First training of Pyramids

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff1881b35daf3b9e562c2b7373fd7f1b3c719f44edad6e89fc47ca31f1bf4ab
+oid sha256:c2ddeba5a5ca27ad6e9850b20bf695e431d371d1309d576aa50772f4f1009144
 size 1420238

Pyramids/Pyramids-499912.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ddeba5a5ca27ad6e9850b20bf695e431d371d1309d576aa50772f4f1009144
+size 1420238

Pyramids/Pyramids-499912.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13dd5dde9425a61236f959313da0ffc3c074c60eef2a51d801d013895133138f
+size 8655149

Pyramids/Pyramids-500168.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ddeba5a5ca27ad6e9850b20bf695e431d371d1309d576aa50772f4f1009144
+size 1420238

Pyramids/Pyramids-500168.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01230889a470727db57b8c9b47397988be24737919a736882c2798356bd2cf7b
+size 8655149

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35974df57212001a4b56f595020bd2c6eb538652c85ff16eeece27c3c10497f8
+oid sha256:29915e14ea0a3a8b2e7789a4edae907e51b6c44e4716f46031e3e2873ee6b842
 size 8654754

Pyramids/events.out.tfevents.1714212102.d7841d41eff8.5869.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aafc2dfc0f86ad6ae795fde783fbfaccce08a1b2f82840ccd59f156302f0ddb
+size 128938

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": 600000, "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": 500000, "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}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 600000
+    max_steps: 500000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

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] 55196 [Flags] 2 [Guid] 2314881328 [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] 55110 [Flags] 2 [Guid] 13513407 [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  0.132 seconds
+- Completed reload, in  0.163 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: 1.175711 ms
+UnloadTime: 2.101153 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]: 1703 frames, [32.0 KB-64.0 KB]: 8480 frames, [64.0 KB-128.0 KB]: 1084 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 6901 frames, [32.0 KB-64.0 KB]: 1818 frames, [64.0 KB-128.0 KB]: 677 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
@@ -146,7 +149,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 480 B
+      Peak Allocated Bytes 240 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -183,12 +186,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -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]: 10969 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 9098 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 12737
+  Peak main deferred allocation count 12584
     [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]: 11267 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 9396 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.5 MB
+      Peak Allocated memory 30.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 11268 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 9397 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.5 MB
+      Peak Allocated memory 24.0 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]: 11267 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9396 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]: 11268 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 9397 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,13 +275,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 10969 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 9098 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]: 11267 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 9396 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -290,25 +293,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 11268 frames
+      Peak usage frame count: [0-1.0 KB]: 9397 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]: 11268 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 9397 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]: 11268 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 9397 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.0 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":1714052892603,"processId":7155,"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":1714213936298,"processId":5943,"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

@@ -2,189 +2,189 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.6478382349014282,
-            "min": 0.6478382349014282,
-            "max": 1.501163363456726,
-            "count": 20
+            "value": 0.7599734663963318,
+            "min": 0.7209876179695129,
+            "max": 1.4070985317230225,
+            "count": 16
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 19414.416015625,
-            "min": 19414.416015625,
-            "max": 45539.29296875,
-            "count": 20
+            "value": 22993.7578125,
+            "min": 21641.1640625,
+            "max": 42685.7421875,
+            "count": 16
         },
         "Pyramids.Step.mean": {
-            "value": 599938.0,
+            "value": 479905.0,
             "min": 29952.0,
-            "max": 599938.0,
-            "count": 20
+            "max": 479905.0,
+            "count": 16
         },
         "Pyramids.Step.sum": {
-            "value": 599938.0,
+            "value": 479905.0,
             "min": 29952.0,
-            "max": 599938.0,
-            "count": 20
+            "max": 479905.0,
+            "count": 16
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.18724876642227173,
-            "min": -0.18214330077171326,
-            "max": 0.18724876642227173,
-            "count": 20
+            "value": 0.01879260689020157,
+            "min": -0.10406187176704407,
+            "max": 0.2354099154472351,
+            "count": 16
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 47.561187744140625,
-            "min": -43.16796112060547,
-            "max": 47.561187744140625,
-            "count": 20
+            "value": 4.622981071472168,
+            "min": -25.07891082763672,
+            "max": 55.79214859008789,
+            "count": 16
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.005261237267404795,
-            "min": 0.005261237267404795,
-            "max": 0.3343900442123413,
-            "count": 20
+            "value": 0.033645398914813995,
+            "min": 0.025427494198083878,
+            "max": 0.415382444858551,
+            "count": 16
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 1.3363542556762695,
-            "min": 1.3363542556762695,
-            "max": 79.25044250488281,
-            "count": 20
+            "value": 8.27676773071289,
+            "min": 6.1788811683654785,
+            "max": 98.44564056396484,
+            "count": 16
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06920473634541155,
-            "min": 0.06683283463617834,
-            "max": 0.07195383903981176,
-            "count": 20
+            "value": 0.06733978535977894,
+            "min": 0.06575865745959983,
+            "max": 0.07418710289688644,
+            "count": 16
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9688663088357617,
-            "min": 0.47693756886074806,
-            "max": 1.0728707710659366,
-            "count": 20
+            "value": 1.010096780396684,
+            "min": 0.47318129119815855,
+            "max": 1.010096780396684,
+            "count": 16
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.011946729921744139,
-            "min": 0.0008682443716028568,
-            "max": 0.011946729921744139,
-            "count": 20
+            "value": 0.005578834796633482,
+            "min": 0.0001478741731252948,
+            "max": 0.007087473844843657,
+            "count": 16
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.16725421890441794,
-            "min": 0.0060777106012199975,
-            "max": 0.16725421890441794,
-            "count": 20
+            "value": 0.08368252194950222,
+            "min": 0.0016266159043782427,
+            "max": 0.09486772501394643,
+            "count": 16
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.054847648416671e-06,
-            "min": 7.054847648416671e-06,
-            "max": 0.0002919177169798095,
-            "count": 20
+            "value": 2.102853299052e-05,
+            "min": 2.102853299052e-05,
+            "max": 0.00029030126037577137,
+            "count": 16
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 9.876786707783339e-05,
-            "min": 9.876786707783339e-05,
-            "max": 0.003045879384707,
-            "count": 20
+            "value": 0.0003154279948578,
+            "min": 0.0003154279948578,
+            "max": 0.0024124490958503998,
+            "count": 16
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10235158333333332,
-            "min": 0.10235158333333332,
-            "max": 0.1973059047619048,
-            "count": 20
+            "value": 0.10700948,
+            "min": 0.10700948,
+            "max": 0.19676708571428575,
+            "count": 16
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4329221666666665,
-            "min": 1.3485226666666668,
-            "max": 2.4152929999999997,
-            "count": 20
+            "value": 1.6051422,
+            "min": 1.3382272,
+            "max": 2.09259,
+            "count": 16
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00024492317500000003,
-            "min": 0.00024492317500000003,
-            "max": 0.009730859885714286,
-            "count": 20
+            "value": 0.0007102470520000002,
+            "min": 0.0007102470520000002,
+            "max": 0.00967703186285714,
+            "count": 16
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0034289244500000007,
-            "min": 0.0034289244500000007,
-            "max": 0.10156777070000002,
-            "count": 20
+            "value": 0.010653705780000003,
+            "min": 0.010653705780000003,
+            "max": 0.08044454504,
+            "count": 16
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.016863195225596428,
-            "min": 0.016720183193683624,
-            "max": 0.3915402889251709,
-            "count": 20
+            "value": 0.026969928294420242,
+            "min": 0.026969928294420242,
+            "max": 0.4718073904514313,
+            "count": 16
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.2360847443342209,
-            "min": 0.2360847443342209,
-            "max": 2.7407820224761963,
-            "count": 20
+            "value": 0.40454891324043274,
+            "min": 0.3871544897556305,
+            "max": 3.3026516437530518,
+            "count": 16
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 587.530612244898,
-            "min": 587.530612244898,
+            "value": 837.6666666666666,
+            "min": 831.3714285714286,
             "max": 999.0,
-            "count": 20
+            "count": 16
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 28789.0,
+            "value": 30156.0,
             "min": 15984.0,
-            "max": 32936.0,
-            "count": 20
+            "max": 31968.0,
+            "count": 16
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.0041754768819224,
+            "value": -0.06025004221333398,
             "min": -1.0000000521540642,
-            "max": 1.0041754768819224,
-            "count": 20
+            "max": 0.025474242653165544,
+            "count": 16
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 49.2045983672142,
+            "value": -2.169001519680023,
             "min": -32.000001668930054,
-            "max": 49.2045983672142,
-            "count": 20
+            "max": 0.8915984928607941,
+            "count": 16
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.0041754768819224,
+            "value": -0.06025004221333398,
             "min": -1.0000000521540642,
-            "max": 1.0041754768819224,
-            "count": 20
+            "max": 0.025474242653165544,
+            "count": 16
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 49.2045983672142,
+            "value": -2.169001519680023,
             "min": -32.000001668930054,
-            "max": 49.2045983672142,
-            "count": 20
+            "max": 0.8915984928607941,
+            "count": 16
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.1021522772094539,
-            "min": 0.1021522772094539,
-            "max": 7.710925901308656,
-            "count": 20
+            "value": 0.23489424048845345,
+            "min": 0.23489424048845345,
+            "max": 9.061561428010464,
+            "count": 16
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 5.005461583263241,
-            "min": 5.005461583263241,
-            "max": 123.37481442093849,
-            "count": 20
+            "value": 8.456192657584324,
+            "min": 7.9692321280017495,
+            "max": 144.98498284816742,
+            "count": 16
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 16
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 16
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1714050857",
+        "start_time_seconds": "1714212100",
         "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",
         "mlagents_version": "1.1.0.dev0",
@@ -192,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.2.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1714052892"
+        "end_time_seconds": "1714213936"
     },
-    "total": 2035.5195693849998,
+    "total": 1835.846905264,
     "count": 1,
-    "self": 1.170947453999588,
+    "self": 0.8496744670001135,
     "children": {
         "run_training.setup": {
-            "total": 0.0873782520000077,
+            "total": 0.08212086200001067,
             "count": 1,
-            "self": 0.0873782520000077
+            "self": 0.08212086200001067
         },
         "TrainerController.start_learning": {
-            "total": 2034.2612436790002,
+            "total": 1834.915109935,
             "count": 1,
-            "self": 1.4362915860294834,
+            "self": 1.3568495619740588,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.5098585850000745,
+                    "total": 4.251138632999982,
                     "count": 1,
-                    "self": 2.5098585850000745
+                    "self": 4.251138632999982
                 },
                 "TrainerController.advance": {
-                    "total": 2030.1492163069706,
-                    "count": 37937,
-                    "self": 1.71343659389413,
+                    "total": 1829.1851239430255,
+                    "count": 31520,
+                    "self": 1.5376524270322989,
                     "children": {
                         "env_step": {
-                            "total": 1311.7210331760184,
-                            "count": 37937,
-                            "self": 1202.3931517710591,
+                            "total": 1203.8001412769786,
+                            "count": 31520,
+                            "self": 1104.5481686250305,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 108.37235794696221,
-                                    "count": 37937,
-                                    "self": 5.114811040994255,
+                                    "total": 98.34488847899775,
+                                    "count": 31520,
+                                    "self": 4.651149765976925,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 103.25754690596796,
-                                            "count": 37559,
-                                            "self": 103.25754690596796
+                                            "total": 93.69373871302082,
+                                            "count": 31321,
+                                            "self": 93.69373871302082
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.9555234579970602,
-                                    "count": 37937,
+                                    "total": 0.9070841729503627,
+                                    "count": 31520,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2029.6379632149115,
-                                            "count": 37937,
+                                            "total": 1830.2551806290148,
+                                            "count": 31520,
                                             "is_parallel": true,
-                                            "self": 951.950502307945,
+                                            "self": 846.5177497510476,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0022997490000307153,
+                                                            "total": 0.008484212999974261,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006597380001949205,
+                                                            "self": 0.005564789999880304,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0016400109998357948,
+                                                                    "total": 0.002919423000093957,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0016400109998357948
+                                                                    "self": 0.002919423000093957
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06654963899995892,
+                                                            "total": 0.08026218899999549,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008212950001507124,
+                                                            "self": 0.0009926469999754772,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0006649509998624126,
+                                                                    "total": 0.0007841110000299523,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006649509998624126
+                                                                    "self": 0.0007841110000299523
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0628841889999876,
+                                                                    "total": 0.07452836900006332,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0628841889999876
+                                                                    "self": 0.07452836900006332
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0021792039999581903,
+                                                                    "total": 0.0039570619999267365,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000498880999884932,
+                                                                    "self": 0.0006147659996713628,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0016803230000732583,
+                                                                            "total": 0.0033422960002553737,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0016803230000732583
+                                                                            "self": 0.0033422960002553737
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1077.6874609069664,
-                                                    "count": 37936,
+                                                    "total": 983.7374308779672,
+                                                    "count": 31519,
                                                     "is_parallel": true,
-                                                    "self": 32.51179417788785,
+                                                    "self": 31.030970321985478,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 17.66922213103976,
-                                                            "count": 37936,
+                                                            "total": 17.714325252019307,
+                                                            "count": 31519,
                                                             "is_parallel": true,
-                                                            "self": 17.66922213103976
+                                                            "self": 17.714325252019307
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 944.2755419109951,
-                                                            "count": 37936,
+                                                            "total": 859.7539580449691,
+                                                            "count": 31519,
                                                             "is_parallel": true,
-                                                            "self": 944.2755419109951
+                                                            "self": 859.7539580449691
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 83.23090268704368,
-                                                            "count": 37936,
+                                                            "total": 75.23817725899335,
+                                                            "count": 31519,
                                                             "is_parallel": true,
-                                                            "self": 17.833601884062773,
+                                                            "self": 16.938205290088035,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 65.39730080298091,
-                                                                    "count": 303488,
+                                                                    "total": 58.29997196890531,
+                                                                    "count": 252152,
                                                                     "is_parallel": true,
-                                                                    "self": 65.39730080298091
+                                                                    "self": 58.29997196890531
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 716.7147465370581,
-                            "count": 37937,
-                            "self": 2.7046983360226022,
+                            "total": 623.8473302390146,
+                            "count": 31520,
+                            "self": 2.549967814034062,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 110.84748384203613,
-                                    "count": 37937,
-                                    "self": 110.71504253303647,
+                                    "total": 98.67590811597938,
+                                    "count": 31520,
+                                    "self": 98.49947127997939,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.13244130899965967,
+                                            "total": 0.1764368359999935,
                                             "count": 1,
-                                            "self": 0.13244130899965967
+                                            "self": 0.1764368359999935
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 603.1625643589994,
-                                    "count": 258,
-                                    "self": 239.17001531900723,
+                                    "total": 522.6214543090011,
+                                    "count": 199,
+                                    "self": 210.35886820299856,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 363.9925490399921,
-                                            "count": 13689,
-                                            "self": 363.9925490399921
+                                            "total": 312.2625861060026,
+                                            "count": 11460,
+                                            "self": 312.2625861060026
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.4830002328380942e-06,
+                    "total": 1.5830000847927295e-06,
                     "count": 1,
-                    "self": 1.4830002328380942e-06
+                    "self": 1.5830000847927295e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1658757179998247,
+                    "total": 0.12199621400031901,
                     "count": 1,
-                    "self": 0.005956058999800007,
+                    "self": 0.005445809000320878,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1599196590000247,
+                            "total": 0.11655040499999814,
                             "count": 1,
-                            "self": 0.1599196590000247
+                            "self": 0.11655040499999814
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,31 +2,31 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499994,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499994.onnx",
-                "reward": 1.278999959429105,
-                "creation_time": 1714052524.301536,
+                "steps": 499912,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499912.onnx",
+                "reward": -0.050000021855036415,
+                "creation_time": 1714213935.3722806,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499994.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499912.pt"
                 ]
             },
             {
-                "steps": 600194,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-600194.onnx",
-                "reward": null,
-                "creation_time": 1714052891.5132313,
+                "steps": 500168,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-500168.onnx",
+                "reward": -0.050000021855036415,
+                "creation_time": 1714213935.525897,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-600194.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-500168.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 600194,
+            "steps": 500168,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1714052891.5132313,
+            "reward": -0.050000021855036415,
+            "creation_time": 1714213935.525897,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-600194.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-500168.pt"
             ]
         }
     },