7526808977127075,
+            "min": 0.3403772711753845,
+            "max": 0.8132508993148804,
+            "count": 67
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 152.81777954101562,
-            "min": -27.953067779541016,
-            "max": 152.81777954101562,
-            "count": 33
+            "value": 222.04086303710938,
+            "min": 88.83847045898438,
+            "max": 243.16201782226562,
+            "count": 67
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.007286582607775927,
-            "min": -0.03917496278882027,
-            "max": 0.2708534896373749,
-            "count": 33
+            "value": -0.015379424206912518,
+            "min": -0.01909688487648964,
+            "max": 0.06433786451816559,
+            "count": 67
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 2.032956600189209,
-            "min": -10.381364822387695,
-            "max": 65.54654693603516,
-            "count": 33
+            "value": -4.536930084228516,
+            "min": -4.536930084228516,
+            "max": 17.37122344970703,
+            "count": 67
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 267.4188034188034,
+            "min": 219.87596899224806,
+            "max": 531.948275862069,
+            "count": 67
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 31288.0,
+            "min": 18218.0,
+            "max": 32184.0,
+            "count": 67
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7154820268480186,
+            "min": 1.1231103220890308,
+            "max": 1.7808692251260465,
+            "count": 67
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 200.71139714121819,
+            "min": 65.14039868116379,
+            "max": 231.7359987795353,
+            "count": 67
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7154820268480186,
+            "min": 1.1231103220890308,
+            "max": 1.7808692251260465,
+            "count": 67
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 200.71139714121819,
+            "min": 65.14039868116379,
+            "max": 231.7359987795353,
+            "count": 67
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.01874066329833307,
+            "min": 0.01625763152926363,
+            "max": 0.051344343154000695,
+            "count": 67
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.1926576059049694,
+            "min": 1.8848839916317957,
+            "max": 3.2472658004262485,
+            "count": 67
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06870663790600484,
-            "min": 0.06585085634448688,
-            "max": 0.07362447643685692,
-            "count": 33
+            "value": 0.07115753559905678,
+            "min": 0.06439512960310485,
+            "max": 0.07460549737852826,
+            "count": 67
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9618929306840678,
-            "min": 0.511078340184725,
-            "max": 1.0547077266268852,
-            "count": 33
+            "value": 0.9962054983867951,
+            "min": 0.6714494764067543,
+            "max": 1.0704061636865578,
+            "count": 67
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01502501104481607,
-            "min": 0.0006209250926686348,
-            "max": 0.01502501104481607,
-            "count": 33
+            "value": 0.0143861130879183,
+            "min": 0.010200310676979523,
+            "max": 0.01712145668058102,
+            "count": 67
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.21035015462742498,
-            "min": 0.008692951297360888,
-            "max": 0.21035015462742498,
-            "count": 33
+            "value": 0.2014055832308562,
+            "min": 0.11399055966709662,
+            "max": 0.2409040310788744,
+            "count": 67
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.384747538450001e-06,
-            "min": 7.384747538450001e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 1.4785280786190503e-06,
+            "min": 1.4785280786190503e-06,
+            "max": 0.00019894532257379261,
+            "count": 67
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010338646553830001,
-            "min": 0.00010338646553830001,
-            "max": 0.0036332071889310005,
-            "count": 33
+            "value": 2.0699393100666706e-05,
+            "min": 2.0699393100666706e-05,
+            "max": 0.00281256056248,
+            "count": 67
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10246155000000001,
-            "min": 0.10246155000000001,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.1004928095238095,
+            "min": 0.1004928095238095,
+            "max": 0.16631509629629632,
+            "count": 67
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4344617000000002,
-            "min": 1.3886848,
-            "max": 2.6110689999999996,
-            "count": 33
+            "value": 1.406899333333333,
+            "min": 1.406899333333333,
+            "max": 2.4375199999999997,
+            "count": 67
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00025590884500000015,
-            "min": 0.00025590884500000015,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 5.9231671428571524e-05,
+            "min": 5.9231671428571524e-05,
+            "max": 0.00663487812,
+            "count": 67
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0035827238300000022,
-            "min": 0.0035827238300000022,
-            "max": 0.1211257931,
-            "count": 33
+            "value": 0.0008292434000000013,
+            "min": 0.0008292434000000013,
+            "max": 0.093808248,
+            "count": 67
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.011887529864907265,
-            "min": 0.01175712700933218,
-            "max": 0.40382641553878784,
-            "count": 33
+            "value": 0.006910291966050863,
+            "min": 0.006267464254051447,
+            "max": 0.01137463003396988,
+            "count": 67
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.166425421833992,
-            "min": 0.16459977626800537,
-            "max": 2.82678484916687,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 343.22222222222223,
-            "min": 343.22222222222223,
-            "max": 999.0,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30890.0,
-            "min": 15984.0,
-            "max": 32989.0,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.5355888722671402,
-            "min": -1.0000000521540642,
-            "max": 1.5395487013917704,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 138.20299850404263,
-            "min": -28.197001732885838,
-            "max": 138.20299850404263,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.5355888722671402,
-            "min": -1.0000000521540642,
-            "max": 1.5395487013917704,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 138.20299850404263,
-            "min": -28.197001732885838,
-            "max": 138.20299850404263,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.04327827774638233,
-            "min": 0.04327827774638233,
-            "max": 7.453175722621381,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 3.895044997174409,
-            "min": 3.4759267813933548,
-            "max": 119.2508115619421,
-            "count": 33
+            "value": 0.09674409031867981,
+            "min": 0.08774449676275253,
+            "max": 0.15356534719467163,
+            "count": 67
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 67
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 67
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1698956229",
+        "start_time_seconds": "1698957740",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.1.0+cu118",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1698957682"
+        "end_time_seconds": "1698960820"
     },
-    "total": 1453.056970418,
+    "total": 3079.4064024080003,
     "count": 1,
-    "self": 0.371980210999709,
+    "self": 0.32205639800076824,
     "children": {
         "run_training.setup": {
-            "total": 0.04032402200004981,
+            "total": 0.043957591999969736,
             "count": 1,
-            "self": 0.04032402200004981
+            "self": 0.043957591999969736
         },
         "TrainerController.start_learning": {
-            "total": 1452.6446661850002,
+            "total": 3079.0403884179996,
             "count": 1,
-            "self": 1.0569437970113995,
+            "self": 2.1447504499651586,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.385779236000076,
+                    "total": 3.3851331480000226,
                     "count": 1,
-                    "self": 3.385779236000076
+                    "self": 3.3851331480000226
                 },
                 "TrainerController.advance": {
-                    "total": 1448.1311863409892,
-                    "count": 63634,
-                    "self": 1.0902291411184706,
+                    "total": 3073.441244140034,
+                    "count": 130477,
+                    "self": 2.250978221929472,
                     "children": {
                         "env_step": {
-                            "total": 935.0803603578981,
-                            "count": 63634,
-                            "self": 829.4690710919295,
+                            "total": 2037.8935502071477,
+                            "count": 130477,
+                            "self": 1827.5517615943077,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 104.96687454795483,
-                                    "count": 63634,
-                                    "self": 3.8377414529923044,
+                                    "total": 209.03697606190553,
+                                    "count": 130477,
+                                    "self": 7.80014143979497,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 101.12913309496253,
-                                            "count": 62561,
-                                            "self": 101.12913309496253
+                                            "total": 201.23683462211056,
+                                            "count": 125048,
+                                            "self": 201.23683462211056
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.6444147180137634,
-                                    "count": 63634,
+                                    "total": 1.3048125509344572,
+                                    "count": 130477,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1450.8360712980016,
-                                            "count": 63634,
+                                            "total": 3075.507062067016,
+                                            "count": 130477,
                                             "is_parallel": true,
-                                            "self": 702.0642350619721,
+                                            "self": 1409.19582373993,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0018041579999135138,
+                                                            "total": 0.0017288639996877464,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005561049997595546,
+                                                            "self": 0.0005731000001105713,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0012480530001539591,
+                                                                    "total": 0.0011557639995771751,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0012480530001539591
+                                                                    "self": 0.0011557639995771751
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03364381200003663,
+                                                            "total": 0.035860842000147386,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00033310100013750343,
+                                                            "self": 0.0003879749992847792,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0002834050000046773,
+                                                                    "total": 0.0003228530003980268,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002834050000046773
+                                                                    "self": 0.0003228530003980268
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03195716999994147,
+                                                                    "total": 0.03405229000009058,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03195716999994147
+                                                                    "self": 0.03405229000009058
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0010701359999529814,
+                                                                    "total": 0.0010977240003740008,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002338089998374926,
+                                                                    "self": 0.0002821739994942618,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0008363270001154888,
+                                                                            "total": 0.0008155500008797389,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0008363270001154888
+                                                                            "self": 0.0008155500008797389
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 748.7718362360295,
-                                                    "count": 63633,
+                                                    "total": 1666.311238327086,
+                                                    "count": 130476,
                                                     "is_parallel": true,
-                                                    "self": 19.895991991093297,
+                                                    "self": 39.75793157228463,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 13.851949299016155,
-                                                            "count": 63633,
+                                                            "total": 27.65938782695821,
+                                                            "count": 130476,
                                                             "is_parallel": true,
-                                                            "self": 13.851949299016155
+                                                            "self": 27.65938782695821
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 658.4641740669387,
-                                                            "count": 63633,
+                                                            "total": 1485.3678151138424,
+                                                            "count": 130476,
                                                             "is_parallel": true,
-                                                            "self": 658.4641740669387
+                                                            "self": 1485.3678151138424
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 56.55972087898135,
-                                                            "count": 63633,
+                                                            "total": 113.52610381400063,
+                                                            "count": 130476,
                                                             "is_parallel": true,
-                                                            "self": 11.945073903034427,
+                                                            "self": 24.249074466750244,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 44.614646975946926,
-                                                                    "count": 509064,
+                                                                    "total": 89.27702934725039,
+                                                                    "count": 1043808,
                                                                     "is_parallel": true,
-                                                                    "self": 44.614646975946926
+                                                                    "self": 89.27702934725039
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 511.9605968419727,
-                            "count": 63634,
-                            "self": 2.0591762999576986,
+                            "total": 1033.296715710957,
+                            "count": 130477,
+                            "self": 4.452361167000618,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 97.112013756014,
-                                    "count": 63634,
-                                    "self": 96.94710044301405,
+                                    "total": 201.96153584894728,
+                                    "count": 130477,
+                                    "self": 201.66451809094724,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.16491331299994272,
-                                            "count": 2,
-                                            "self": 0.16491331299994272
+                                            "total": 0.29701775800003816,
+                                            "count": 4,
+                                            "self": 0.29701775800003816
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 412.789406786001,
-                                    "count": 453,
-                                    "self": 239.33156542198867,
+                                    "total": 826.8828186950091,
+                                    "count": 946,
+                                    "self": 482.3568385889894,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 173.45784136401232,
-                                            "count": 22809,
-                                            "self": 173.45784136401232
+                                            "total": 344.5259801060197,
+                                            "count": 45510,
+                                            "self": 344.5259801060197
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.869997145666275e-07,
+                    "total": 9.90999978967011e-07,
                     "count": 1,
-                    "self": 8.869997145666275e-07
+                    "self": 9.90999978967011e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.07075592399996822,
+                    "total": 0.06925968900031876,
                     "count": 1,
-                    "self": 0.0013630660000671924,
+                    "self": 0.0016841140004544286,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.06939285799990103,
+                            "total": 0.06757557499986433,
                             "count": 1,
-                            "self": 0.06939285799990103
+                            "self": 0.06757557499986433
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499888,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499888.onnx",
-                "reward": 0.6943332875768343,
-                "creation_time": 1698956934.7475002,
+                "steps": 1499998,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499998.onnx",
+                "reward": 1.6803333436449368,
+                "creation_time": 1698958504.7193198,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499888.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1499998.pt"
                 ]
             },
             {
-                "steps": 999927,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999927.onnx",
-                "reward": 1.6359999477863312,
-                "creation_time": 1698957682.2328188,
+                "steps": 1999875,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999875.onnx",
+                "reward": null,
+                "creation_time": 1698959271.720239,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999927.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1999875.pt"
                 ]
             },
             {
-                "steps": 1000010,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000010.onnx",
-                "reward": 1.7129999622702599,
-                "creation_time": 1698957682.3119304,
+                "steps": 2499905,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499905.onnx",
+                "reward": 1.809999977548917,
+                "creation_time": 1698960043.6205704,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000010.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2499905.pt"
+                ]
+            },
+            {
+                "steps": 2999900,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999900.onnx",
+                "reward": 1.542999970416228,
+                "creation_time": 1698960819.7643135,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2999900.pt"
+                ]
+            },
+            {
+                "steps": 3000028,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000028.onnx",
+                "reward": 1.542999970416228,
+                "creation_time": 1698960819.8425608,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-3000028.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000010,
+            "steps": 3000028,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.7129999622702599,
-            "creation_time": 1698957682.3119304,
+            "reward": 1.542999970416228,
+            "creation_time": 1698960819.8425608,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000010.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-3000028.pt"
             ]
         }
     },