commit

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d84d797242bc071fc801de77a2855ec574396f5eafd406d98d2a8f658fea1c0
+oid sha256:409014f8a8c4b01bd230e030c76306b5bdcec536b6ee6ac139d190c18d602289
 size 1420238

Pyramids/Pyramids-200121.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:409014f8a8c4b01bd230e030c76306b5bdcec536b6ee6ac139d190c18d602289
+size 1420238

Pyramids/Pyramids-200121.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b91ff354d9c527acd0f8a831421bbaebddb2ea98a0a4b4daf7fbc7c90cbc241e
+size 8656000

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3728cb94871e53f74b95a8cb0fa43da10d1e0cb0c7bb74dafb8776d8de3165b
+oid sha256:c78055bf4775c5f695a82649a136db947cf6528c17be6a3dfef9e531200ea39a
 size 8655605

Pyramids/events.out.tfevents.1782636913.ba684205ff41.15251.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feeb2e1d665c3ab221bdb9da7a0154f9c94480cc8071346f0fa669a9164a0e07
+size 1422

Pyramids/events.out.tfevents.1782636951.ba684205ff41.15462.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6482f8e2328606138a793f494550f14a93488faad01ee6bde2dedfe696b999b
+size 13535

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": 100000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "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": 200000, "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: 100000
+    max_steps: 200000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -82,8 +82,8 @@ checkpoint_settings:
   run_id: Pyramids Training
   initialize_from: null
   load_model: false
-  resume: false
-  force: true
+  resume: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

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] 55025 [Flags] 2 [Guid] 2161846138 [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] 55387 [Flags] 2 [Guid] 583358607 [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  0.084 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)
@@ -65,7 +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: 0.767665 ms
+UnloadTime: 0.794149 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.
@@ -78,7 +78,7 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 1307 frames, [32.0 KB-64.0 KB]: 509 frames, [64.0 KB-128.0 KB]: 60 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1437 frames, [32.0 KB-64.0 KB]: 370 frames, [64.0 KB-128.0 KB]: 69 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
@@ -210,22 +210,22 @@ PlayerConnection::CleanupMemory Statistics:
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12190
+  Peak main deferred allocation count 12215
     [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]: 1875 frames, [32.0 MB-64.0 MB]: 1 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 1874 frames, [32.0 MB-64.0 MB]: 2 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 32.5 MB
+      Peak Allocated memory 32.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
       Peak usage frame count: [16.0 MB-32.0 MB]: 1877 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 21.9 MB
+      Peak Allocated memory 21.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -311,4 +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":1782636816277,"processId":13948,"allocatedMemory":1970545,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":11015},{"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":1782637165438,"processId":15482,"allocatedMemory":1970545,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":11015},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.8785458207130432,
-            "min": 0.8785458207130432,
-            "max": 1.4580861330032349,
+            "value": 0.9259867668151855,
+            "min": 0.8769648671150208,
+            "max": 0.9259867668151855,
             "count": 3
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 26314.205078125,
-            "min": 26314.205078125,
-            "max": 44232.5,
+            "value": 27735.15625,
+            "min": 17623.486328125,
+            "max": 27735.15625,
             "count": 3
         },
         "Pyramids.Step.mean": {
-            "value": 89936.0,
-            "min": 29952.0,
-            "max": 89936.0,
+            "value": 179921.0,
+            "min": 119888.0,
+            "max": 179921.0,
             "count": 3
         },
         "Pyramids.Step.sum": {
-            "value": 89936.0,
-            "min": 29952.0,
-            "max": 89936.0,
+            "value": 179921.0,
+            "min": 119888.0,
+            "max": 179921.0,
             "count": 3
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.08782708644866943,
-            "min": -0.1085633859038353,
-            "max": -0.08782708644866943,
+            "value": -0.09521700441837311,
+            "min": -0.10461809486150742,
+            "max": -0.09216971695423126,
             "count": 3
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -21.078500747680664,
-            "min": -25.729522705078125,
-            "max": -21.078500747680664,
+            "value": -22.852081298828125,
+            "min": -22.852081298828125,
+            "max": -16.529659271240234,
             "count": 3
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.15133734047412872,
-            "min": 0.15133734047412872,
-            "max": 0.24542230367660522,
+            "value": 0.06673477590084076,
+            "min": 0.06673477590084076,
+            "max": 0.10928431898355484,
             "count": 3
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 36.320960998535156,
-            "min": 36.320960998535156,
-            "max": 59.14677429199219,
+            "value": 16.016345977783203,
+            "min": 16.016345977783203,
+            "max": 23.216726303100586,
             "count": 3
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06495481815248133,
-            "min": 0.06495481815248133,
-            "max": 0.07249901429466633,
+            "value": 0.06650441241170575,
+            "min": 0.06650441241170575,
+            "max": 0.07030591471725726,
             "count": 3
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.7145029996772947,
-            "min": 0.5074931000626643,
-            "max": 0.7145029996772947,
+            "value": 0.798052948940469,
+            "min": 0.2801994997298816,
+            "max": 0.798052948940469,
             "count": 3
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0011104338353228277,
-            "min": 0.0011104338353228277,
-            "max": 0.007185363666452795,
+            "value": 0.00017486471076749626,
+            "min": 0.00017486471076749626,
+            "max": 0.0013649598767580102,
             "count": 3
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.012214772188551106,
-            "min": 0.010986305519253066,
-            "max": 0.050297545665169564,
+            "value": 0.0020983765292099553,
+            "min": 0.0020983765292099553,
+            "max": 0.0136495987675801,
             "count": 3
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.738698329527271e-05,
-            "min": 7.738698329527271e-05,
-            "max": 0.0002515063018788571,
+            "value": 5.34945821685e-05,
+            "min": 5.34945821685e-05,
+            "max": 0.00013471205509600002,
             "count": 3
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0008512568162479999,
-            "min": 0.0008512568162479999,
-            "max": 0.0017605441131519997,
+            "value": 0.000641934986022,
+            "min": 0.0005388482203840001,
+            "max": 0.000982176672608,
             "count": 3
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.12579563636363636,
-            "min": 0.12579563636363636,
-            "max": 0.1838354285714286,
+            "value": 0.11783150000000002,
+            "min": 0.11783150000000002,
+            "max": 0.144904,
             "count": 3
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.3837519999999999,
-            "min": 1.232812,
-            "max": 1.3837519999999999,
+            "value": 1.4139780000000002,
+            "min": 0.579616,
+            "max": 1.4139780000000002,
             "count": 3
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.002586984072727273,
-            "min": 0.002586984072727273,
-            "max": 0.008385159314285713,
+            "value": 0.0017913668500000007,
+            "min": 0.0017913668500000007,
+            "max": 0.0044959096,
             "count": 3
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.028456824800000002,
-            "min": 0.028456824800000002,
-            "max": 0.058696115199999996,
+            "value": 0.021496402200000007,
+            "min": 0.0179836384,
+            "max": 0.0328064608,
             "count": 3
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.10751008242368698,
-            "min": 0.10751008242368698,
-            "max": 0.4035429060459137,
+            "value": 0.05180659890174866,
+            "min": 0.05180659890174866,
+            "max": 0.07853716611862183,
             "count": 3
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 1.1826108694076538,
-            "min": 1.1826108694076538,
-            "max": 2.8248002529144287,
+            "value": 0.6216791868209839,
+            "min": 0.3141486644744873,
+            "max": 0.6216791868209839,
             "count": 3
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 993.9677419354839,
-            "min": 990.6363636363636,
+            "value": 999.0,
+            "min": 998.28125,
             "max": 999.0,
             "count": 3
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30813.0,
+            "value": 31968.0,
             "min": 15984.0,
-            "max": 32691.0,
+            "max": 31968.0,
             "count": 3
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.9303742464511625,
+            "value": -0.9999484393385148,
             "min": -1.0000000521540642,
-            "max": -0.9303742464511625,
+            "max": -0.8741938006132841,
             "count": 3
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -28.841601639986038,
-            "min": -30.7230017632246,
+            "value": -30.99840161949396,
+            "min": -30.99840161949396,
             "max": -16.000000834465027,
             "count": 3
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.9303742464511625,
+            "value": -0.9999484393385148,
             "min": -1.0000000521540642,
-            "max": -0.9303742464511625,
+            "max": -0.8741938006132841,
             "count": 3
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -28.841601639986038,
-            "min": -30.7230017632246,
+            "value": -30.99840161949396,
+            "min": -30.99840161949396,
             "max": -16.000000834465027,
             "count": 3
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 1.253413832235721,
-            "min": 1.253413832235721,
-            "max": 8.478282627649605,
+            "value": 0.534257584281506,
+            "min": 0.534257584281506,
+            "max": 0.8186110365204513,
             "count": 3
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 38.855828799307346,
-            "min": 38.855828799307346,
-            "max": 135.65252204239368,
+            "value": 16.56198511272669,
+            "min": 13.097776584327221,
+            "max": 19.85759885981679,
             "count": 3
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +184,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1782636613",
+        "start_time_seconds": "1782636950",
         "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 --force",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1782636816"
+        "end_time_seconds": "1782637165"
     },
-    "total": 202.55769397699987,
+    "total": 214.87066589799997,
     "count": 1,
-    "self": 0.836918238999715,
+    "self": 0.4798725320001722,
     "children": {
         "run_training.setup": {
-            "total": 0.02300984100020287,
+            "total": 0.02424729899985323,
             "count": 1,
-            "self": 0.02300984100020287
+            "self": 0.02424729899985323
         },
         "TrainerController.start_learning": {
-            "total": 201.69776589699995,
+            "total": 214.36654606699994,
             "count": 1,
-            "self": 0.12199668399352959,
+            "self": 0.13467098800947497,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.096969272000024,
+                    "total": 2.1855458589998307,
                     "count": 1,
-                    "self": 2.096969272000024
+                    "self": 2.1855458589998307
                 },
                 "TrainerController.advance": {
-                    "total": 199.3073203220065,
-                    "count": 6262,
-                    "self": 0.12857911500532282,
+                    "total": 211.81623517799062,
+                    "count": 6266,
+                    "self": 0.1456589550134595,
                     "children": {
                         "env_step": {
-                            "total": 136.36064226499593,
-                            "count": 6262,
-                            "self": 121.4755987349804,
+                            "total": 150.42087508299892,
+                            "count": 6266,
+                            "self": 134.77207955304357,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 14.809959378018448,
-                                    "count": 6262,
-                                    "self": 0.45034861101203205,
+                                    "total": 15.566905309963659,
+                                    "count": 6266,
+                                    "self": 0.4703167549682803,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 14.359610767006416,
+                                            "total": 15.096588554995378,
                                             "count": 6256,
-                                            "self": 14.359610767006416
+                                            "self": 15.096588554995378
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.07508415199708907,
-                                    "count": 6262,
+                                    "total": 0.08189021999169199,
+                                    "count": 6266,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 200.71155644900045,
-                                            "count": 6262,
+                                            "total": 213.42091515801076,
+                                            "count": 6266,
                                             "is_parallel": true,
-                                            "self": 90.68195961001857,
+                                            "self": 90.6735544820267,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0016301639998346218,
+                                                            "total": 0.0017912769999384182,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005307460000949504,
+                                                            "self": 0.0006375309994837153,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0010994179997396714,
+                                                                    "total": 0.0011537460004547029,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0010994179997396714
+                                                                    "self": 0.0011537460004547029
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04908001300009346,
+                                                            "total": 0.05034289000013814,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005519950004782004,
+                                                            "self": 0.0005745249995925406,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005019850000280712,
+                                                                    "total": 0.00046643500036225305,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005019850000280712
+                                                                    "self": 0.00046643500036225305
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.046450565999748505,
+                                                                    "total": 0.04747408399998676,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.046450565999748505
+                                                                    "self": 0.04747408399998676
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0015754669998386817,
+                                                                    "total": 0.0018278460001965868,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003295449992037902,
+                                                                    "self": 0.0003568780002751737,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0012459220006348914,
+                                                                            "total": 0.0014709679999214131,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0012459220006348914
+                                                                            "self": 0.0014709679999214131
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 110.02959683898189,
-                                                    "count": 6261,
+                                                    "total": 122.74736067598405,
+                                                    "count": 6265,
                                                     "is_parallel": true,
-                                                    "self": 3.3200672519642467,
+                                                    "self": 3.4582741830149644,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 2.35931884400361,
-                                                            "count": 6261,
+                                                            "total": 2.3929653799882544,
+                                                            "count": 6265,
                                                             "is_parallel": true,
-                                                            "self": 2.35931884400361
+                                                            "self": 2.3929653799882544
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 93.62116089400479,
-                                                            "count": 6261,
+                                                            "total": 105.69274092498563,
+                                                            "count": 6265,
                                                             "is_parallel": true,
-                                                            "self": 93.62116089400479
+                                                            "self": 105.69274092498563
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 10.729049849009243,
-                                                            "count": 6261,
+                                                            "total": 11.203380187995208,
+                                                            "count": 6265,
                                                             "is_parallel": true,
-                                                            "self": 2.213632401005725,
+                                                            "self": 2.374361956912253,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 8.515417448003518,
-                                                                    "count": 50088,
+                                                                    "total": 8.829018231082955,
+                                                                    "count": 50120,
                                                                     "is_parallel": true,
-                                                                    "self": 8.515417448003518
+                                                                    "self": 8.829018231082955
                                                                 }
                                                             }
                                                         }
@@ -343,24 +343,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 62.818098942005236,
-                            "count": 6262,
-                            "self": 0.15990334300659015,
+                            "total": 61.24970113997824,
+                            "count": 6266,
+                            "self": 0.19105842799581296,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 10.248074063997592,
-                                    "count": 6262,
-                                    "self": 10.248074063997592
+                                    "total": 10.351301033983873,
+                                    "count": 6266,
+                                    "self": 10.351301033983873
                                 },
                                 "_update_policy": {
-                                    "total": 52.41012153500105,
-                                    "count": 30,
-                                    "self": 28.577149207021193,
+                                    "total": 50.707341677998556,
+                                    "count": 33,
+                                    "self": 27.28086230200597,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 23.83297232797986,
+                                            "total": 23.426479375992585,
                                             "count": 2283,
-                                            "self": 23.83297232797986
+                                            "self": 23.426479375992585
                                         }
                                     }
                                 }
@@ -369,19 +369,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.3670000953425188e-06,
+                    "total": 8.679999154992402e-07,
                     "count": 1,
-                    "self": 1.3670000953425188e-06
+                    "self": 8.679999154992402e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.17147825199981526,
+                    "total": 0.23009317400010332,
                     "count": 1,
-                    "self": 0.00268765999999232,
+                    "self": 0.001246918000106234,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.16879059199982294,
+                            "total": 0.22884625599999708,
                             "count": 1,
-                            "self": 0.16879059199982294
+                            "self": 0.22884625599999708
                         }
                     }
                 }

run_logs/training_status.json

@@ -9,15 +9,33 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-100048.pt"
                 ]
+            },
+            {
+                "steps": 100048,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-100048.onnx",
+                "reward": null,
+                "creation_time": 1782636914.9880667,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-100048.pt"
+                ]
+            },
+            {
+                "steps": 200121,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-200121.onnx",
+                "reward": null,
+                "creation_time": 1782637165.0008516,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-200121.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 100048,
+            "steps": 200121,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
             "reward": null,
-            "creation_time": 1782636815.4834762,
+            "creation_time": 1782637165.0008516,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-100048.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-200121.pt"
             ]
         }
     },