First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06e2f6e7f57e8e333e5d0d2b18a2d62370957d48c80788979296aa975475236b
+oid sha256:6486d037f2a295d3ae456529ffddaeb17bc770b886f4814dbac8d784bcc874f9
 size 1418184

Pyramids/Pyramids-1499996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edfe19b971ad80ad72d884bd5b1cdc560103ff85dcc589c02fa43a38de98b2ec
+size 1418184

Pyramids/Pyramids-1499996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c633d0a5244686462a7d64a9d837a810a98abe927b8c613ba1c50e5240f4e043
+size 8650990

Pyramids/Pyramids-1999977.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c33e866a2d772adb4717757b6d82b6290f87cc298f450b63e8f0b313d447f5b
+size 1418184

Pyramids/Pyramids-1999977.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee7ad1719eae92193be30ec06675e35029d3ae4aadab292a2dde4508a29196e9
+size 8650990

Pyramids/Pyramids-2499973.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad3626400c03ea37b053aac9a9f696adb3a5e3cbcd13a6dba4d1a755b16a822
+size 1418184

Pyramids/Pyramids-2499973.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb71f1860a597f76efb15f22a133b47867338214cc4b8ddc1df0bb285d3b838
+size 8650990

Pyramids/Pyramids-2999969.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6486d037f2a295d3ae456529ffddaeb17bc770b886f4814dbac8d784bcc874f9
+size 1418184

Pyramids/Pyramids-2999969.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df99146f7da5a233980babd54c9e15f0fdf334411353d879f3b0be5833a6e30a
+size 8650990

Pyramids/Pyramids-3000097.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6486d037f2a295d3ae456529ffddaeb17bc770b886f4814dbac8d784bcc874f9
+size 1418184

Pyramids/Pyramids-3000097.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab95e81181af2db4f5c2845800930e88ea43d31b7d62820281eee3dbe0384e3
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51932df50e5b0f9d32d33f6708029c22dfe18ab682b7614f71b43a562271b48f
+oid sha256:bab95e81181af2db4f5c2845800930e88ea43d31b7d62820281eee3dbe0384e3
 size 8650990

Pyramids/events.out.tfevents.1686376010.26c74d5d5b88.19100.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0b8f2decced04540661cebdbaef0bd56d9cceba0966641c6916bdb5f5a0321
+size 1423

Pyramids/events.out.tfevents.1686376081.26c74d5d5b88.19458.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e6526974e527f78fb3a3397f07fbf5cb546f39d141f8dfdd72987a6ee9efef
+size 397213

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 50000, "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, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"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": 3000000, "time_horizon": 128, "summary_freq": 50000, "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, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 3000000
     time_horizon: 128
     summary_freq: 50000
     threaded: false
@@ -80,7 +80,7 @@ checkpoint_settings:
   run_id: Pyramids Training
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 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] 55230 [Flags] 2 [Guid] 3789030083 [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] 55337 [Flags] 2 [Guid] 1771124001 [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
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2642:(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  0.085 seconds
+- Completed reload, in  0.084 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)
@@ -68,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.836208 ms
+UnloadTime: 1.023544 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.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 3158 frames, [32.0 KB-64.0 KB]: 12284 frames, [64.0 KB-128.0 KB]: 3326 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1109 frames, [32.0 KB-64.0 KB]: 23435 frames, [64.0 KB-128.0 KB]: 12972 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
@@ -207,28 +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]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 36 frames, [1.0 MB-2.0 MB]: 37481 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12590
+  Peak main deferred allocation count 11671
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18768 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37516 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 29.7 MB
+      Peak Block count 2
+      Peak Allocated memory 24.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37517 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.5 MB
+      Peak Allocated memory 22.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37516 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]: 18769 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 37517 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 39 frames, [1.0 MB-2.0 MB]: 37478 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]: 18768 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 37516 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
@@ -291,21 +288,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18769 frames
+      Peak usage frame count: [0-1.0 KB]: 37517 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]: 18769 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37517 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]: 18769 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 37517 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -314,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1686375302133,"processId":7249,"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":1686381186382,"processId":19476,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.35135510563850403,
-            "min": 0.3437347114086151,
-            "max": 1.2542389631271362,
-            "count": 20
+            "value": 0.13053016364574432,
+            "min": 0.13053016364574432,
+            "max": 0.34393319487571716,
+            "count": 40
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 17573.376953125,
-            "min": 17159.236328125,
-            "max": 63554.796875,
-            "count": 20
+            "value": 6543.2158203125,
+            "min": 6508.48681640625,
+            "max": 17504.82421875,
+            "count": 40
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 226.53982300884957,
+            "min": 217.42918454935622,
+            "max": 335.7635135135135,
+            "count": 40
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 51198.0,
+            "min": 46619.0,
+            "max": 51401.0,
+            "count": 40
         },
         "Pyramids.Step.mean": {
-            "value": 999999.0,
-            "min": 49959.0,
-            "max": 999999.0,
-            "count": 20
+            "value": 2999969.0,
+            "min": 1049963.0,
+            "max": 2999969.0,
+            "count": 40
         },
         "Pyramids.Step.sum": {
-            "value": 999999.0,
-            "min": 49959.0,
-            "max": 999999.0,
-            "count": 20
+            "value": 2999969.0,
+            "min": 1049963.0,
+            "max": 2999969.0,
+            "count": 40
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.5636146664619446,
-            "min": -0.08218594640493393,
-            "max": 0.5653014779090881,
-            "count": 20
+            "value": 0.8029366135597229,
+            "min": 0.5550001859664917,
+            "max": 0.8423917889595032,
+            "count": 40
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 263.2080383300781,
-            "min": -33.03874969482422,
-            "max": 263.2080383300781,
-            "count": 20
+            "value": 407.0888671875,
+            "min": 256.965087890625,
+            "max": 432.9893798828125,
+            "count": 40
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.007806922774761915,
-            "min": 0.007806922774761915,
-            "max": 0.4125056862831116,
-            "count": 20
+            "value": 0.016411546617746353,
+            "min": -0.010096848011016846,
+            "max": 0.0640997514128685,
+            "count": 40
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 3.6458330154418945,
-            "min": 3.6458330154418945,
-            "max": 165.0022735595703,
-            "count": 20
+            "value": 8.320653915405273,
+            "min": -4.907068252563477,
+            "max": 29.678184509277344,
+            "count": 40
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7557530854457775,
+            "min": 1.5966486237641122,
+            "max": 1.7725354446606203,
+            "count": 40
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 396.8001973107457,
+            "min": 236.3039963170886,
+            "max": 413.1451980918646,
+            "count": 40
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7557530854457775,
+            "min": 1.5966486237641122,
+            "max": 1.7725354446606203,
+            "count": 40
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 396.8001973107457,
+            "min": 236.3039963170886,
+            "max": 413.1451980918646,
+            "count": 40
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.016251778906775368,
+            "min": 0.015597144257745558,
+            "max": 0.034564408739219156,
+            "count": 40
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.6729020329312334,
+            "min": 3.4313717367040226,
+            "max": 5.288354537100531,
+            "count": 40
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06778426025913278,
-            "min": 0.06652670221439246,
-            "max": 0.07334119114734719,
-            "count": 20
+            "value": 0.06941192193508731,
+            "min": 0.06467020634631303,
+            "max": 0.07191291106935192,
+            "count": 40
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 1.6268222462191868,
-            "min": 1.0267766760628607,
-            "max": 1.6970636773187957,
-            "count": 20
+            "value": 1.6658861264420957,
+            "min": 1.5020420119959725,
+            "max": 1.725909865664446,
+            "count": 40
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.016569182275310998,
-            "min": 0.0012711221483666876,
-            "max": 0.01765561954096775,
-            "count": 20
+            "value": 0.015384109843699404,
+            "min": 0.012953029207141222,
+            "max": 0.01637407874148907,
+            "count": 40
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.39766037460746395,
-            "min": 0.029235809412433814,
-            "max": 0.40607924944225826,
-            "count": 20
+            "value": 0.3692186362487857,
+            "min": 0.2979196717642481,
+            "max": 0.38210905112175486,
+            "count": 40
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.581272472941665e-06,
-            "min": 7.581272472941665e-06,
-            "max": 0.00029159603851560713,
-            "count": 20
+            "value": 2.429511690195832e-06,
+            "min": 2.429511690195832e-06,
+            "max": 0.00019744786896666374,
+            "count": 40
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00018195053935059997,
-            "min": 0.00018195053935059997,
-            "max": 0.0060378704873766,
-            "count": 20
+            "value": 5.830828056469996e-05,
+            "min": 5.830828056469996e-05,
+            "max": 0.004619409360197167,
+            "count": 40
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10252705833333335,
-            "min": 0.10252705833333335,
-            "max": 0.19719867857142856,
-            "count": 20
+            "value": 0.10080980416666667,
+            "min": 0.10080980416666667,
+            "max": 0.16581594492753626,
+            "count": 40
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 2.4606494000000003,
-            "min": 2.4606494000000003,
-            "max": 4.3126234000000006,
-            "count": 20
+            "value": 2.4194353,
+            "min": 2.4194353,
+            "max": 3.9398028333333333,
+            "count": 40
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002624531275,
-            "min": 0.0002624531275,
-            "max": 0.009720147989285716,
-            "count": 20
+            "value": 9.089943624999996e-05,
+            "min": 9.089943624999996e-05,
+            "max": 0.0065850128982608705,
+            "count": 40
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0062988750599999995,
-            "min": 0.0062988750599999995,
-            "max": 0.20129107766,
-            "count": 20
+            "value": 0.002181586469999999,
+            "min": 0.002181586469999999,
+            "max": 0.15406630305000002,
+            "count": 40
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.009527774527668953,
-            "min": 0.009527774527668953,
-            "max": 0.41762715578079224,
-            "count": 20
+            "value": 0.006933924276381731,
+            "min": 0.006791813764721155,
+            "max": 0.010334798134863377,
+            "count": 40
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.22866658866405487,
-            "min": 0.22866658866405487,
-            "max": 5.846780300140381,
-            "count": 20
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 339.97972972972974,
-            "min": 338.56643356643355,
-            "max": 997.1458333333334,
-            "count": 20
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 50317.0,
-            "min": 47051.0,
-            "max": 52579.0,
-            "count": 20
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.592208142639423,
-            "min": -0.9564417197058598,
-            "max": 1.6194615204121683,
-            "count": 20
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 234.05459696799517,
-            "min": -45.90920254588127,
-            "max": 234.05459696799517,
-            "count": 20
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.592208142639423,
-            "min": -0.9564417197058598,
-            "max": 1.6194615204121683,
-            "count": 20
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 234.05459696799517,
-            "min": -45.90920254588127,
-            "max": 234.05459696799517,
-            "count": 20
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.03380435873202637,
-            "min": 0.03380435873202637,
-            "max": 6.084363122625898,
-            "count": 20
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 4.969240733607876,
-            "min": 4.969240733607876,
-            "max": 292.0494298860431,
-            "count": 20
+            "value": 0.16641418635845184,
+            "min": 0.16214092075824738,
+            "max": 0.23770035803318024,
+            "count": 40
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 40
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 40
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1686373182",
+        "start_time_seconds": "1686376080",
         "python_version": "3.10.12 (main, Jun  7 2023, 12:45:35) [GCC 9.4.0]",
-        "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",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1686375302"
+        "end_time_seconds": "1686381186"
     },
-    "total": 2119.3034031409998,
+    "total": 5105.509026824,
     "count": 1,
-    "self": 0.47542574499948387,
+    "self": 0.441498130000582,
     "children": {
         "run_training.setup": {
-            "total": 0.03698148500006937,
+            "total": 0.03876343899992207,
             "count": 1,
-            "self": 0.03698148500006937
+            "self": 0.03876343899992207
         },
         "TrainerController.start_learning": {
-            "total": 2118.790995911,
+            "total": 5105.028765255,
             "count": 1,
-            "self": 1.2670965880029144,
+            "self": 2.787783518168908,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.9749093469999934,
+                    "total": 4.312965602999611,
                     "count": 1,
-                    "self": 3.9749093469999934
+                    "self": 4.312965602999611
                 },
                 "TrainerController.advance": {
-                    "total": 2113.457703399997,
-                    "count": 63873,
-                    "self": 1.2667271999130207,
+                    "total": 5097.834866287832,
+                    "count": 131136,
+                    "self": 2.8199113848386332,
                     "children": {
                         "env_step": {
-                            "total": 1475.7471504740952,
-                            "count": 63873,
-                            "self": 1368.2087681150745,
+                            "total": 3809.999547644815,
+                            "count": 131136,
+                            "self": 3591.752417211447,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 106.81009274905068,
-                                    "count": 63873,
-                                    "self": 4.592955099020855,
+                                    "total": 216.53971534624998,
+                                    "count": 131136,
+                                    "self": 9.37691775055373,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 102.21713765002983,
-                                            "count": 62561,
-                                            "self": 102.21713765002983
+                                            "total": 207.16279759569625,
+                                            "count": 125056,
+                                            "self": 207.16279759569625
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7282896099700338,
-                                    "count": 63873,
+                                    "total": 1.7074150871176244,
+                                    "count": 131136,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2114.08891636499,
-                                            "count": 63873,
+                                            "total": 5093.981040424949,
+                                            "count": 131136,
                                             "is_parallel": true,
-                                            "self": 854.0269211289844,
+                                            "self": 1737.400396409189,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0017286979998516472,
+                                                            "total": 0.001776224000423099,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005476689993884065,
+                                                            "self": 0.0005706380006813561,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0011810290004632407,
+                                                                    "total": 0.0012055859997417429,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0011810290004632407
+                                                                    "self": 0.0012055859997417429
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.07697923999990053,
+                                                            "total": 0.08704309699987789,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006119560000570345,
+                                                            "self": 0.0005678710003849119,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00046551499985980627,
+                                                                    "total": 0.00043306200041115517,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00046551499985980627
+                                                                    "self": 0.00043306200041115517
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0740684570000667,
+                                                                    "total": 0.08425388799969369,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0740684570000667
+                                                                    "self": 0.08425388799969369
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018333119999169867,
+                                                                    "total": 0.0017882759993881336,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003654529994037148,
+                                                                    "self": 0.0003485019988147542,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001467859000513272,
+                                                                            "total": 0.0014397740005733795,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001467859000513272
+                                                                            "self": 0.0014397740005733795
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1260.0619952360055,
-                                                    "count": 63872,
+                                                    "total": 3356.5806440157603,
+                                                    "count": 131135,
                                                     "is_parallel": true,
-                                                    "self": 32.321872371902145,
+                                                    "self": 66.04875748262566,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 21.65442949095427,
-                                                            "count": 63872,
+                                                            "total": 44.59532830708031,
+                                                            "count": 131135,
                                                             "is_parallel": true,
-                                                            "self": 21.65442949095427
+                                                            "self": 44.59532830708031
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1109.908463243082,
-                                                            "count": 63872,
+                                                            "total": 3043.2339099858636,
+                                                            "count": 131135,
                                                             "is_parallel": true,
-                                                            "self": 1109.908463243082
+                                                            "self": 3043.2339099858636
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 96.17723013006707,
-                                                            "count": 63872,
+                                                            "total": 202.70264824019068,
+                                                            "count": 131135,
                                                             "is_parallel": true,
-                                                            "self": 18.477071257100533,
+                                                            "self": 40.38878473092791,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 77.70015887296654,
-                                                                    "count": 510976,
+                                                                    "total": 162.31386350926277,
+                                                                    "count": 1049080,
                                                                     "is_parallel": true,
-                                                                    "self": 77.70015887296654
+                                                                    "self": 162.31386350926277
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 636.4438257259887,
-                            "count": 63873,
-                            "self": 2.46895552301703,
+                            "total": 1285.0154072581781,
+                            "count": 131136,
+                            "self": 5.809300956127117,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 106.82426519397814,
-                                    "count": 63873,
-                                    "self": 106.61683175897815,
+                                    "total": 224.75797619306013,
+                                    "count": 131136,
+                                    "self": 224.31268628105954,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.20743343499998446,
-                                            "count": 2,
-                                            "self": 0.20743343499998446
+                                            "total": 0.44528991200058954,
+                                            "count": 4,
+                                            "self": 0.44528991200058954
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 527.1506050089936,
-                                    "count": 454,
-                                    "self": 336.0804614169881,
+                                    "total": 1054.4481301089909,
+                                    "count": 947,
+                                    "self": 678.76073158895,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 191.07014359200548,
-                                            "count": 22845,
-                                            "self": 191.07014359200548
+                                            "total": 375.6873985200409,
+                                            "count": 45561,
+                                            "self": 375.6873985200409
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.089999366551638e-07,
+                    "total": 9.899995347950608e-07,
                     "count": 1,
-                    "self": 9.089999366551638e-07
+                    "self": 9.899995347950608e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09128566700019292,
+                    "total": 0.09314885599997069,
                     "count": 1,
-                    "self": 0.0013680140000360552,
+                    "self": 0.0017387700008839602,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08991765300015686,
+                            "total": 0.09141008599908673,
                             "count": 1,
-                            "self": 0.08991765300015686
+                            "self": 0.09141008599908673
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499897,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499897.onnx",
-                "reward": null,
-                "creation_time": 1686374162.5413673,
+                "steps": 1499996,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499996.onnx",
+                "reward": 1.7666250076144934,
+                "creation_time": 1686377309.325065,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499996.pt"
+                ]
+            },
+            {
+                "steps": 1999977,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999977.onnx",
+                "reward": 1.4659999534487724,
+                "creation_time": 1686378606.959674,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499897.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1999977.pt"
                 ]
             },
             {
-                "steps": 999999,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999999.onnx",
-                "reward": 1.5879999846220016,
-                "creation_time": 1686375301.5903716,
+                "steps": 2499973,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499973.onnx",
+                "reward": 1.8709999471902847,
+                "creation_time": 1686379894.1080823,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999999.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2499973.pt"
                 ]
             },
             {
-                "steps": 1000120,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000120.onnx",
-                "reward": 1.5951999843120575,
-                "creation_time": 1686375301.6904116,
+                "steps": 2999969,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999969.onnx",
+                "reward": null,
+                "creation_time": 1686381185.8684719,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2999969.pt"
+                ]
+            },
+            {
+                "steps": 3000097,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000097.onnx",
+                "reward": null,
+                "creation_time": 1686381185.972116,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000120.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-3000097.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000120,
+            "steps": 3000097,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.5951999843120575,
-            "creation_time": 1686375301.6904116,
+            "reward": null,
+            "creation_time": 1686381185.972116,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000120.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-3000097.pt"
             ]
         }
     },