First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbf787bc93d9bda8960a35ec1574ba5d2ac1e1365c95e57eb9ba1d55b95698fe
+oid sha256:d4b9a078afccb01588fc5a5830d87ed2e19b0c8b00a6e557f55fcb45ea015a80
 size 1417437

Pyramids/{Pyramids-1000035.onnx → Pyramids-1499972.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbf787bc93d9bda8960a35ec1574ba5d2ac1e1365c95e57eb9ba1d55b95698fe
+oid sha256:e19475e2a99872290bfb3c4f0ecbd9aac57beeccc0c913ac5b32bb69343f2d80
 size 1417437

Pyramids/{Pyramids-999907.pt → Pyramids-1499972.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5ec221220705dc9573fbeb91da98a5c92deeb20facd94fda8ca65b2bc01c46
+oid sha256:87f8621c0eb4767e8506fd8b606f97d4ce6515dbf9777449cc6183a643189979
 size 8652382

Pyramids/{Pyramids-999907.onnx → Pyramids-1999906.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbf787bc93d9bda8960a35ec1574ba5d2ac1e1365c95e57eb9ba1d55b95698fe
+oid sha256:d4b9a078afccb01588fc5a5830d87ed2e19b0c8b00a6e557f55fcb45ea015a80
 size 1417437

Pyramids/{Pyramids-1000035.pt → Pyramids-1999906.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e42189730ce7d64b99c783b4364795cc36e9cf165044164e7c8cac551f06d667
+oid sha256:389416fb5406333071fbf74c90735477128af9f3702520a233486b5555ce3c71
 size 8652382

Pyramids/{Pyramids-499894.onnx → Pyramids-2000034.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c90f5b9968a51a25ce5b518e2e447123eb164a15340972856079d67e6179f9c7
+oid sha256:d4b9a078afccb01588fc5a5830d87ed2e19b0c8b00a6e557f55fcb45ea015a80
 size 1417437

Pyramids/{Pyramids-499894.pt → Pyramids-2000034.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e30830fb2551ca3a2c83468ea514f96ce8582fe4760b5716582756167f59018e
+oid sha256:4dde239ad2088d0854e54b4a9148ccfa3112b35b4b07ac16d3d8c928b6d507a9
 size 8652382

Pyramids/Pyramids-499970.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:342b35ff4a6517bc4b8485c0d42d71693d8a1a9c922b5741fffd4f45bc2cca91
+size 1417437

Pyramids/Pyramids-499970.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e824f564bfea5bba16522793969dc2a8c4f5c7d313a4155d3b8bedb26031a862
+size 8652382

Pyramids/Pyramids-999936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7184090a0b62a14055c26beaf26be88b5004361d3351abe297649baee0a3bf6a
+size 1417437

Pyramids/Pyramids-999936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dff302a2cd442f9f3a880f31afaa841a44a871cf8b0466aa3c93b896c0f4fbd
+size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e42189730ce7d64b99c783b4364795cc36e9cf165044164e7c8cac551f06d667
+oid sha256:4dde239ad2088d0854e54b4a9148ccfa3112b35b4b07ac16d3d8c928b6d507a9
 size 8652382

Pyramids/{events.out.tfevents.1673543464.bd504cca4280.5743.0 → events.out.tfevents.1673546416.bd504cca4280.17969.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42626d2918cd8f5467787c4e33cdf6a8ee8b14979708eb9970a1f47dcce54fd
-size 313832
+oid sha256:a6ff4c71635b291d5c858b175b4782589e515bf60945b5f6795b24f3ac388cf0
+size 655521

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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "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 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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 2000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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 2", "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

@@ -49,7 +49,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 500000
-    max_steps: 1000000
+    max_steps: 2000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -75,7 +75,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: Pyramids Training 2
   initialize_from: null
   load_model: false
   resume: 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) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55320 [Flags] 2 [Guid] 18765844 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.2 [Port] 55139 [Flags] 2 [Guid] 1386499345 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [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:2495:(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  0.119 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)
@@ -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: 1.147323 ms
+UnloadTime: 0.798286 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]: 4269 frames, [32.0 KB-64.0 KB]: 12519 frames, [64.0 KB-128.0 KB]: 1983 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 8682 frames, [32.0 KB-64.0 KB]: 21239 frames, [64.0 KB-128.0 KB]: 7594 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
@@ -131,12 +128,12 @@ PlayerConnection::CleanupMemory Statistics:
       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 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
@@ -149,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 480 B
+      Peak Allocated Bytes 240 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -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]: 18473 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37217 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12737
+  Peak main deferred allocation count 12723
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.6 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18771 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37515 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.7 MB
+      Peak Allocated memory 30.2 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18772 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37516 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.4 MB
+      Peak Allocated memory 23.4 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.6 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18771 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37515 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 18772 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 37516 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,16 +272,16 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.6 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18473 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37217 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 18771 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 37515 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.1 MB
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -293,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.6 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18772 frames
+      Peak usage frame count: [0-1.0 KB]: 37516 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 18772 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37516 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 18772 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 37516 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.1 KB
+  Peak Allocated memory 29.2 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673545490375,"processId":5767,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"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":1673550518939,"processId":17990,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"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

@@ -2,256 +2,256 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.6067982912063599,
-            "min": 0.5946165323257446,
-            "max": 1.492523193359375,
-            "count": 33
+            "value": 0.1671365648508072,
+            "min": 0.1671365648508072,
+            "max": 1.435519814491272,
+            "count": 66
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 18077.734375,
-            "min": 17610.1640625,
-            "max": 45277.18359375,
-            "count": 33
+            "value": 5051.53564453125,
+            "min": 5051.53564453125,
+            "max": 43547.9296875,
+            "count": 66
         },
         "Pyramids.Step.mean": {
-            "value": 989983.0,
+            "value": 1979974.0,
             "min": 29952.0,
-            "max": 989983.0,
-            "count": 33
+            "max": 1979974.0,
+            "count": 66
         },
         "Pyramids.Step.sum": {
-            "value": 989983.0,
+            "value": 1979974.0,
             "min": 29952.0,
-            "max": 989983.0,
-            "count": 33
+            "max": 1979974.0,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.3739718496799469,
-            "min": -0.10135970264673233,
-            "max": 0.39559856057167053,
-            "count": 33
+            "value": 0.5358601808547974,
+            "min": -0.11700937896966934,
+            "max": 0.7015327215194702,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 100.22445678710938,
-            "min": -24.427688598632812,
-            "max": 104.04241943359375,
-            "count": 33
+            "value": 153.25601196289062,
+            "min": -27.73122215270996,
+            "max": 205.54908752441406,
+            "count": 66
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 2.067133903503418,
-            "min": -0.17633558809757233,
-            "max": 2.5856447219848633,
-            "count": 33
+            "value": 0.016772892326116562,
+            "min": -0.028345569968223572,
+            "max": 0.5080322623252869,
+            "count": 66
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 553.9918823242188,
-            "min": -44.43656921386719,
-            "max": 680.0245361328125,
-            "count": 33
+            "value": 4.797047138214111,
+            "min": -7.596612930297852,
+            "max": 120.40364837646484,
+            "count": 66
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.0676869948469435,
-            "min": 0.0641419018465254,
-            "max": 0.07218902012876545,
-            "count": 33
+            "value": 0.06841565237846227,
+            "min": 0.06532535654130496,
+            "max": 0.07275287406912842,
+            "count": 66
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9476179278572091,
-            "min": 0.47691782939163485,
-            "max": 1.0828353019314818,
-            "count": 33
+            "value": 0.9578191332984717,
+            "min": 0.5005644435790935,
+            "max": 1.06032787480702,
+            "count": 66
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.3436576472373591,
-            "min": 0.0003787110192846611,
-            "max": 0.5421189686582822,
-            "count": 33
+            "value": 0.014863313009430255,
+            "min": 0.00020938235665503006,
+            "max": 0.017486680912914367,
+            "count": 66
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 4.811207061323027,
-            "min": 0.0038595791418566507,
-            "max": 7.589665561215952,
-            "count": 33
+            "value": 0.20808638213202357,
+            "min": 0.002721970636515391,
+            "max": 0.24481353278080115,
+            "count": 66
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.391433250507146e-06,
-            "min": 7.391433250507146e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 5.299373233575e-06,
+            "min": 5.299373233575e-06,
+            "max": 0.0002975753150939428,
+            "count": 66
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010348006550710005,
-            "min": 0.00010348006550710005,
-            "max": 0.0031406099531301,
-            "count": 33
+            "value": 7.419122527005e-05,
+            "min": 7.419122527005e-05,
+            "max": 0.003853526515491201,
+            "count": 66
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10246377857142855,
-            "min": 0.10246377857142855,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.101766425,
+            "min": 0.101766425,
+            "max": 0.19919177142857142,
+            "count": 66
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4344928999999997,
-            "min": 1.3691136000000002,
-            "max": 2.4426114000000005,
-            "count": 33
+            "value": 1.42472995,
+            "min": 1.3845568000000001,
+            "max": 2.6845087999999997,
+            "count": 66
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002561314792857144,
-            "min": 0.0002561314792857144,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 0.00018646585750000001,
+            "min": 0.00018646585750000001,
+            "max": 0.009919257965714285,
+            "count": 66
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0035858407100000014,
-            "min": 0.0035858407100000014,
-            "max": 0.10471230301,
-            "count": 33
+            "value": 0.002610522005,
+            "min": 0.002610522005,
+            "max": 0.12846242912,
+            "count": 66
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.00816297810524702,
-            "min": 0.00816297810524702,
-            "max": 0.2904655635356903,
-            "count": 33
+            "value": 0.00727482233196497,
+            "min": 0.00727482233196497,
+            "max": 0.5102919936180115,
+            "count": 66
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.11428169906139374,
-            "min": 0.11428169906139374,
-            "max": 2.0332589149475098,
-            "count": 33
+            "value": 0.10184751451015472,
+            "min": 0.10184751451015472,
+            "max": 3.5720438957214355,
+            "count": 66
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 485.5633802816901,
-            "min": 464.0327868852459,
+            "value": 301.45,
+            "min": 262.8695652173913,
             "max": 999.0,
-            "count": 33
+            "count": 66
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 34475.0,
+            "value": 30145.0,
             "min": 15984.0,
-            "max": 34475.0,
-            "count": 33
+            "max": 32926.0,
+            "count": 66
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.2326675819259294,
+            "value": 1.4984939842671157,
             "min": -1.0000000521540642,
-            "max": 1.3719704743535792,
-            "count": 33
+            "max": 1.632751289917075,
+            "count": 66
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 87.51939831674099,
+            "value": 149.84939842671156,
             "min": -32.000001668930054,
-            "max": 87.51939831674099,
-            "count": 33
+            "max": 187.76639834046364,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.2326675819259294,
+            "value": 1.4984939842671157,
             "min": -1.0000000521540642,
-            "max": 1.3719704743535792,
-            "count": 33
+            "max": 1.632751289917075,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 87.51939831674099,
+            "value": 149.84939842671156,
             "min": -32.000001668930054,
-            "max": 87.51939831674099,
-            "count": 33
+            "max": 187.76639834046364,
+            "count": 66
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.040849869856225574,
-            "min": 0.040849869856225574,
-            "max": 6.029075302183628,
-            "count": 33
+            "value": 0.023019604940782302,
+            "min": 0.02293750223749236,
+            "max": 10.073955454863608,
+            "count": 66
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 2.900340759792016,
-            "min": 2.506619504361879,
-            "max": 96.46520483493805,
-            "count": 33
+            "value": 2.30196049407823,
+            "min": 2.280451965620159,
+            "max": 161.18328727781773,
+            "count": 66
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 66
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 66
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673543461",
+        "start_time_seconds": "1673546413",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
-        "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 2 --no-graphics",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1673545490"
+        "end_time_seconds": "1673550519"
     },
-    "total": 2029.2126793460002,
+    "total": 4105.909641729999,
     "count": 1,
-    "self": 0.3863970490003794,
+    "self": 0.4249261779996232,
     "children": {
         "run_training.setup": {
-            "total": 0.17051346900007047,
+            "total": 0.10533701100030157,
             "count": 1,
-            "self": 0.17051346900007047
+            "self": 0.10533701100030157
         },
         "TrainerController.start_learning": {
-            "total": 2028.6557688279997,
+            "total": 4105.379378540999,
             "count": 1,
-            "self": 1.3633993779899356,
+            "self": 2.335072648023015,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.784951048000039,
+                    "total": 6.182917680000173,
                     "count": 1,
-                    "self": 6.784951048000039
+                    "self": 6.182917680000173
                 },
                 "TrainerController.advance": {
-                    "total": 2020.4200659870096,
-                    "count": 63361,
-                    "self": 1.352595980977867,
+                    "total": 4096.777086414975,
+                    "count": 128504,
+                    "self": 2.3665180063662774,
                     "children": {
                         "env_step": {
-                            "total": 1366.3036992300347,
-                            "count": 63361,
-                            "self": 1253.7858413500423,
+                            "total": 2804.564204866173,
+                            "count": 128504,
+                            "self": 2606.02531857308,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 111.63974775697875,
-                                    "count": 63361,
-                                    "self": 4.452627727955587,
+                                    "total": 197.0560491029837,
+                                    "count": 128504,
+                                    "self": 8.256623862006563,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 107.18712002902316,
-                                            "count": 62573,
-                                            "self": 35.45982324601346,
+                                            "total": 188.79942524097714,
+                                            "count": 125053,
+                                            "self": 64.08367310995618,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 71.7272967830097,
-                                                    "count": 62573,
-                                                    "self": 71.7272967830097
+                                                    "total": 124.71575213102096,
+                                                    "count": 125053,
+                                                    "self": 124.71575213102096
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.8781101230135846,
-                                    "count": 63361,
+                                    "total": 1.4828371901094215,
+                                    "count": 128504,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2023.9419690330164,
-                                            "count": 63361,
+                                            "total": 4096.73127901483,
+                                            "count": 128504,
                                             "is_parallel": true,
-                                            "self": 876.1969632799551,
+                                            "self": 1683.692985817922,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0025878510000438837,
+                                                            "total": 0.0016672239999024896,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008195449997856485,
+                                                            "self": 0.000595927001995733,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0017683060002582351,
+                                                                    "total": 0.0010712969979067566,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0017683060002582351
+                                                                    "self": 0.0010712969979067566
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05008789799990154,
+                                                            "total": 0.055998612000621506,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005109890000767336,
+                                                            "self": 0.0005208380016483716,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004365699999198114,
+                                                                    "total": 0.00038594799934799084,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004365699999198114
+                                                                    "self": 0.00038594799934799084
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04756104900002356,
+                                                                    "total": 0.05338423299963324,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04756104900002356
+                                                                    "self": 0.05338423299963324
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0015792899998814391,
+                                                                    "total": 0.0017075929999919026,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00040109700034918205,
+                                                                    "self": 0.0004413309989104164,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001178192999532257,
+                                                                            "total": 0.0012662620010814862,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001178192999532257
+                                                                            "self": 0.0012662620010814862
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1147.7450057530614,
-                                                    "count": 63360,
+                                                    "total": 2413.038293196908,
+                                                    "count": 128503,
                                                     "is_parallel": true,
-                                                    "self": 28.52720906920331,
+                                                    "self": 54.75101230896598,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 23.315242914941336,
-                                                            "count": 63360,
+                                                            "total": 44.80629490994579,
+                                                            "count": 128503,
                                                             "is_parallel": true,
-                                                            "self": 23.315242914941336
+                                                            "self": 44.80629490994579
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 992.1043001059743,
-                                                            "count": 63360,
+                                                            "total": 2110.9525191950434,
+                                                            "count": 128503,
                                                             "is_parallel": true,
-                                                            "self": 992.1043001059743
+                                                            "self": 2110.9525191950434
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 103.79825366294244,
-                                                            "count": 63360,
+                                                            "total": 202.52846678295282,
+                                                            "count": 128503,
                                                             "is_parallel": true,
-                                                            "self": 23.45344488607975,
+                                                            "self": 44.341408289201354,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 80.34480877686269,
-                                                                    "count": 506880,
+                                                                    "total": 158.18705849375146,
+                                                                    "count": 1028024,
                                                                     "is_parallel": true,
-                                                                    "self": 80.34480877686269
+                                                                    "self": 158.18705849375146
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 652.763770775997,
-                            "count": 63361,
-                            "self": 2.5137365659929856,
+                            "total": 1289.846363542436,
+                            "count": 128504,
+                            "self": 4.523266965513358,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 145.38694136700246,
-                                    "count": 63361,
-                                    "self": 145.1950817780023,
+                                    "total": 287.9918757849491,
+                                    "count": 128504,
+                                    "self": 287.6241151779486,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.19185958900015976,
-                                            "count": 2,
-                                            "self": 0.19185958900015976
+                                            "total": 0.3677606070004913,
+                                            "count": 4,
+                                            "self": 0.3677606070004913
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 504.8630928430016,
-                                    "count": 435,
-                                    "self": 195.32756440798903,
+                                    "total": 997.3312207919735,
+                                    "count": 916,
+                                    "self": 386.153883986045,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 309.53552843501257,
-                                            "count": 22830,
-                                            "self": 309.53552843501257
+                                            "total": 611.1773368059285,
+                                            "count": 45597,
+                                            "self": 611.1773368059285
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.249997674487531e-07,
+                    "total": 8.759998308960348e-07,
                     "count": 1,
-                    "self": 9.249997674487531e-07
+                    "self": 8.759998308960348e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0873514900004011,
+                    "total": 0.08430092200069339,
                     "count": 1,
-                    "self": 0.0017026900004566414,
+                    "self": 0.0013292070016177604,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08564879999994446,
+                            "total": 0.08297171499907563,
                             "count": 1,
-                            "self": 0.08564879999994446
+                            "self": 0.08297171499907563
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499894,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499894.onnx",
-                "reward": -0.2134666989247004,
-                "creation_time": 1673544435.4588456,
+                "steps": 499970,
+                "file_path": "results/Pyramids Training 2/Pyramids/Pyramids-499970.onnx",
+                "reward": null,
+                "creation_time": 1673547339.2827,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499894.pt"
+                    "results/Pyramids Training 2/Pyramids/Pyramids-499970.pt"
                 ]
             },
             {
-                "steps": 999907,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999907.onnx",
+                "steps": 999936,
+                "file_path": "results/Pyramids Training 2/Pyramids/Pyramids-999936.onnx",
                 "reward": null,
-                "creation_time": 1673545489.9086545,
+                "creation_time": 1673548360.08119,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999907.pt"
+                    "results/Pyramids Training 2/Pyramids/Pyramids-999936.pt"
                 ]
             },
             {
-                "steps": 1000035,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000035.onnx",
-                "reward": null,
-                "creation_time": 1673545490.0104454,
+                "steps": 1499972,
+                "file_path": "results/Pyramids Training 2/Pyramids/Pyramids-1499972.onnx",
+                "reward": 1.7519999891519547,
+                "creation_time": 1673549433.3718832,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training 2/Pyramids/Pyramids-1499972.pt"
+                ]
+            },
+            {
+                "steps": 1999906,
+                "file_path": "results/Pyramids Training 2/Pyramids/Pyramids-1999906.onnx",
+                "reward": 1.7730000168085098,
+                "creation_time": 1673550518.4805794,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training 2/Pyramids/Pyramids-1999906.pt"
+                ]
+            },
+            {
+                "steps": 2000034,
+                "file_path": "results/Pyramids Training 2/Pyramids/Pyramids-2000034.onnx",
+                "reward": 1.7730000168085098,
+                "creation_time": 1673550518.5783641,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000035.pt"
+                    "results/Pyramids Training 2/Pyramids/Pyramids-2000034.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000035,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1673545490.0104454,
+            "steps": 2000034,
+            "file_path": "results/Pyramids Training 2/Pyramids.onnx",
+            "reward": 1.7730000168085098,
+            "creation_time": 1673550518.5783641,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000035.pt"
+                "results/Pyramids Training 2/Pyramids/Pyramids-2000034.pt"
             ]
         }
     },