First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab0c27f9b3c0dadae7c92dca6ab947c145c92272b1dabfab91eabcf04f7890cd
+oid sha256:7bf2885a346b4ea13471d631300bf901e201e123b38351873162ff88f6141df4
 size 2471804

Pyramids/Pyramids-2100049.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf2885a346b4ea13471d631300bf901e201e123b38351873162ff88f6141df4
+size 2471804

Pyramids/Pyramids-2100049.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85c9c2842ad7b963916631f8377bc0b940cc9e076f0262fb2c62c86bd66d0e3a
+size 14963804

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79c75ffb228ace481e6387bafd5ae722819e82eab6e8cbc3dcabf3c228241b0
+oid sha256:b84b6c56253138a5283042e1984c6e01a231eddc92e9e3d15b018fc8fded24c0
 size 14963234

Pyramids/events.out.tfevents.1709849499.54b79351de07.91689.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75eb9390c278ddd67ec56e2ca983b6e40ba01886ee98a15f0d8adb5280968ec
+size 24109

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 2048, "learning_rate": 0.0002, "beta": 0.01, "epsilon": 0.05, "lambd": 0.95, "num_epoch": 5, "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": 3, "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": 2000000, "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": "PyramidsTraining2", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 2048, "learning_rate": 0.0001, "beta": 0.01, "epsilon": 0.01, "lambd": 0.95, "num_epoch": 5, "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": 3, "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": 2100000, "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": "PyramidsTraining2", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,9 +5,9 @@ behaviors:
     hyperparameters:
       batch_size: 256
       buffer_size: 2048
-      learning_rate: 0.0002
+      learning_rate: 0.0001
       beta: 0.01
-      epsilon: 0.05
+      epsilon: 0.01
       lambd: 0.95
       num_epoch: 5
       shared_critic: false
@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 2000000
+    max_steps: 2100000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55395 [Flags] 2 [Guid] 879112390 [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] 55499 [Flags] 2 [Guid] 3842386024 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,10 +33,17 @@ 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  0.082 seconds
+- Completed reload, in  0.106 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)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
 WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - 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?
@@ -58,14 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
-ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
-WARNING: Shader Did you use #pragma only_renderers and omit this platform?
-WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.925600 ms
+UnloadTime: 1.144441 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 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 1514 frames, [32.0 KB-64.0 KB]: 10891 frames, [64.0 KB-128.0 KB]: 6367 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 170 frames, [32.0 KB-64.0 KB]: 1033 frames, [64.0 KB-128.0 KB]: 689 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 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -204,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 26 frames, [1.0 MB-2.0 MB]: 18747 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 41 frames, [1.0 MB-2.0 MB]: 1852 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.1 MB
+  Peak Allocated memory 1.0 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 10125
+  Peak main deferred allocation count 6677
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.4 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18772 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 1892 frames
       Requested Block Size 16.0 MB
       Peak Block count 2
-      Peak Allocated memory 24.8 MB
+      Peak Allocated memory 23.5 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18773 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1893 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.9 MB
+      Peak Allocated memory 22.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -252,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.4 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18772 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1892 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]: 18773 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 1893 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -270,45 +270,45 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.4 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 34 frames, [1.0 MB-2.0 MB]: 18739 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 28 frames, [1.0 MB-2.0 MB]: 1865 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]: 18772 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 1892 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
+      Peak Allocated memory 4.3 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.4 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18773 frames
+      Peak usage frame count: [0-1.0 KB]: 1893 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]: 18773 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 1893 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]: 18773 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 1893 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 27.4 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":1709848088297,"processId":73787,"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":1709849813312,"processId":91725,"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": 0.1375330239534378,
-            "min": 0.13713061809539795,
-            "max": 0.23822951316833496,
-            "count": 33
+            "value": 0.14686335623264313,
+            "min": 0.14086739718914032,
+            "max": 0.1524546891450882,
+            "count": 4
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 4123.7900390625,
-            "min": 4118.306640625,
-            "max": 7185.001953125,
-            "count": 33
+            "value": 4368.3037109375,
+            "min": 1516.8577880859375,
+            "max": 4615.1083984375,
+            "count": 4
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 247.86507936507937,
-            "min": 222.57364341085272,
-            "max": 338.0421052631579,
-            "count": 33
+            "value": 234.25384615384615,
+            "min": 189.0612244897959,
+            "max": 260.2173913043478,
+            "count": 4
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31231.0,
-            "min": 18034.0,
-            "max": 32114.0,
-            "count": 33
+            "value": 30453.0,
+            "min": 9264.0,
+            "max": 30453.0,
+            "count": 4
         },
         "Pyramids.Step.mean": {
-            "value": 1979920.0,
-            "min": 1019935.0,
-            "max": 1979920.0,
-            "count": 33
+            "value": 2099921.0,
+            "min": 2009927.0,
+            "max": 2099921.0,
+            "count": 4
         },
         "Pyramids.Step.sum": {
-            "value": 1979920.0,
-            "min": 1019935.0,
-            "max": 1979920.0,
-            "count": 33
+            "value": 2099921.0,
+            "min": 2009927.0,
+            "max": 2099921.0,
+            "count": 4
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.7534557580947876,
-            "min": 0.5822848677635193,
-            "max": 0.8246222734451294,
-            "count": 33
+            "value": 0.8053473234176636,
+            "min": 0.7133234739303589,
+            "max": 0.8290045261383057,
+            "count": 4
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 217.74871826171875,
-            "min": 124.41722869873047,
-            "max": 249.03591918945312,
-            "count": 33
+            "value": 244.82559204101562,
+            "min": 79.23908996582031,
+            "max": 253.67538452148438,
+            "count": 4
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.0010156136704608798,
-            "min": -0.039015840739011765,
-            "max": 0.025501089170575142,
-            "count": 33
+            "value": 0.01725996471941471,
+            "min": -0.06481077522039413,
+            "max": 0.01725996471941471,
+            "count": 4
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 0.29351234436035156,
-            "min": -11.353610038757324,
-            "max": 7.344313621520996,
-            "count": 33
+            "value": 5.2470293045043945,
+            "min": -12.610334396362305,
+            "max": 5.2470293045043945,
+            "count": 4
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.7209759850502013,
-            "min": 1.5356147170066834,
-            "max": 1.7638425027995597,
-            "count": 33
+            "value": 1.7503553699988585,
+            "min": 1.7207120570900112,
+            "max": 1.810938761550553,
+            "count": 4
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 215.12199813127518,
-            "min": 119.964998729527,
-            "max": 227.61099806427956,
-            "count": 33
+            "value": 227.5461980998516,
+            "min": 88.7359993159771,
+            "max": 227.5461980998516,
+            "count": 4
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.7209759850502013,
-            "min": 1.5356147170066834,
-            "max": 1.7638425027995597,
-            "count": 33
+            "value": 1.7503553699988585,
+            "min": 1.7207120570900112,
+            "max": 1.810938761550553,
+            "count": 4
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 215.12199813127518,
-            "min": 119.964998729527,
-            "max": 227.61099806427956,
-            "count": 33
+            "value": 227.5461980998516,
+            "min": 88.7359993159771,
+            "max": 227.5461980998516,
+            "count": 4
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.019867865281703416,
-            "min": 0.01796629832147859,
-            "max": 0.03236385448932803,
-            "count": 33
+            "value": 0.018230752151878103,
+            "min": 0.015216292770655483,
+            "max": 0.02087518214358201,
+            "count": 4
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 2.483483160212927,
-            "min": 1.873240277316654,
-            "max": 3.005827545421198,
-            "count": 33
+            "value": 2.3699977797441534,
+            "min": 0.7455983457621187,
+            "max": 2.421521128655513,
+            "count": 4
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.046392814426716146,
-            "min": 0.04285314011697968,
-            "max": 0.05108637610017987,
-            "count": 33
+            "value": 0.045669686837520984,
+            "min": 0.045669686837520984,
+            "max": 0.05387836435693316,
+            "count": 4
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.649499401974026,
-            "min": 0.3856782610528171,
-            "max": 0.7298336750362069,
-            "count": 33
+            "value": 0.6393756157252938,
+            "min": 0.21551345742773265,
+            "max": 0.6912090754485689,
+            "count": 4
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.014424966649884092,
-            "min": 0.011963329645472446,
-            "max": 0.016835752428908436,
-            "count": 33
+            "value": 0.015640732158707187,
+            "min": 0.01431870764686859,
+            "max": 0.015640732158707187,
+            "count": 4
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.2019495330983773,
-            "min": 0.13363652646075933,
-            "max": 0.23570053400471808,
-            "count": 33
+            "value": 0.21897025022190061,
+            "min": 0.0590569645864889,
+            "max": 0.22341725134756413,
+            "count": 4
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 3.446698276699998e-06,
-            "min": 3.446698276699998e-06,
-            "max": 9.893718386476668e-05,
-            "count": 33
+            "value": 6.917217573571425e-07,
+            "min": 6.917217573571425e-07,
+            "max": 4.507440730750002e-06,
+            "count": 4
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 4.825377587379997e-05,
-            "min": 4.825377587379997e-05,
-            "max": 0.0013576829211589497,
-            "count": 33
+            "value": 9.684104602999994e-06,
+            "min": 9.684104602999994e-06,
+            "max": 5.038434961700002e-05,
+            "count": 4
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.09913835000000003,
-            "min": 0.07526571666666666,
-            "max": 0.09913835000000003,
-            "count": 33
+            "value": 0.09937753979591837,
+            "min": 0.09594338928571429,
+            "max": 0.09937753979591837,
+            "count": 4
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.3879369000000004,
-            "min": 0.67739145,
-            "max": 1.4756142750000003,
-            "count": 33
+            "value": 1.3912855571428573,
+            "min": 0.38377355714285716,
+            "max": 1.4710937142857141,
+            "count": 4
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00018215766999999994,
-            "min": 0.00018215766999999994,
-            "max": 0.004951909809999999,
-            "count": 33
+            "value": 7.909308265306118e-05,
+            "min": 7.909308265306118e-05,
+            "max": 0.00046028378928571445,
+            "count": 4
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.002550207379999999,
-            "min": 0.002550207379999999,
-            "max": 0.06796622089499998,
-            "count": 33
+            "value": 0.0011073031571428565,
+            "min": 0.0011073031571428565,
+            "max": 0.005173261700000002,
+            "count": 4
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.007662124466150999,
-            "min": 0.007479414809495211,
-            "max": 0.009971946477890015,
-            "count": 33
+            "value": 0.00750921992585063,
+            "min": 0.007449968717992306,
+            "max": 0.007671576924622059,
+            "count": 4
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.10726974159479141,
-            "min": 0.08974751830101013,
-            "max": 0.13969619572162628,
-            "count": 33
+            "value": 0.10512907803058624,
+            "min": 0.030686307698488235,
+            "max": 0.11174952983856201,
+            "count": 4
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 4
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 4
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1709845029",
+        "start_time_seconds": "1709849498",
         "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=PyramidsTraining2 --no-graphics --resume",
         "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": "1709848088"
+        "end_time_seconds": "1709849813"
     },
-    "total": 3058.4707801580007,
+    "total": 315.26667822700256,
     "count": 1,
-    "self": 0.4737069219991099,
+    "self": 0.6019607260059274,
     "children": {
         "run_training.setup": {
-            "total": 0.052605658001994016,
+            "total": 0.06336075699800858,
             "count": 1,
-            "self": 0.052605658001994016
+            "self": 0.06336075699800858
         },
         "TrainerController.start_learning": {
-            "total": 3057.9444675779996,
+            "total": 314.6013567439986,
             "count": 1,
-            "self": 2.206688922819012,
+            "self": 0.199611276100768,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.7855579959978058,
+                    "total": 2.620254447996558,
                     "count": 1,
-                    "self": 1.7855579959978058
+                    "self": 2.620254447996558
                 },
                 "TrainerController.advance": {
-                    "total": 3053.8628669321843,
-                    "count": 65661,
-                    "self": 2.238769279079861,
+                    "total": 311.6721845939028,
+                    "count": 6653,
+                    "self": 0.22345633607619675,
                     "children": {
                         "env_step": {
-                            "total": 1874.0822943699131,
-                            "count": 65661,
-                            "self": 1725.5800883304037,
+                            "total": 193.677894733024,
+                            "count": 6653,
+                            "self": 178.74847731585032,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 147.24639795818803,
-                                    "count": 65661,
-                                    "self": 5.633965653560153,
+                                    "total": 14.803519072062045,
+                                    "count": 6653,
+                                    "self": 0.523928353923111,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 141.61243230462787,
-                                            "count": 62575,
-                                            "self": 141.61243230462787
+                                            "total": 14.279590718138934,
+                                            "count": 6308,
+                                            "self": 14.279590718138934
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.2558080813214474,
-                                    "count": 65661,
+                                    "total": 0.12589834511163644,
+                                    "count": 6653,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 3053.4543606632105,
-                                            "count": 65661,
+                                            "total": 314.0457970251664,
+                                            "count": 6653,
                                             "is_parallel": true,
-                                            "self": 1470.4695967291482,
+                                            "self": 149.29729433146713,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0015718399990873877,
+                                                            "total": 0.0027240900017204694,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0004578700063575525,
+                                                            "self": 0.0007551800117653329,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0011139699927298352,
+                                                                    "total": 0.0019689099899551366,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0011139699927298352
+                                                                    "self": 0.0019689099899551366
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.048755717998574255,
+                                                            "total": 0.051165728000341915,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006368899994413368,
+                                                            "self": 0.0006359199978760444,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.000442190001194831,
+                                                                    "total": 0.0004655800003092736,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000442190001194831
+                                                                    "self": 0.0004655800003092736
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04601073799858568,
+                                                                    "total": 0.04856568800096284,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04601073799858568
+                                                                    "self": 0.04856568800096284
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016658999993524048,
+                                                                    "total": 0.00149854000119376,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004009000076621305,
+                                                                    "self": 0.0003199400052835699,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0012649999916902743,
+                                                                            "total": 0.00117859999591019,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0012649999916902743
+                                                                            "self": 0.00117859999591019
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1582.9847639340624,
-                                                    "count": 65660,
+                                                    "total": 164.74850269369927,
+                                                    "count": 6652,
                                                     "is_parallel": true,
-                                                    "self": 39.65575918263494,
+                                                    "self": 3.9677036714710994,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 20.023395557913318,
-                                                            "count": 65660,
+                                                            "total": 2.036080707104702,
+                                                            "count": 6652,
                                                             "is_parallel": true,
-                                                            "self": 20.023395557913318
+                                                            "self": 2.036080707104702
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1425.3997200350022,
-                                                            "count": 65660,
+                                                            "total": 148.8719915580623,
+                                                            "count": 6652,
                                                             "is_parallel": true,
-                                                            "self": 1425.3997200350022
+                                                            "self": 148.8719915580623
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 97.90588915851185,
-                                                            "count": 65660,
+                                                            "total": 9.872726757061173,
+                                                            "count": 6652,
                                                             "is_parallel": true,
-                                                            "self": 21.064568478104775,
+                                                            "self": 2.210711467632791,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 76.84132068040708,
-                                                                    "count": 525280,
+                                                                    "total": 7.662015289428382,
+                                                                    "count": 53216,
                                                                     "is_parallel": true,
-                                                                    "self": 76.84132068040708
+                                                                    "self": 7.662015289428382
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1177.5418032831913,
-                            "count": 65661,
-                            "self": 4.234237973923882,
+                            "total": 117.77083352480258,
+                            "count": 6653,
+                            "self": 0.39953413871626253,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 138.94052156524413,
-                                    "count": 65661,
-                                    "self": 138.75362716324162,
-                                    "children": {
-                                        "RLTrainer._checkpoint": {
-                                            "total": 0.1868944020025083,
-                                            "count": 2,
-                                            "self": 0.1868944020025083
-                                        }
-                                    }
+                                    "total": 13.724161448091763,
+                                    "count": 6653,
+                                    "self": 13.724161448091763
                                 },
                                 "_update_policy": {
-                                    "total": 1034.3670437440232,
-                                    "count": 473,
-                                    "self": 348.64777346871415,
+                                    "total": 103.64713793799456,
+                                    "count": 47,
+                                    "self": 34.89935663793949,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 685.7192702753091,
-                                            "count": 18920,
-                                            "self": 685.7192702753091
+                                            "total": 68.74778130005507,
+                                            "count": 1880,
+                                            "self": 68.74778130005507
                                         }
                                     }
                                 }
@@ -376,19 +369,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 7.899980118963867e-07,
+                    "total": 7.999988156370819e-07,
                     "count": 1,
-                    "self": 7.899980118963867e-07
+                    "self": 7.999988156370819e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08935293700051261,
+                    "total": 0.10930562599969562,
                     "count": 1,
-                    "self": 0.002800210000714287,
+                    "self": 0.0030194499995559454,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08655272699979832,
+                            "total": 0.10628617600013968,
                             "count": 1,
-                            "self": 0.08655272699979832
+                            "self": 0.10628617600013968
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,15 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 999911,
-                "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-999911.onnx",
-                "reward": 1.716599988937378,
-                "creation_time": 1709844961.6339633,
-                "auxillary_file_paths": [
-                    "results/PyramidsTraining2/Pyramids/Pyramids-999911.pt"
-                ]
-            },
             {
                 "steps": 1000039,
                 "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-1000039.onnx",
@@ -45,15 +36,24 @@
                 "auxillary_file_paths": [
                     "results/PyramidsTraining2/Pyramids/Pyramids-2000102.pt"
                 ]
+            },
+            {
+                "steps": 2100049,
+                "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-2100049.onnx",
+                "reward": 1.790499970316887,
+                "creation_time": 1709849812.783655,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining2/Pyramids/Pyramids-2100049.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000102,
+            "steps": 2100049,
             "file_path": "results/PyramidsTraining2/Pyramids.onnx",
-            "reward": 1.5183199688792228,
-            "creation_time": 1709848087.8528948,
+            "reward": 1.790499970316887,
+            "creation_time": 1709849812.783655,
             "auxillary_file_paths": [
-                "results/PyramidsTraining2/Pyramids/Pyramids-2000102.pt"
+                "results/PyramidsTraining2/Pyramids/Pyramids-2100049.pt"
             ]
         }
     },