Third Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc2c34ac53ff71025a8cab93d7e9631d48aef2d5fcaf0470439c0c1c5755f00f
+oid sha256:ee5d300cec62072c62d917865ec940ca4328b80b2bea391c89e5859ed1f6a4f9
 size 1418184

Pyramids/{Pyramids-1499924.onnx → Pyramids-1000001.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac61f864a23c61b90b6d3dc198b5a6f082ebb683999fb19add66eea9ffac4eb
+oid sha256:ee5d300cec62072c62d917865ec940ca4328b80b2bea391c89e5859ed1f6a4f9
 size 1418184

Pyramids/{Pyramids-2499952.pt → Pyramids-1000001.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b21238b4bd5fd9bb1311a61a64353f8a431555404845a8f36778ebe022d7a2
+oid sha256:6cb99e37e293916adc28a0765cd97919dcd7f4536cac52e0252456ae7423863f
 size 8650990

Pyramids/Pyramids-1999992.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3d0abbd9c63b3873b8a62722e037345d811c25c938dae4d42d900c4a98ccd102
-size 8650990

Pyramids/Pyramids-2999924.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fc2c34ac53ff71025a8cab93d7e9631d48aef2d5fcaf0470439c0c1c5755f00f
-size 1418184

Pyramids/Pyramids-3000052.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fc2c34ac53ff71025a8cab93d7e9631d48aef2d5fcaf0470439c0c1c5755f00f
-size 1418184

Pyramids/Pyramids-3000052.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:553280eff67a5b3c4cc19dd9c2c092ecceec3510f3d3f4b7232872ca5819d7f7
-size 8650990

Pyramids/{Pyramids-2499952.onnx → Pyramids-499959.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d289eafbdaf4525f01ff7dec54b8349c1fe437290d33cab962acdefecf791a8b
+oid sha256:3ba7b79d6d14b91966e35ba5cd9a423c75f6b2be8469baac6f3ce8bf30bdc1c7
 size 1418184

Pyramids/{Pyramids-1499924.pt → Pyramids-499959.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af052f7fc24d94bdbbb40f466311598e6f03c38128bc1d6d7a9bacb5df0d014
+oid sha256:cfb87bce600c670a847ef2cb7f36d127b6359253849f64c64853d65073313128
 size 8650990

Pyramids/{Pyramids-1999992.onnx → Pyramids-999873.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d846bb6734084ccf79b86e38123a00c2cd4f6f0635e28d0b0e7a3ecc33be095
+oid sha256:ee5d300cec62072c62d917865ec940ca4328b80b2bea391c89e5859ed1f6a4f9
 size 1418184

Pyramids/{Pyramids-2999924.pt → Pyramids-999873.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36edc4e9c5bf40e975f319089f3fec347a3b4d074fc0b880034b246099a91266
+oid sha256:fc1b7b3003e30075e170cc94c61d18935441403bfd29c8d4ab6e8217af4d5da8
 size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:553280eff67a5b3c4cc19dd9c2c092ecceec3510f3d3f4b7232872ca5819d7f7
+oid sha256:6cb99e37e293916adc28a0765cd97919dcd7f4536cac52e0252456ae7423863f
 size 8650990

Pyramids/{events.out.tfevents.1681628565.f72ae4945cd6.12704.0 → events.out.tfevents.1681647205.af77deb9154e.3472.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4979033e304c4cfadab2130299785d0e7da7e18dac206c9cf7f00d0dac63c78
-size 980457
+oid sha256:2c00da396666ce0e73b085f0e44624f32a45c7e61e5390259277db4ec8b70ebb
+size 323934

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": 3000000, "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, "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": 0.02, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
           deterministic: false
       rnd:
         gamma: 0.99
-        strength: 0.01
+        strength: 0.02
         network_settings:
           normalize: false
           hidden_units: 64
@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 3000000
+    max_steps: 1000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -77,7 +77,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: Pyramids
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,11 +1,14 @@
-Mono path[0] = '/content/ml-agents/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
-Mono config path = '/content/ml-agents/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+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] 55267 [Flags] 2 [Guid] 2660571432 [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] 55318 [Flags] 2 [Guid] 4231710299 [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/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
@@ -33,7 +36,7 @@ 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  0.090 seconds
+- Completed reload, in  0.089 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -65,7 +68,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.992444 ms
+UnloadTime: 1.267351 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -73,7 +76,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 6447 frames, [32.0 KB-64.0 KB]: 33488 frames, [64.0 KB-128.0 KB]: 16338 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 6660 frames, [32.0 KB-64.0 KB]: 9388 frames, [64.0 KB-128.0 KB]: 2722 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
@@ -123,17 +126,17 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -204,28 +207,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55975 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 13175
+  Peak main deferred allocation count 12502
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 56273 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18770 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.0 MB
+      Peak Allocated memory 29.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 56274 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.3 MB
+      Peak Allocated memory 24.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -254,13 +257,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 56273 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18770 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]: 56274 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,13 +275,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55975 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 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]: 56273 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18770 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -290,19 +293,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 56274 frames
+      Peak usage frame count: [0-1.0 KB]: 18771 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]: 56274 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18771 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]: 56274 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18771 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -311,4 +314,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1681636123260,"processId":12724,"allocatedMemory":1970163,"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":3477},{"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":1681649600324,"processId":3492,"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": 0.15028825402259827,
-            "min": 0.13628928363323212,
-            "max": 1.4530024528503418,
-            "count": 100
+            "value": 0.4559151828289032,
+            "min": 0.4422323703765869,
+            "max": 1.4052366018295288,
+            "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 4571.16748046875,
-            "min": 4127.9296875,
-            "max": 44078.28125,
-            "count": 100
+            "value": 13582.625,
+            "min": 13274.046875,
+            "max": 42629.2578125,
+            "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 2999924.0,
-            "min": 29985.0,
-            "max": 2999924.0,
-            "count": 100
+            "value": 989988.0,
+            "min": 29952.0,
+            "max": 989988.0,
+            "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 2999924.0,
-            "min": 29985.0,
-            "max": 2999924.0,
-            "count": 100
+            "value": 989988.0,
+            "min": 29952.0,
+            "max": 989988.0,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.775213360786438,
-            "min": -0.11173892766237259,
-            "max": 0.8763826489448547,
-            "count": 100
+            "value": 0.48993533849716187,
+            "min": -0.11382244527339935,
+            "max": 0.511127233505249,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 227.9127197265625,
-            "min": -26.929080963134766,
-            "max": 262.7988586425781,
-            "count": 100
+            "value": 134.24227905273438,
+            "min": -27.431209564208984,
+            "max": 141.0711212158203,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.004806601442396641,
-            "min": -0.06742094457149506,
-            "max": 0.35290655493736267,
-            "count": 100
+            "value": 0.029282841831445694,
+            "min": 0.029282841831445694,
+            "max": 0.5828818082809448,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 1.4131407737731934,
-            "min": -17.933971405029297,
-            "max": 83.99176025390625,
-            "count": 100
+            "value": 8.02349853515625,
+            "min": 8.02349853515625,
+            "max": 139.89163208007812,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.07180016206187846,
-            "min": 0.06209282546511128,
-            "max": 0.07441218909814841,
-            "count": 100
+            "value": 0.06744790576132281,
+            "min": 0.06498703005743546,
+            "max": 0.07305000646628279,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 1.077002430928177,
-            "min": 0.49200265078812744,
-            "max": 1.090765496177197,
-            "count": 100
+            "value": 0.9442706806585194,
+            "min": 0.488342339750018,
+            "max": 1.0373851726608871,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.015771305755890138,
-            "min": 0.0009254115546579213,
-            "max": 0.01738545046966811,
-            "count": 100
+            "value": 0.014664451570189113,
+            "min": 0.0011588689386030318,
+            "max": 0.015088778200653656,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.23656958633835207,
-            "min": 0.012955761765210898,
-            "max": 0.24619345302926376,
-            "count": 100
+            "value": 0.20530232198264758,
+            "min": 0.012988580887551882,
+            "max": 0.21130263393085139,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 1.500966166377776e-06,
-            "min": 1.500966166377776e-06,
-            "max": 0.00029838354339596195,
-            "count": 100
+            "value": 7.525597491499999e-06,
+            "min": 7.525597491499999e-06,
+            "max": 0.00029515063018788575,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 2.251449249566664e-05,
-            "min": 2.251449249566664e-05,
-            "max": 0.0039274984908338655,
-            "count": 100
+            "value": 0.00010535836488099998,
+            "min": 0.00010535836488099998,
+            "max": 0.003633921488692899,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10050028888888889,
-            "min": 0.10050028888888889,
-            "max": 0.19946118095238097,
-            "count": 100
+            "value": 0.10250849999999999,
+            "min": 0.10250849999999999,
+            "max": 0.19838354285714285,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.5075043333333333,
-            "min": 1.3962282666666668,
-            "max": 2.752564133333333,
-            "count": 100
+            "value": 1.4351189999999998,
+            "min": 1.3691136000000002,
+            "max": 2.6113071,
+            "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 5.997885999999993e-05,
-            "min": 5.997885999999993e-05,
-            "max": 0.009946171977142856,
-            "count": 100
+            "value": 0.00026059915000000003,
+            "min": 0.00026059915000000003,
+            "max": 0.00983851593142857,
+            "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.000899682899999999,
-            "min": 0.000899682899999999,
-            "max": 0.13092569672,
-            "count": 100
+            "value": 0.0036483881000000007,
+            "min": 0.0036483881000000007,
+            "max": 0.12114957929,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.006179341580718756,
-            "min": 0.005584712605923414,
-            "max": 0.3742859661579132,
-            "count": 100
+            "value": 0.016887223348021507,
+            "min": 0.016887223348021507,
+            "max": 0.4436214566230774,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.0926901251077652,
-            "min": 0.07818597555160522,
-            "max": 2.620001792907715,
-            "count": 100
+            "value": 0.236421138048172,
+            "min": 0.236421138048172,
+            "max": 3.1053502559661865,
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 225.94615384615383,
-            "min": 209.05755395683454,
-            "max": 997.96875,
-            "count": 100
+            "value": 376.775,
+            "min": 376.2470588235294,
+            "max": 999.0,
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29373.0,
-            "min": 16784.0,
-            "max": 34455.0,
-            "count": 100
+            "value": 30142.0,
+            "min": 15984.0,
+            "max": 32920.0,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.7586630687117577,
-            "min": -0.9363875531125814,
-            "max": 1.7809774276233257,
-            "count": 100
+            "value": 1.5414419560520738,
+            "min": -1.0000000521540642,
+            "max": 1.5766776216380736,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 228.6261989325285,
-            "min": -29.964401699602604,
-            "max": 245.13619814813137,
-            "count": 100
+            "value": 124.85679844021797,
+            "min": -32.000001668930054,
+            "max": 134.01759783923626,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.7586630687117577,
-            "min": -0.9363875531125814,
-            "max": 1.7809774276233257,
-            "count": 100
+            "value": 1.5414419560520738,
+            "min": -1.0000000521540642,
+            "max": 1.5766776216380736,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 228.6261989325285,
-            "min": -29.964401699602604,
-            "max": 245.13619814813137,
-            "count": 100
+            "value": 124.85679844021797,
+            "min": -32.000001668930054,
+            "max": 134.01759783923626,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.014618397399653286,
-            "min": 0.012806391585533728,
-            "max": 7.132044997285394,
-            "count": 100
+            "value": 0.13358603501448085,
+            "min": 0.13358603501448085,
+            "max": 15.834431545808911,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 1.9003916619549273,
-            "min": 1.7248815242637647,
-            "max": 121.2447649538517,
-            "count": 100
+            "value": 10.82046883617295,
+            "min": 9.927237732510548,
+            "max": 253.35090473294258,
+            "count": 33
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 100
+            "count": 33
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 100
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1681628564",
+        "start_time_seconds": "1681647204",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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 /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --no-graphics",
         "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": "1681636123"
+        "end_time_seconds": "1681649600"
     },
-    "total": 7559.148627760999,
+    "total": 2396.1113926949997,
     "count": 1,
-    "self": 0.4770450799996979,
+    "self": 0.909659716999613,
     "children": {
         "run_training.setup": {
-            "total": 0.12020545999985188,
+            "total": 0.11602401300001475,
             "count": 1,
-            "self": 0.12020545999985188
+            "self": 0.11602401300001475
         },
         "TrainerController.start_learning": {
-            "total": 7558.551377221,
+            "total": 2395.085708965,
             "count": 1,
-            "self": 4.706374739901548,
+            "self": 1.996679792026498,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.859987935999925,
+                    "total": 4.098378780999951,
                     "count": 1,
-                    "self": 4.859987935999925
+                    "self": 4.098378780999951
                 },
                 "TrainerController.advance": {
-                    "total": 7548.888584849101,
-                    "count": 195256,
-                    "self": 4.855284335072611,
+                    "total": 2388.830204293973,
+                    "count": 63738,
+                    "self": 2.0129098109368897,
                     "children": {
                         "env_step": {
-                            "total": 5639.4698552920745,
-                            "count": 195256,
-                            "self": 5286.642067047201,
+                            "total": 1743.9614275100366,
+                            "count": 63738,
+                            "self": 1605.7994242030586,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 349.79841155093254,
-                                    "count": 195256,
-                                    "self": 15.868053174926445,
+                                    "total": 136.91944303600337,
+                                    "count": 63738,
+                                    "self": 5.6998883750188725,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 333.9303583760061,
-                                            "count": 187580,
-                                            "self": 333.9303583760061
+                                            "total": 131.2195546609845,
+                                            "count": 62569,
+                                            "self": 131.2195546609845
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 3.0293766939412308,
-                                    "count": 195256,
+                                    "total": 1.2425602709747636,
+                                    "count": 63738,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 7540.8466218293,
-                                            "count": 195256,
+                                            "total": 2388.6352776790027,
+                                            "count": 63738,
                                             "is_parallel": true,
-                                            "self": 2630.004492781485,
+                                            "self": 921.8071001679627,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0019528179996086692,
+                                                            "total": 0.006126612000002751,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006659030000264465,
+                                                            "self": 0.004685610000251472,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0012869149995822227,
+                                                                    "total": 0.001441001999751279,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0012869149995822227
+                                                                    "self": 0.001441001999751279
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.07461918700028036,
+                                                            "total": 0.051761601999942286,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005821660001856799,
+                                                            "self": 0.0006463089998760552,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005055819997323852,
+                                                                    "total": 0.0005826740000429709,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005055819997323852
+                                                                    "self": 0.0005826740000429709
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.07164154600013717,
+                                                                    "total": 0.048374417999980324,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.07164154600013717
+                                                                    "self": 0.048374417999980324
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001889893000225129,
+                                                                    "total": 0.0021582010000429364,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004852750012105389,
+                                                                    "self": 0.0005100459999312079,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014046179990145902,
+                                                                            "total": 0.0016481550001117284,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014046179990145902
+                                                                            "self": 0.0016481550001117284
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 4910.8421290478145,
-                                                    "count": 195255,
+                                                    "total": 1466.82817751104,
+                                                    "count": 63737,
                                                     "is_parallel": true,
-                                                    "self": 102.33124459885039,
+                                                    "self": 36.63106474803635,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 75.48990465689576,
-                                                            "count": 195255,
+                                                            "total": 26.225539284004867,
+                                                            "count": 63737,
                                                             "is_parallel": true,
-                                                            "self": 75.48990465689576
+                                                            "self": 26.225539284004867
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 4419.782575011996,
-                                                            "count": 195255,
+                                                            "total": 1293.5296550399603,
+                                                            "count": 63737,
                                                             "is_parallel": true,
-                                                            "self": 4419.782575011996
+                                                            "self": 1293.5296550399603
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 313.23840478007105,
-                                                            "count": 195255,
+                                                            "total": 110.44191843903843,
+                                                            "count": 63737,
                                                             "is_parallel": true,
-                                                            "self": 68.9859682451256,
+                                                            "self": 24.89603632997739,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 244.25243653494545,
-                                                                    "count": 1562040,
+                                                                    "total": 85.54588210906104,
+                                                                    "count": 509896,
                                                                     "is_parallel": true,
-                                                                    "self": 244.25243653494545
+                                                                    "self": 85.54588210906104
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1904.5634452219538,
-                            "count": 195256,
-                            "self": 9.08374154378589,
+                            "total": 642.8558669729996,
+                            "count": 63738,
+                            "self": 3.6148124689850647,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 355.65531858921076,
-                                    "count": 195256,
-                                    "self": 355.0060678342106,
+                                    "total": 118.86801613701584,
+                                    "count": 63738,
+                                    "self": 118.53411737401541,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.6492507550001392,
-                                            "count": 6,
-                                            "self": 0.6492507550001392
+                                            "total": 0.333898763000434,
+                                            "count": 2,
+                                            "self": 0.333898763000434
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1539.8243850889571,
-                                    "count": 1398,
-                                    "self": 985.021096393984,
+                                    "total": 520.3730383669987,
+                                    "count": 450,
+                                    "self": 331.7025403050093,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 554.8032886949732,
-                                            "count": 68385,
-                                            "self": 554.8032886949732
+                                            "total": 188.6704980619894,
+                                            "count": 22770,
+                                            "self": 188.6704980619894
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.419982234248891e-07,
+                    "total": 1.3459998626785818e-06,
                     "count": 1,
-                    "self": 9.419982234248891e-07
+                    "self": 1.3459998626785818e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09642875399913464,
+                    "total": 0.16044475200033048,
                     "count": 1,
-                    "self": 0.0014697320002596825,
+                    "self": 0.0020525010004348587,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09495902199887496,
+                            "total": 0.15839225099989562,
                             "count": 1,
-                            "self": 0.09495902199887496
+                            "self": 0.15839225099989562
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 1499924,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499924.onnx",
-                "reward": 1.427236321297559,
-                "creation_time": 1681632076.6298258,
+                "steps": 499959,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-499959.onnx",
+                "reward": null,
+                "creation_time": 1681648335.0146089,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1499924.pt"
+                    "results/Pyramids/Pyramids/Pyramids-499959.pt"
                 ]
             },
             {
-                "steps": 1999992,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999992.onnx",
-                "reward": 1.74125000461936,
-                "creation_time": 1681633392.9655871,
+                "steps": 999873,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-999873.onnx",
+                "reward": 1.3980000093579292,
+                "creation_time": 1681649599.2990875,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1999992.pt"
+                    "results/Pyramids/Pyramids/Pyramids-999873.pt"
                 ]
             },
             {
-                "steps": 2499952,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499952.onnx",
-                "reward": 1.7259999811649323,
-                "creation_time": 1681634741.9137526,
+                "steps": 1000001,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-1000001.onnx",
+                "reward": 1.3980000093579292,
+                "creation_time": 1681649599.4752176,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-2499952.pt"
-                ]
-            },
-            {
-                "steps": 2999924,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999924.onnx",
-                "reward": 1.56899993121624,
-                "creation_time": 1681636122.6986294,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-2999924.pt"
-                ]
-            },
-            {
-                "steps": 3000052,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000052.onnx",
-                "reward": 1.56899993121624,
-                "creation_time": 1681636122.8044143,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-3000052.pt"
+                    "results/Pyramids/Pyramids/Pyramids-1000001.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 3000052,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.56899993121624,
-            "creation_time": 1681636122.8044143,
+            "steps": 1000001,
+            "file_path": "results/Pyramids/Pyramids.onnx",
+            "reward": 1.3980000093579292,
+            "creation_time": 1681649599.4752176,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-3000052.pt"
+                "results/Pyramids/Pyramids/Pyramids-1000001.pt"
             ]
         }
     },