Ver1

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b46cbe30274811307c3eea376e6212b105e54efa439fc60cf7310925ba09b063
+oid sha256:acde757b3abaedaeddf169243ef94344ac1decd0349ba621ff65fe215367acbf
 size 1420238

Pyramids/Pyramids-1000002.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acde757b3abaedaeddf169243ef94344ac1decd0349ba621ff65fe215367acbf
+size 1420238

Pyramids/Pyramids-1000002.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3581275a39b030687d09437ee31975c18c04d292131af6b552fcae7106194447
+size 8655228

Pyramids/Pyramids-499986.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86495387ee75439ea6135167355d5459c1f3e34f49e4364c538482e43c4860eb
+size 1420238

Pyramids/Pyramids-499986.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:872dc1ce89ee39c58be6d220bbe77c3d5ed9321afe43f84c4ef835d09ad2b7f7
+size 8655149

Pyramids/Pyramids-999874.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acde757b3abaedaeddf169243ef94344ac1decd0349ba621ff65fe215367acbf
+size 1420238

Pyramids/Pyramids-999874.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6d2ce7d6d3431623b9257e3f372c52d8027b163b0470163ec6c7f5eeb4aa77
+size 8655149

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c06c7b9529937062febf27253998c42dfcb3bab4e2eb237c9e37974c10049e1
+oid sha256:b196123dbdf9db0369a65bae8cc6d62eedc872f5df4655b8ddddfab3e1c99a03
 size 8654754

Pyramids/events.out.tfevents.1714982721.982787a1b84e.4598.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f351b74004db3050cd1427fe052a69683df3fafcd6434bf66ed38ea051c12f1f
+size 304068

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": 25000, "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": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -53,7 +53,7 @@ behaviors:
     even_checkpoints: false
     max_steps: 1000000
     time_horizon: 128
-    summary_freq: 25000
+    summary_freq: 30000
     threaded: false
     self_play: null
     behavioral_cloning: null
@@ -83,7 +83,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -1,9 +1,12 @@
 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] 55278 [Flags] 2 [Guid] 596179513 [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] 55120 [Flags] 2 [Guid] 1856787423 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -33,7 +36,7 @@ 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  0.118 seconds
+- Completed reload, in  0.122 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 +68,7 @@ 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: 1.170960 ms
+UnloadTime: 1.146997 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.
@@ -73,7 +76,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 7933 frames, [32.0 KB-64.0 KB]: 9300 frames, [64.0 KB-128.0 KB]: 1538 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 9420 frames, [32.0 KB-64.0 KB]: 8058 frames, [64.0 KB-128.0 KB]: 1285 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
@@ -204,28 +207,28 @@ 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]: 18473 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18465 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 10918
+  Peak main deferred allocation count 12308
     [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]: 18771 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18763 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.6 MB
+      Peak Allocated memory 30.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18772 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18764 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.4 MB
+      Peak Allocated memory 22.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -254,13 +257,13 @@ 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]: 18771 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18763 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]: 18772 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18764 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,16 +275,16 @@ 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]: 18473 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18465 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]: 18771 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18763 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
@@ -290,19 +293,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18772 frames
+      Peak usage frame count: [0-1.0 KB]: 18764 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]: 18772 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18764 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]: 18772 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18764 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -311,4 +314,4 @@ 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":1714950742568,"processId":8953,"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":1714985571791,"processId":4642,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.5788527727127075,
-            "min": 0.5075520277023315,
-            "max": 1.4878400564193726,
-            "count": 40
+            "value": 0.07455726712942123,
+            "min": 0.07132061570882797,
+            "max": 1.3283107280731201,
+            "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 14744.537109375,
-            "min": 12400.51171875,
-            "max": 39040.921875,
-            "count": 40
+            "value": 2233.13916015625,
+            "min": 2135.053955078125,
+            "max": 40295.6328125,
+            "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 999974.0,
-            "min": 24960.0,
-            "max": 999974.0,
-            "count": 40
+            "value": 989993.0,
+            "min": 29936.0,
+            "max": 989993.0,
+            "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 999974.0,
-            "min": 24960.0,
-            "max": 999974.0,
-            "count": 40
+            "value": 989993.0,
+            "min": 29936.0,
+            "max": 989993.0,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.041352529078722,
-            "min": -0.10387088358402252,
-            "max": 0.09415142983198166,
-            "count": 40
+            "value": -0.07817629724740982,
+            "min": -0.1059875339269638,
+            "max": -0.0019704073201864958,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 8.394563674926758,
-            "min": -20.981918334960938,
-            "max": 19.11273956298828,
-            "count": 40
+            "value": -18.84048843383789,
+            "min": -25.437007904052734,
+            "max": -0.46895694732666016,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.013669253326952457,
-            "min": -0.02086319401860237,
-            "max": 0.5626580119132996,
-            "count": 40
+            "value": 2.491220474243164,
+            "min": 1.0348438024520874,
+            "max": 2.539546251296997,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -2.7748584747314453,
-            "min": -4.256091594696045,
-            "max": 111.40628051757812,
-            "count": 40
+            "value": 600.3841552734375,
+            "min": 246.29283142089844,
+            "max": 614.0382080078125,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.07271344667732194,
-            "min": 0.060989299619117164,
-            "max": 0.07682047858867998,
-            "count": 40
+            "value": 0.065614514083378,
+            "min": 0.0645075750368747,
+            "max": 0.07181220632628539,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.8725613601278632,
-            "min": 0.4609228715320799,
-            "max": 0.8725613601278632,
-            "count": 40
+            "value": 0.9186031971672919,
+            "min": 0.5738096991478857,
+            "max": 1.0172520895281978,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.005559318314397304,
-            "min": 6.892239868742414e-05,
-            "max": 0.028220939736028173,
-            "count": 40
+            "value": 0.005526476083120366,
+            "min": 0.0033118486424310637,
+            "max": 0.05471255845147784,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.06671181977276765,
-            "min": 0.0007581463855616655,
-            "max": 0.16932563841616904,
-            "count": 40
+            "value": 0.07737066516368513,
+            "min": 0.046365880994034894,
+            "max": 0.43770046761182274,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 3.56592381139167e-06,
-            "min": 3.56592381139167e-06,
-            "max": 0.0002957568014144,
-            "count": 40
+            "value": 7.555704624321432e-06,
+            "min": 7.555704624321432e-06,
+            "max": 0.0002949271891909375,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 4.279108573670004e-05,
-            "min": 4.279108573670004e-05,
-            "max": 0.0027636358787880995,
-            "count": 40
+            "value": 0.00010577986474050005,
+            "min": 0.00010577986474050005,
+            "max": 0.0036340867886378,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10118860833333333,
-            "min": 0.10118860833333333,
-            "max": 0.1985856,
-            "count": 40
+            "value": 0.1025185357142857,
+            "min": 0.1025185357142857,
+            "max": 0.19830906250000002,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.2142633,
-            "min": 1.1915136,
-            "max": 2.0249231,
-            "count": 40
+            "value": 1.4352594999999997,
+            "min": 1.4352594999999997,
+            "max": 2.6113622000000003,
+            "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00012874197250000013,
-            "min": 0.00012874197250000013,
-            "max": 0.00985870144,
-            "count": 40
+            "value": 0.00026160171785714296,
+            "min": 0.00026160171785714296,
+            "max": 0.009831075343749999,
+            "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0015449036700000015,
-            "min": 0.0015449036700000015,
-            "max": 0.09213906880999999,
-            "count": 40
+            "value": 0.003662424050000001,
+            "min": 0.003662424050000001,
+            "max": 0.12115508378,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.015322144143283367,
-            "min": 0.014871549792587757,
-            "max": 0.6652459502220154,
-            "count": 40
+            "value": 2.4843578338623047,
+            "min": 1.1381711959838867,
+            "max": 2.532205820083618,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.1838657259941101,
-            "min": 0.17368657886981964,
-            "max": 3.991475820541382,
-            "count": 40
+            "value": 34.781009674072266,
+            "min": 9.105369567871094,
+            "max": 37.70604705810547,
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 865.2222222222222,
-            "min": 770.34375,
+            "value": 959.1935483870968,
+            "min": 878.6,
             "max": 999.0,
-            "count": 40
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 23361.0,
-            "min": 15984.0,
-            "max": 31928.0,
-            "count": 40
+            "value": 29735.0,
+            "min": 16734.0,
+            "max": 33430.0,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.12481486328222134,
-            "min": -1.0000000521540642,
-            "max": 0.32346662946722726,
-            "count": 40
+            "value": -0.8307355313051131,
+            "min": -0.9997677937630685,
+            "max": -0.479148619728429,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -3.370001308619976,
-            "min": -29.959001623094082,
-            "max": 10.674398772418499,
-            "count": 40
+            "value": -25.752801470458508,
+            "min": -30.99280160665512,
+            "max": -12.75000087916851,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.12481486328222134,
-            "min": -1.0000000521540642,
-            "max": 0.32346662946722726,
-            "count": 40
+            "value": -0.8307355313051131,
+            "min": -0.9997677937630685,
+            "max": -0.479148619728429,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -3.370001308619976,
-            "min": -29.959001623094082,
-            "max": 10.674398772418499,
-            "count": 40
+            "value": -25.752801470458508,
+            "min": -30.99280160665512,
+            "max": -12.75000087916851,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.13425074744521193,
-            "min": 0.1261344698312528,
-            "max": 13.221708751283586,
-            "count": 40
+            "value": 24.168192972098627,
+            "min": 12.799532570772701,
+            "max": 25.182880740011893,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 3.624770181020722,
-            "min": 3.624770181020722,
-            "max": 211.54734002053738,
-            "count": 40
+            "value": 749.2139821350574,
+            "min": 337.66693917661905,
+            "max": 820.8074612617493,
+            "count": 33
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 40
+            "count": 33
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 40
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1714947562",
+        "start_time_seconds": "1714982720",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --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",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.2.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1714950742"
+        "end_time_seconds": "1714985571"
     },
-    "total": 3179.7104532840003,
+    "total": 2851.334854015,
     "count": 1,
-    "self": 0.6293249960003777,
+    "self": 0.6444775009995283,
     "children": {
         "run_training.setup": {
-            "total": 0.06399147399997673,
+            "total": 0.0703482950000307,
             "count": 1,
-            "self": 0.06399147399997673
+            "self": 0.0703482950000307
         },
         "TrainerController.start_learning": {
-            "total": 3179.017136814,
+            "total": 2850.6200282190002,
             "count": 1,
-            "self": 2.1964379759929216,
+            "self": 2.1801448129285745,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.9917514930002653,
+                    "total": 3.7731822739999643,
                     "count": 1,
-                    "self": 2.9917514930002653
+                    "self": 3.7731822739999643
                 },
                 "TrainerController.advance": {
-                    "total": 3173.740101920007,
-                    "count": 63147,
-                    "self": 2.5670525030473073,
+                    "total": 2844.5752912720714,
+                    "count": 63166,
+                    "self": 2.4229753350377905,
                     "children": {
                         "env_step": {
-                            "total": 2069.150516912996,
-                            "count": 63147,
-                            "self": 1901.6252850599326,
+                            "total": 1742.0621759190403,
+                            "count": 63166,
+                            "self": 1579.316787149144,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 166.09323028403196,
-                                    "count": 63147,
-                                    "self": 7.0478826240282615,
+                                    "total": 161.33067456894992,
+                                    "count": 63166,
+                                    "self": 7.031003369945893,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 159.0453476600037,
-                                            "count": 62571,
-                                            "self": 159.0453476600037
+                                            "total": 154.29967119900402,
+                                            "count": 62545,
+                                            "self": 154.29967119900402
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.4320015690313994,
-                                    "count": 63147,
+                                    "total": 1.4147142009464915,
+                                    "count": 63166,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 3172.8734618389512,
-                                            "count": 63147,
+                                            "total": 2844.977574130914,
+                                            "count": 63166,
                                             "is_parallel": true,
-                                            "self": 1457.236391190991,
+                                            "self": 1447.7276523028481,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002283305999753793,
+                                                            "total": 0.00715304299978925,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006858580004518444,
+                                                            "self": 0.0055326729996068025,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0015974479993019486,
+                                                                    "total": 0.0016203700001824473,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0015974479993019486
+                                                                    "self": 0.0016203700001824473
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.14202162199990198,
+                                                            "total": 0.0657242300001144,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0009058839996214374,
+                                                            "self": 0.0008261030000085157,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005030610000176239,
+                                                                    "total": 0.0005049030000918719,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005030610000176239
+                                                                    "self": 0.0005049030000918719
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.13858043800019004,
+                                                                    "total": 0.06225493700003426,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.13858043800019004
+                                                                    "self": 0.06225493700003426
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0020322390000728774,
+                                                                    "total": 0.002138286999979755,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004962849998264574,
+                                                                    "self": 0.0004544600003555388,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.00153595400024642,
+                                                                            "total": 0.0016838269996242161,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.00153595400024642
+                                                                            "self": 0.0016838269996242161
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1715.6370706479602,
-                                                    "count": 63146,
+                                                    "total": 1397.249921828066,
+                                                    "count": 63165,
                                                     "is_parallel": true,
-                                                    "self": 51.504114547959034,
+                                                    "self": 50.14738497017811,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 27.97836596996285,
-                                                            "count": 63146,
+                                                            "total": 27.276636888926532,
+                                                            "count": 63165,
                                                             "is_parallel": true,
-                                                            "self": 27.97836596996285
+                                                            "self": 27.276636888926532
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1503.1463776709957,
-                                                            "count": 63146,
+                                                            "total": 1189.330745613935,
+                                                            "count": 63165,
                                                             "is_parallel": true,
-                                                            "self": 1503.1463776709957
+                                                            "self": 1189.330745613935
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 133.00821245904262,
-                                                            "count": 63146,
+                                                            "total": 130.49515435502622,
+                                                            "count": 63165,
                                                             "is_parallel": true,
-                                                            "self": 28.523905566722988,
+                                                            "self": 27.54295952398047,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 104.48430689231964,
-                                                                    "count": 505168,
+                                                                    "total": 102.95219483104574,
+                                                                    "count": 505320,
                                                                     "is_parallel": true,
-                                                                    "self": 104.48430689231964
+                                                                    "self": 102.95219483104574
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1102.0225325039637,
-                            "count": 63147,
-                            "self": 4.28274637705681,
+                            "total": 1100.0901400179935,
+                            "count": 63166,
+                            "self": 4.377121299980672,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 168.60562072290531,
-                                    "count": 63147,
-                                    "self": 168.381087445905,
+                                    "total": 167.10743509001327,
+                                    "count": 63166,
+                                    "self": 166.86853313101278,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.22453327700031878,
+                                            "total": 0.23890195900048639,
                                             "count": 2,
-                                            "self": 0.22453327700031878
+                                            "self": 0.23890195900048639
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 929.1341654040016,
-                                    "count": 441,
-                                    "self": 366.3056278879799,
+                                    "total": 928.6055836279995,
+                                    "count": 455,
+                                    "self": 369.2479338760438,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 562.8285375160217,
-                                            "count": 22827,
-                                            "self": 562.8285375160217
+                                            "total": 559.3576497519557,
+                                            "count": 22725,
+                                            "self": 559.3576497519557
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.089999386749696e-06,
+                    "total": 1.2390000847517513e-06,
                     "count": 1,
-                    "self": 1.089999386749696e-06
+                    "self": 1.2390000847517513e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08884433500043087,
+                    "total": 0.09140862100002778,
                     "count": 1,
-                    "self": 0.0023472490001950064,
+                    "self": 0.002121488999819121,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08649708600023587,
+                            "total": 0.08928713200020866,
                             "count": 1,
-                            "self": 0.08649708600023587
+                            "self": 0.08928713200020866
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499928,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499928.onnx",
+                "steps": 499986,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499986.onnx",
                 "reward": null,
-                "creation_time": 1714949107.4603968,
+                "creation_time": 1714984170.4654858,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499928.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499986.pt"
                 ]
             },
             {
-                "steps": 999974,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999974.onnx",
-                "reward": null,
-                "creation_time": 1714950741.899395,
+                "steps": 999874,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999874.onnx",
+                "reward": -0.9996000528335571,
+                "creation_time": 1714985571.1016953,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999974.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999874.pt"
                 ]
             },
             {
-                "steps": 1000102,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000102.onnx",
-                "reward": null,
-                "creation_time": 1714950742.0019765,
+                "steps": 1000002,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000002.onnx",
+                "reward": -0.9996000528335571,
+                "creation_time": 1714985571.2060378,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000102.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000002.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000102,
+            "steps": 1000002,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1714950742.0019765,
+            "reward": -0.9996000528335571,
+            "creation_time": 1714985571.2060378,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000102.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000002.pt"
             ]
         }
     },