PyramidsRND first try

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:406304e16eb0a116f8c92846680d2b923eb98a436d6f543eac3b905617557e41
+oid sha256:c7dfb7bcf3edda72681b3e8cd38cd2c6d7f236ed930720e861ad603ab26534fd
 size 1420238

Pyramids/Pyramids-1200099.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ac4c630ea82ec41709c690665f0ddac854e3e631e5c82c2c07bf3bd4ca9f19
+size 1420238

Pyramids/Pyramids-1200099.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5236243d997a33512e0063ccc2a5ec48c220a24a0bc0914542956691d1122d2f
+size 8655643

Pyramids/Pyramids-1499949.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403d87233a42e86c1a101ef415734be8fd78a7dea28e0408543c481fbba916cd
+size 1420238

Pyramids/Pyramids-1499949.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca75238e3ed7a7fc2473ecea8a18a34937fa90085ed08e4d0c0d667e085c9025
+size 8655643

Pyramids/Pyramids-1600001.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7dfb7bcf3edda72681b3e8cd38cd2c6d7f236ed930720e861ad603ab26534fd
+size 1420238

Pyramids/Pyramids-1600001.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e1473386dcfd95bfd7964d9ee7ebe9ed9eb542007c7782718d488deb5667e8
+size 8655643

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706c5309eca79833625b708578d84356b701bee4f1b86249b2c34a82f0a9febd
+oid sha256:4aef08157bf16d894201c9f8bf14f776533149d9a9139189304ff8ced7041415
 size 8655157

Pyramids/events.out.tfevents.1750181762.5a4b92ec8867.23180.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbd70e5f94b57586e31c2395c44e89215cec08f09be6c1f58349cddf61f9938
+size 73854

Pyramids/events.out.tfevents.1750182616.5a4b92ec8867.26647.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a405d8dee17a9d7c6f341a1dce6b3f3e935ecba70bb8a09160f879a76895c64a
+size 135908

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "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": 1600000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 1600000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 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] 55024 [Flags] 2 [Guid] 702607789 [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] 55439 [Flags] 2 [Guid] 2158576320 [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'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,7 +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  0.241 seconds
+- Completed reload, in  0.118 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)
@@ -65,17 +65,15 @@ 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: 5.579863 ms
+UnloadTime: 1.558025 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.
-abort_threads: Failed aborting id: 0x7c73f2bfb640, mono_thread_manage will ignore it
-
 PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 12 frames, [32.0 KB-64.0 KB]: 5230 frames, [64.0 KB-128.0 KB]: 2272 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
@@ -206,28 +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]: 1 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 77 frames, [1.0 MB-2.0 MB]: 7438 frames
   Requested Block Size 1.0 MB
-  Peak Block count 1
-  Peak Allocated memory 0.9 MB
+  Peak Block count 2
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 9990
+  Peak main deferred allocation count 11320
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.2 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 7514 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 14.1 MB
+      Peak Block count 2
+      Peak Allocated memory 23.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 7515 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 18.1 MB
+      Peak Allocated memory 22.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -241,7 +239,7 @@ PlayerConnection::CleanupMemory Statistics:
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
   Initial Block Size 2.0 MB
-  Used Block Count 1
+  Used Block Count 2
   Overflow Count (too large) 0
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -254,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.2 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 7514 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]: 1 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 7515 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,45 +270,45 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.2 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 88 frames, [1.0 MB-2.0 MB]: 7427 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.9 MB
+      Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 7514 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 3.9 MB
+      Peak Block count 2
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.2 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1 frames
+      Peak usage frame count: [0-1.0 KB]: 7515 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]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 7515 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]: 1 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 7515 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 27.4 KB
+  Peak Allocated memory 29.2 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1750181691395,"processId":22847,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1750184077632,"processId":26670,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -1,8 +1,190 @@
 {
     "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.46655145287513733,
+            "min": 0.4543718099594116,
+            "max": 0.5169422030448914,
+            "count": 13
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 13989.0791015625,
+            "min": 13529.375,
+            "max": 15318.03125,
+            "count": 13
+        },
+        "Pyramids.Step.mean": {
+            "value": 1589898.0,
+            "min": 1229962.0,
+            "max": 1589898.0,
+            "count": 13
+        },
+        "Pyramids.Step.sum": {
+            "value": 1589898.0,
+            "min": 1229962.0,
+            "max": 1589898.0,
+            "count": 13
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.3393390476703644,
+            "min": 0.1938980519771576,
+            "max": 0.3393390476703644,
+            "count": 13
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 89.24617004394531,
+            "min": 49.25010681152344,
+            "max": 89.24617004394531,
+            "count": 13
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 9.462202072143555,
+            "min": 8.912569046020508,
+            "max": 18.159835815429688,
+            "count": 13
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 2488.55908203125,
+            "min": 2335.093017578125,
+            "max": 4739.71728515625,
+            "count": 13
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 489.4375,
+            "min": 436.26785714285717,
+            "max": 678.8723404255319,
+            "count": 13
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 31324.0,
+            "min": 24431.0,
+            "max": 32105.0,
+            "count": 13
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.2646126727026605,
+            "min": 0.554914856210668,
+            "max": 1.4208178309989827,
+            "count": 13
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 79.67059838026762,
+            "min": 26.080998241901398,
+            "max": 79.67059838026762,
+            "count": 13
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.2646126727026605,
+            "min": 0.554914856210668,
+            "max": 1.4208178309989827,
+            "count": 13
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 79.67059838026762,
+            "min": 26.080998241901398,
+            "max": 79.67059838026762,
+            "count": 13
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.0364661766160723,
+            "min": 0.0364661766160723,
+            "max": 0.07318291784279009,
+            "count": 13
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.297369126812555,
+            "min": 2.137254884570666,
+            "max": 3.439597138611134,
+            "count": 13
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06579424443415996,
+            "min": 0.06579424443415996,
+            "max": 0.07123254773753053,
+            "count": 13
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9211194220782394,
+            "min": 0.9211194220782394,
+            "max": 1.0418033949584544,
+            "count": 13
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 9.290047738257616,
+            "min": 9.28028309158459,
+            "max": 41.81478864327073,
+            "count": 13
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 130.06066833560664,
+            "min": 129.92396328218425,
+            "max": 585.4070410057902,
+            "count": 13
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 4.629741313928572e-06,
+            "min": 4.629741313928572e-06,
+            "max": 7.203146884667855e-05,
+            "count": 13
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 6.481637839500001e-05,
+            "min": 6.481637839500001e-05,
+            "max": 0.0010084405638534997,
+            "count": 13
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.1015432142857143,
+            "min": 0.1015432142857143,
+            "max": 0.1240104642857143,
+            "count": 13
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4216050000000002,
+            "min": 1.4216050000000002,
+            "max": 1.7361465000000003,
+            "count": 13
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00016416710714285722,
+            "min": 0.00016416710714285722,
+            "max": 0.002408645382142857,
+            "count": 13
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.002298339500000001,
+            "min": 0.002298339500000001,
+            "max": 0.03372103535,
+            "count": 13
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.00714080547913909,
+            "min": 0.007051652763038874,
+            "max": 0.010782291181385517,
+            "count": 13
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.09997127950191498,
+            "min": 0.09872313588857651,
+            "max": 0.1509520709514618,
+            "count": 13
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 13
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 13
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1750181684",
+        "start_time_seconds": "1750182615",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "1.2.0.dev0",
@@ -10,41 +192,203 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.7.1+cu126",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1750181691"
+        "end_time_seconds": "1750184077"
     },
-    "total": 6.590542244000062,
+    "total": 1461.9023671020004,
     "count": 1,
-    "self": 1.5319512850001047,
+    "self": 0.6293885169998248,
     "children": {
         "run_training.setup": {
-            "total": 0.0439647530001821,
+            "total": 0.02867036400039069,
             "count": 1,
-            "self": 0.0439647530001821
+            "self": 0.02867036400039069
         },
         "TrainerController.start_learning": {
-            "total": 5.014626205999775,
+            "total": 1461.2443082210002,
             "count": 1,
-            "self": 0.00040185500074585434,
+            "self": 1.119093739008349,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.643859316000089,
+                    "total": 3.476560967000296,
                     "count": 1,
-                    "self": 4.643859316000089
+                    "self": 3.476560967000296
+                },
+                "TrainerController.advance": {
+                    "total": 1456.5675661149917,
+                    "count": 25604,
+                    "self": 1.1881691179823974,
+                    "children": {
+                        "env_step": {
+                            "total": 1002.010742176064,
+                            "count": 25604,
+                            "self": 929.6181848720043,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 71.73163796901736,
+                                    "count": 25604,
+                                    "self": 3.546071992996076,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 68.18556597602128,
+                                            "count": 25050,
+                                            "self": 68.18556597602128
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.6609193350423084,
+                                    "count": 25604,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1457.1067589910745,
+                                            "count": 25604,
+                                            "is_parallel": true,
+                                            "self": 611.0327728740058,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0028622559993891628,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0011329169983582688,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.001729339001030894,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.001729339001030894
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.16418239399990853,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007876739991843351,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0006024300000717631,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0006024300000717631
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.15549212699988857,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.15549212699988857
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.00730016300076386,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.005706316000214429,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001593847000549431,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001593847000549431
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 846.0739861170687,
+                                                    "count": 25603,
+                                                    "is_parallel": true,
+                                                    "self": 19.921130432023347,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 13.73654646396335,
+                                                            "count": 25603,
+                                                            "is_parallel": true,
+                                                            "self": 13.73654646396335
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 756.7903139829805,
+                                                            "count": 25603,
+                                                            "is_parallel": true,
+                                                            "self": 756.7903139829805
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 55.625995238101495,
+                                                            "count": 25603,
+                                                            "is_parallel": true,
+                                                            "self": 12.366150976169592,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 43.2598442619319,
+                                                                    "count": 204824,
+                                                                    "is_parallel": true,
+                                                                    "self": 43.2598442619319
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 453.36865482094527,
+                            "count": 25604,
+                            "self": 2.35918888696051,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 73.63783944298757,
+                                    "count": 25604,
+                                    "self": 73.51909879798768,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.1187406449998889,
+                                            "count": 1,
+                                            "self": 0.1187406449998889
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 377.3716264909972,
+                                    "count": 189,
+                                    "self": 149.91948618401057,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 227.45214030698662,
+                                            "count": 9093,
+                                            "self": 227.45214030698662
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
                 },
                 "trainer_threads": {
-                    "total": 1.562999386806041e-06,
+                    "total": 8.810002327663824e-07,
                     "count": 1,
-                    "self": 1.562999386806041e-06
+                    "self": 8.810002327663824e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.37036347199955344,
+                    "total": 0.0810865189996548,
                     "count": 1,
-                    "self": 0.01072422400011419,
+                    "self": 0.0025666270003057434,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.35963924799943925,
+                            "total": 0.07851989199934906,
                             "count": 1,
-                            "self": 0.35963924799943925
+                            "self": 0.07851989199934906
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 499906,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499906.onnx",
-                "reward": 1.5149999111890793,
-                "creation_time": 1750178585.8330705,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499906.pt"
-                ]
-            },
-            {
-                "steps": 999913,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999913.onnx",
-                "reward": null,
-                "creation_time": 1750180274.5424159,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999913.pt"
-                ]
-            },
             {
                 "steps": 1000041,
                 "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000041.onnx",
@@ -36,15 +18,42 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1000041.pt"
                 ]
+            },
+            {
+                "steps": 1200099,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1200099.onnx",
+                "reward": null,
+                "creation_time": 1750182486.9410627,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1200099.pt"
+                ]
+            },
+            {
+                "steps": 1499949,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499949.onnx",
+                "reward": 1.6297499909996986,
+                "creation_time": 1750183709.8331668,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499949.pt"
+                ]
+            },
+            {
+                "steps": 1600001,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1600001.onnx",
+                "reward": 0.1287999376654625,
+                "creation_time": 1750184077.0530765,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1600001.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000041,
+            "steps": 1600001,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1750181689.9162915,
+            "reward": 0.1287999376654625,
+            "creation_time": 1750184077.0530765,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000041.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1600001.pt"
             ]
         }
     },