2nd Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca634e864a2e8641670abaf77782500418d71ad2d67326a5d29b39081fad0bc2
+oid sha256:2fb84aeb007a83c8565b91473e582eb6f43902f85583899f402b2c98ae7c0bfc
 size 1420238

Pyramids/Pyramids-1000073.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb84aeb007a83c8565b91473e582eb6f43902f85583899f402b2c98ae7c0bfc
+size 1420238

Pyramids/Pyramids-1000073.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a85aa946b6c54f83bcb839cc4a2b112f5427c537562e4983fed6b9c9977bf33f
+size 8656079

Pyramids/Pyramids-499899.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d49300e15891286c603bd9f83b6acfe73c4652899ca59e391414cbe562ecab7
+size 1420238

Pyramids/Pyramids-499899.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab51f29ae5e5ea7259f65384239a26c10fdaa57f5c7b058731bfb1975b4995f
+size 8656000

Pyramids/Pyramids-999945.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb84aeb007a83c8565b91473e582eb6f43902f85583899f402b2c98ae7c0bfc
+size 1420238

Pyramids/Pyramids-999945.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0410e3c9b65dac34628b9677a6cba72caf55546965a86b59e8fcd440a08b3a
+size 8656000

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0208c4c8ba09ad98fa3e41c581d8a379e29ca03ff2120b936e91d78391296d23
+oid sha256:1f0b70d730a59a02e1c2e17f361e41926c435c7d867b10a7efacd381844ad81a
 size 8655605

Pyramids/events.out.tfevents.1770600269.ea52937bc0e2.42230.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1887c1bd6d6e34004b36c41bbcc350012b823e40874c6909e670aa9afe546480
+size 239118

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": 300000, "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 1-", "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": 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 1-", "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: 300000
+    max_steps: 1000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -82,7 +82,7 @@ checkpoint_settings:
   run_id: Pyramids Training 1-
   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/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/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] 55267 [Flags] 2 [Guid] 967787953 [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] 55062 [Flags] 2 [Guid] 2883269053 [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/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  0.088 seconds
+- Completed reload, in  0.085 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: 0.934585 ms
+UnloadTime: 0.780464 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]: 4457 frames, [32.0 KB-64.0 KB]: 901 frames, [64.0 KB-128.0 KB]: 278 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3652 frames, [32.0 KB-64.0 KB]: 7568 frames, [64.0 KB-128.0 KB]: 1924 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
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 5338 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 215 frames, [1.0 MB-2.0 MB]: 12930 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.5 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12983
+  Peak main deferred allocation count 12227
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 5636 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 13144 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.9 MB
+      Peak Allocated memory 30.5 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5637 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 13145 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.3 MB
+      Peak Allocated memory 22.4 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5636 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13144 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]: 5637 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 13145 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,13 +272,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 5338 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 12846 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]: 5636 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 13144 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
@@ -293,19 +290,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5637 frames
+      Peak usage frame count: [0-1.0 KB]: 13145 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]: 5637 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 13145 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]: 5637 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 13145 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 27.4 KB
@@ -314,4 +311,4 @@ 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":1770599783667,"processId":37622,"allocatedMemory":1970103,"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":3417},{"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":1770601778136,"processId":42256,"allocatedMemory":1970103,"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":3417},{"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

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.654793918132782,
-            "min": 0.6478329300880432,
-            "max": 1.4048986434936523,
-            "count": 10
+            "value": 0.3744937777519226,
+            "min": 0.35644930601119995,
+            "max": 0.820889413356781,
+            "count": 23
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 19832.3984375,
-            "min": 19403.892578125,
-            "max": 42619.00390625,
-            "count": 10
+            "value": 11144.9345703125,
+            "min": 10716.2919921875,
+            "max": 24692.353515625,
+            "count": 23
         },
         "Pyramids.Step.mean": {
-            "value": 299994.0,
-            "min": 29952.0,
-            "max": 299994.0,
-            "count": 10
+            "value": 989886.0,
+            "min": 329889.0,
+            "max": 989886.0,
+            "count": 23
         },
         "Pyramids.Step.sum": {
-            "value": 299994.0,
-            "min": 29952.0,
-            "max": 299994.0,
-            "count": 10
+            "value": 989886.0,
+            "min": 329889.0,
+            "max": 989886.0,
+            "count": 23
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.04982955381274223,
-            "min": -0.10805169492959976,
-            "max": 0.058144956827163696,
-            "count": 10
+            "value": 0.39457809925079346,
+            "min": -0.08253936469554901,
+            "max": 0.39457809925079346,
+            "count": 23
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -12.008922576904297,
-            "min": -25.93240737915039,
-            "max": 13.780354499816895,
-            "count": 10
+            "value": 104.56319427490234,
+            "min": -19.891986846923828,
+            "max": 104.56319427490234,
+            "count": 23
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.04126422107219696,
-            "min": 0.04126422107219696,
-            "max": 0.30380281805992126,
-            "count": 10
+            "value": -0.025564437732100487,
+            "min": -0.025564437732100487,
+            "max": 0.04511326178908348,
+            "count": 23
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 9.944677352905273,
-            "min": 9.944677352905273,
-            "max": 72.91267395019531,
-            "count": 10
+            "value": -6.774576187133789,
+            "min": -6.774576187133789,
+            "max": 10.962522506713867,
+            "count": 23
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06866013502118318,
-            "min": 0.06700665638841614,
-            "max": 0.07165957830601818,
-            "count": 10
+            "value": 0.0674477375846845,
+            "min": 0.06511295669146681,
+            "max": 0.07281731183978819,
+            "count": 23
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.8925817552753813,
-            "min": 0.5016170481421273,
-            "max": 0.8925817552753813,
-            "count": 10
+            "value": 0.9442683261855831,
+            "min": 0.6630763047665358,
+            "max": 1.0399824782798532,
+            "count": 23
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0023572908855028674,
-            "min": 0.00011362052573243488,
-            "max": 0.009334010101711863,
-            "count": 10
+            "value": 0.012122288151514357,
+            "min": 0.0009611697074516269,
+            "max": 0.012610700131127875,
+            "count": 23
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.030644781511537277,
-            "min": 0.0013634463087892185,
-            "max": 0.06533807071198304,
-            "count": 10
+            "value": 0.169712034121201,
+            "min": 0.011534036489419523,
+            "max": 0.18405007849893687,
+            "count": 23
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 1.5968710061743588e-05,
-            "min": 1.5968710061743588e-05,
-            "max": 0.0002838354339596191,
-            "count": 10
+            "value": 7.556711766842858e-06,
+            "min": 7.556711766842858e-06,
+            "max": 0.00020492562169146999,
+            "count": 23
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00020759323080266664,
-            "min": 0.00020759323080266664,
-            "max": 0.0022984601338466664,
-            "count": 10
+            "value": 0.0001057939647358,
+            "min": 0.0001057939647358,
+            "max": 0.0024986396671203,
+            "count": 23
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10532287179487182,
-            "min": 0.10532287179487182,
-            "max": 0.19461180952380958,
-            "count": 10
+            "value": 0.10251887142857143,
+            "min": 0.10251887142857143,
+            "max": 0.16830852999999996,
+            "count": 23
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.3691973333333336,
-            "min": 1.362282666666667,
-            "max": 1.7546,
-            "count": 10
+            "value": 1.4352642,
+            "min": 1.4352642,
+            "max": 2.2328797,
+            "count": 23
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0005417548923076923,
-            "min": 0.0005417548923076923,
-            "max": 0.00946171977142857,
-            "count": 10
+            "value": 0.0002616352557142858,
+            "min": 0.0002616352557142858,
+            "max": 0.006834022147,
+            "count": 23
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0070428136,
-            "min": 0.0070428136,
-            "max": 0.07662871799999998,
-            "count": 10
+            "value": 0.003662893580000001,
+            "min": 0.003662893580000001,
+            "max": 0.08334468203,
+            "count": 23
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.03469758480787277,
-            "min": 0.03469758480787277,
-            "max": 0.473726749420166,
-            "count": 10
+            "value": 0.0110855083912611,
+            "min": 0.0110855083912611,
+            "max": 0.03396270051598549,
+            "count": 23
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.45106858015060425,
-            "min": 0.45106858015060425,
-            "max": 3.316087245941162,
-            "count": 10
+            "value": 0.1551971137523651,
+            "min": 0.1551971137523651,
+            "max": 0.39017587900161743,
+            "count": 23
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 988.09375,
-            "min": 903.125,
-            "max": 999.0,
-            "count": 10
+            "value": 485.6,
+            "min": 485.6,
+            "max": 980.25,
+            "count": 23
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31619.0,
-            "min": 15984.0,
-            "max": 32451.0,
-            "count": 10
+            "value": 31564.0,
+            "min": 18380.0,
+            "max": 32478.0,
+            "count": 23
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.7303613323357797,
-            "min": -1.0000000521540642,
-            "max": -0.40365005532900494,
-            "count": 10
+            "value": 1.2373753591225698,
+            "min": -0.85615005181171,
+            "max": 1.2724236981090853,
+            "count": 23
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -22.641201302409172,
-            "min": -31.999601677060127,
-            "max": -9.687601327896118,
-            "count": 10
+            "value": 80.42939834296703,
+            "min": -27.39680165797472,
+            "max": 80.42939834296703,
+            "count": 23
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.7303613323357797,
-            "min": -1.0000000521540642,
-            "max": -0.40365005532900494,
-            "count": 10
+            "value": 1.2373753591225698,
+            "min": -0.85615005181171,
+            "max": 1.2724236981090853,
+            "count": 23
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -22.641201302409172,
-            "min": -31.999601677060127,
-            "max": -9.687601327896118,
-            "count": 10
+            "value": 80.42939834296703,
+            "min": -27.39680165797472,
+            "max": 80.42939834296703,
+            "count": 23
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.3630878441636601,
-            "min": 0.3630878441636601,
-            "max": 9.068632766604424,
-            "count": 10
+            "value": 0.05634882780991925,
+            "min": 0.05634882780991925,
+            "max": 0.34386324157056053,
+            "count": 23
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 11.255723169073462,
-            "min": 9.356544498354197,
-            "max": 145.09812426567078,
-            "count": 10
+            "value": 3.662673807644751,
+            "min": 3.419767190818675,
+            "max": 10.351330703124404,
+            "count": 23
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 23
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 23
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1770599154",
+        "start_time_seconds": "1770600268",
         "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 1- --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 1- --no-graphics --resume",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1770599783"
+        "end_time_seconds": "1770601778"
     },
-    "total": 629.3117860390012,
+    "total": 1509.6666606159997,
     "count": 1,
-    "self": 0.8957872960017994,
+    "self": 0.8436420190009812,
     "children": {
         "run_training.setup": {
-            "total": 0.022585602999242838,
+            "total": 0.021299127000020235,
             "count": 1,
-            "self": 0.022585602999242838
+            "self": 0.021299127000020235
         },
         "TrainerController.start_learning": {
-            "total": 628.3934131400001,
+            "total": 1508.8017194699987,
             "count": 1,
-            "self": 0.42129503688192926,
+            "self": 0.927150354569676,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.0404642930006958,
+                    "total": 2.694056038000781,
                     "count": 1,
-                    "self": 2.0404642930006958
+                    "self": 2.694056038000781
                 },
                 "TrainerController.advance": {
-                    "total": 625.7709983601162,
-                    "count": 18850,
-                    "self": 0.4446266141385422,
+                    "total": 1505.0787303814304,
+                    "count": 44540,
+                    "self": 0.9622249445219495,
                     "children": {
                         "env_step": {
-                            "total": 431.01641104386545,
-                            "count": 18850,
-                            "self": 383.66166498779785,
+                            "total": 1048.9855434837518,
+                            "count": 44540,
+                            "self": 946.3716842257891,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 47.09538204103956,
-                                    "count": 18850,
-                                    "self": 1.453246123090139,
+                                    "total": 102.06356559412052,
+                                    "count": 44540,
+                                    "self": 3.202877071320472,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 45.64213591794942,
-                                            "count": 18789,
-                                            "self": 45.64213591794942
+                                            "total": 98.86068852280005,
+                                            "count": 43816,
+                                            "self": 98.86068852280005
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.25936401502804074,
-                                    "count": 18850,
+                                    "total": 0.5502936638422398,
+                                    "count": 44540,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 626.4255063059463,
-                                            "count": 18850,
+                                            "total": 1504.2441182311068,
+                                            "count": 44540,
                                             "is_parallel": true,
-                                            "self": 278.92514598896923,
+                                            "self": 637.4337421761938,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0019073889998253435,
+                                                            "total": 0.002456062000419479,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006447529976867372,
+                                                            "self": 0.0006841460017312784,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0012626360021386063,
+                                                                    "total": 0.0017719159986882005,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0012626360021386063
+                                                                    "self": 0.0017719159986882005
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.048906072001045686,
+                                                            "total": 0.09175023499847157,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005397179993451573,
+                                                            "self": 0.0005729769982281141,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.000507906001075753,
+                                                                    "total": 0.0004338199996709591,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000507906001075753
+                                                                    "self": 0.0004338199996709591
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04603685100119037,
+                                                                    "total": 0.08707945599962841,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04603685100119037
+                                                                    "self": 0.08707945599962841
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001821596999434405,
+                                                                    "total": 0.003663982000944088,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004129350036237156,
+                                                                    "self": 0.00034964199767273385,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014086619958106894,
+                                                                            "total": 0.0033143400032713544,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014086619958106894
+                                                                            "self": 0.0033143400032713544
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 347.5003603169771,
-                                                    "count": 18849,
+                                                    "total": 866.8103760549129,
+                                                    "count": 44539,
                                                     "is_parallel": true,
-                                                    "self": 10.167513736814726,
+                                                    "self": 23.335727580564708,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 7.200146758066694,
-                                                            "count": 18849,
+                                                            "total": 16.370495459745143,
+                                                            "count": 44539,
                                                             "is_parallel": true,
-                                                            "self": 7.200146758066694
+                                                            "self": 16.370495459745143
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 296.8633793310273,
-                                                            "count": 18849,
+                                                            "total": 752.8083490887766,
+                                                            "count": 44539,
                                                             "is_parallel": true,
-                                                            "self": 296.8633793310273
+                                                            "self": 752.8083490887766
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 33.269320491068356,
-                                                            "count": 18849,
+                                                            "total": 74.29580392582648,
+                                                            "count": 44539,
                                                             "is_parallel": true,
-                                                            "self": 7.050377170018692,
+                                                            "self": 15.610935690858241,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 26.218943321049665,
-                                                                    "count": 150792,
+                                                                    "total": 58.684868234968235,
+                                                                    "count": 356312,
                                                                     "is_parallel": true,
-                                                                    "self": 26.218943321049665
+                                                                    "self": 58.684868234968235
                                                                 }
                                                             }
                                                         }
@@ -343,24 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 194.30996070211222,
-                            "count": 18850,
-                            "self": 0.6400671890260128,
+                            "total": 455.13096195315666,
+                            "count": 44540,
+                            "self": 1.8208620301757037,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 36.28984809607391,
-                                    "count": 18850,
-                                    "self": 36.28984809607391
+                                    "total": 86.41271897398292,
+                                    "count": 44540,
+                                    "self": 86.15479847298229,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.25792050100062625,
+                                            "count": 2,
+                                            "self": 0.25792050100062625
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 157.3800454170123,
-                                    "count": 110,
-                                    "self": 88.77259325694104,
+                                    "total": 366.89738094899803,
+                                    "count": 322,
+                                    "self": 202.94853052493454,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 68.60745216007126,
-                                            "count": 6861,
-                                            "self": 68.60745216007126
+                                            "total": 163.9488504240635,
+                                            "count": 15933,
+                                            "self": 163.9488504240635
                                         }
                                     }
                                 }
@@ -369,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.3389999367063865e-06,
+                    "total": 1.1699994502123445e-06,
                     "count": 1,
-                    "self": 1.3389999367063865e-06
+                    "self": 1.1699994502123445e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.16065411100134952,
+                    "total": 0.10178152599837631,
                     "count": 1,
-                    "self": 0.0012746970023727044,
+                    "self": 0.0024809429996821564,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.15937941399897682,
+                            "total": 0.09930058299869415,
                             "count": 1,
-                            "self": 0.15937941399897682
+                            "self": 0.09930058299869415
                         }
                     }
                 }

run_logs/training_status.json

@@ -9,15 +9,42 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training 1-/Pyramids/Pyramids-300098.pt"
                 ]
+            },
+            {
+                "steps": 499899,
+                "file_path": "results/Pyramids Training 1-/Pyramids/Pyramids-499899.onnx",
+                "reward": 0.2573999688029289,
+                "creation_time": 1770600687.1444545,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training 1-/Pyramids/Pyramids-499899.pt"
+                ]
+            },
+            {
+                "steps": 999945,
+                "file_path": "results/Pyramids Training 1-/Pyramids/Pyramids-999945.onnx",
+                "reward": 1.5789999812841415,
+                "creation_time": 1770601777.2512383,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training 1-/Pyramids/Pyramids-999945.pt"
+                ]
+            },
+            {
+                "steps": 1000073,
+                "file_path": "results/Pyramids Training 1-/Pyramids/Pyramids-1000073.onnx",
+                "reward": 1.5789999812841415,
+                "creation_time": 1770601777.3673873,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training 1-/Pyramids/Pyramids-1000073.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 300098,
+            "steps": 1000073,
             "file_path": "results/Pyramids Training 1-/Pyramids.onnx",
-            "reward": -0.9993000477552414,
-            "creation_time": 1770599782.8331976,
+            "reward": 1.5789999812841415,
+            "creation_time": 1770601777.3673873,
             "auxillary_file_paths": [
-                "results/Pyramids Training 1-/Pyramids/Pyramids-300098.pt"
+                "results/Pyramids Training 1-/Pyramids/Pyramids-1000073.pt"
             ]
         }
     },