PyramidsRND initial training

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39444e8e1addf713683670ceaa81ff9d5ee0e9c19491261a42cb4b22f13368cd
+oid sha256:a36b96a37ca1d315cd61b235930bd88fade7bc89721c58943e33e73295009c8b
 size 1417437

Pyramids/{Pyramids-1000033.onnx → Pyramids-1499956.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39444e8e1addf713683670ceaa81ff9d5ee0e9c19491261a42cb4b22f13368cd
+oid sha256:021ff5a7cf548cd190c12269969cf4b9d5a23398d1d6c1d1113f7b188d3127c4
 size 1417437

Pyramids/{Pyramids-999963.pt → Pyramids-1499956.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c031809d514029163c9b25c534b096b1f6c4f87f7d454168adfdadb321d104a
+oid sha256:9f7ecb9b0c320517ba0716187b22cbbb2d5953506b87b9670f2fba307047f34c
 size 8652382

Pyramids/{Pyramids-999963.onnx → Pyramids-1999953.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39444e8e1addf713683670ceaa81ff9d5ee0e9c19491261a42cb4b22f13368cd
+oid sha256:a36b96a37ca1d315cd61b235930bd88fade7bc89721c58943e33e73295009c8b
 size 1417437

Pyramids/{Pyramids-1000033.pt → Pyramids-1999953.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67788fc26cc0dbf66d64dff9bde495e4c1877b87ae9c268e4db29cb678fb022d
+oid sha256:94873b0bf518c10f301e356fc3e736115d2b18e77ef4e5df7bddb57028f74563
 size 8652382

Pyramids/{Pyramids-499958.onnx → Pyramids-2000081.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c3aa33249e23404d1d88b56091681f8094e079b0ba195ca274dd99831a98696
+oid sha256:a36b96a37ca1d315cd61b235930bd88fade7bc89721c58943e33e73295009c8b
 size 1417437

Pyramids/{Pyramids-499958.pt → Pyramids-2000081.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8cfeba79e6e53c165dbf08c0ad067b16e4eefdf7cdc9845ce930782e6299aef
+oid sha256:73d4a75be774728b9f15185ebc535cee2de3c55b7aa8278ced5a2ba28ddb747f
 size 8652382

Pyramids/Pyramids-499891.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8dc8e7bce2dad522c529336de49791a1c775ca728b1b45818fc6a411051cc2d
+size 1417437

Pyramids/Pyramids-499891.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c94b07a3dc80476a2bfccf92b9ff923896bd5b46f8a82de60100cbdbf5696ed4
+size 8652382

Pyramids/Pyramids-999988.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1060e43cddd44dc93a6c85ef36cacef868a147776d23fe80b71535d12c5bd2a6
+size 1417437

Pyramids/Pyramids-999988.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df04dd9d72e3b35549dc7bfdf9c8b0acfbaa3b7aa3e705d0ad0efad628343707
+size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67788fc26cc0dbf66d64dff9bde495e4c1877b87ae9c268e4db29cb678fb022d
+oid sha256:73d4a75be774728b9f15185ebc535cee2de3c55b7aa8278ced5a2ba28ddb747f
 size 8652382

Pyramids/{events.out.tfevents.1673528808.26233154d771.10628.0 → events.out.tfevents.1673620321.ffb8d9a6a8c2.2138.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f4590bdf38968b5d9a8c37cb935c528e5edaaabeb56aa67677e1cc8dc9bcea6
-size 305129
+oid sha256:5fd65abca3e17d451efe13cc5f4119f1531cf1440af46d87b27c481927974f85
+size 525173

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", "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

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55467 [Flags] 2 [Guid] 3270381840 [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] 55410 [Flags] 2 [Guid] 3107314465 [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
@@ -36,7 +36,7 @@ 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  0.082 seconds
+- Completed reload, in  0.079 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 +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: 0.735338 ms
+UnloadTime: 0.749062 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 +76,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 4567 frames, [32.0 KB-64.0 KB]: 10936 frames, [64.0 KB-128.0 KB]: 3264 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 10126 frames, [32.0 KB-64.0 KB]: 17718 frames, [64.0 KB-128.0 KB]: 9672 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 +131,12 @@ PlayerConnection::CleanupMemory Statistics:
       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 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -186,12 +186,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       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 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -207,28 +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]: 18469 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37218 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 12850
+  Peak main deferred allocation count 12989
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      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]: 18767 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 243 frames, [16.0 MB-32.0 MB]: 37274 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.9 MB
+      Peak Allocated memory 28.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18768 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37517 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.6 MB
+      Peak Allocated memory 24.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +255,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18767 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37516 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 18768 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 37517 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,15 +273,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      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]: 18469 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37218 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]: 18767 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 37516 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -291,21 +291,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18768 frames
+      Peak usage frame count: [0-1.0 KB]: 37517 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 18768 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37517 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 18768 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 37517 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -314,4 +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":1673530772218,"processId":10645,"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":1673624710575,"processId":2155,"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

@@ -2,189 +2,189 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.31749632954597473,
-            "min": 0.31628549098968506,
-            "max": 1.434346318244934,
-            "count": 33
+            "value": 0.2071920931339264,
+            "min": 0.201755091547966,
+            "max": 1.4341418743133545,
+            "count": 66
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 9504.5703125,
-            "min": 9504.5703125,
-            "max": 43512.328125,
-            "count": 33
+            "value": 6232.33837890625,
+            "min": 6030.05615234375,
+            "max": 43506.12890625,
+            "count": 66
         },
         "Pyramids.Step.mean": {
-            "value": 989878.0,
+            "value": 1979889.0,
             "min": 29952.0,
-            "max": 989878.0,
-            "count": 33
+            "max": 1979889.0,
+            "count": 66
         },
         "Pyramids.Step.sum": {
-            "value": 989878.0,
+            "value": 1979889.0,
             "min": 29952.0,
-            "max": 989878.0,
-            "count": 33
+            "max": 1979889.0,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.6455972194671631,
-            "min": -0.1168774738907814,
-            "max": 0.6455972194671631,
-            "count": 33
+            "value": 0.8243393301963806,
+            "min": -0.09622462093830109,
+            "max": 0.9279937148094177,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 182.70401000976562,
-            "min": -28.050594329833984,
-            "max": 182.70401000976562,
-            "count": 33
+            "value": 248.9504852294922,
+            "min": -23.190134048461914,
+            "max": 290.4620361328125,
+            "count": 66
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.0038588286843150854,
-            "min": -0.012985886074602604,
-            "max": 0.342542827129364,
-            "count": 33
+            "value": 0.011662246659398079,
+            "min": -0.07439544796943665,
+            "max": 0.31239381432533264,
+            "count": 66
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -1.0920485258102417,
-            "min": -3.467231512069702,
-            "max": 81.18264770507812,
-            "count": 33
+            "value": 3.521998405456543,
+            "min": -21.42588996887207,
+            "max": 75.28691101074219,
+            "count": 66
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06685160312783502,
-            "min": 0.06489947712954457,
-            "max": 0.07449346778291922,
-            "count": 33
+            "value": 0.06858035875068577,
+            "min": 0.06510530802738725,
+            "max": 0.07328678109514018,
+            "count": 66
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9359224437896901,
-            "min": 0.5214542744804346,
-            "max": 1.0712448345193657,
-            "count": 33
+            "value": 0.9601250225096009,
+            "min": 0.5068921602656262,
+            "max": 1.0789347016446604,
+            "count": 66
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01624618123269331,
-            "min": 0.0007064353986446451,
-            "max": 0.01673300117124907,
-            "count": 33
+            "value": 0.016518163341624176,
+            "min": 0.000323967105224438,
+            "max": 0.017910530448879643,
+            "count": 66
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.22744653725770633,
-            "min": 0.008477224783735741,
-            "max": 0.25099501756873605,
-            "count": 33
+            "value": 0.23125428678273846,
+            "min": 0.002915703947019942,
+            "max": 0.250747426284315,
+            "count": 66
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.381340396728573e-06,
-            "min": 7.381340396728573e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 5.334291079078573e-06,
+            "min": 5.334291079078573e-06,
+            "max": 0.0002975753150939428,
+            "count": 66
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010333876555420002,
-            "min": 0.00010333876555420002,
-            "max": 0.0032595956134681995,
-            "count": 33
+            "value": 7.468007510710002e-05,
+            "min": 7.468007510710002e-05,
+            "max": 0.0037903268865577496,
+            "count": 66
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10246041428571429,
-            "min": 0.10246041428571429,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.1017780642857143,
+            "min": 0.1017780642857143,
+            "max": 0.19919177142857142,
+            "count": 66
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4344458,
-            "min": 1.3886848,
-            "max": 2.4430154999999996,
-            "count": 33
+            "value": 1.4248929000000001,
+            "min": 1.3943424,
+            "max": 2.6634422500000006,
+            "count": 66
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002557953871428572,
-            "min": 0.0002557953871428572,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 0.00018762862214285718,
+            "min": 0.00018762862214285718,
+            "max": 0.009919257965714285,
+            "count": 66
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0035811354200000005,
-            "min": 0.0035811354200000005,
-            "max": 0.10867452681999999,
-            "count": 33
+            "value": 0.0026268007100000005,
+            "min": 0.0026268007100000005,
+            "max": 0.12635788077500001,
+            "count": 66
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.014713412150740623,
-            "min": 0.014713412150740623,
-            "max": 0.4901486933231354,
-            "count": 33
+            "value": 0.008229024708271027,
+            "min": 0.007826493121683598,
+            "max": 0.4388757348060608,
+            "count": 66
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.20598776638507843,
-            "min": 0.20598776638507843,
-            "max": 3.4310407638549805,
-            "count": 33
+            "value": 0.11520634591579437,
+            "min": 0.10957090556621552,
+            "max": 3.0721302032470703,
+            "count": 66
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 311.4845360824742,
-            "min": 298.2736842105263,
+            "value": 220.4962962962963,
+            "min": 203.6993006993007,
             "max": 999.0,
-            "count": 33
+            "count": 66
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30214.0,
+            "value": 29767.0,
             "min": 15984.0,
-            "max": 32564.0,
-            "count": 33
+            "max": 33082.0,
+            "count": 66
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.6678886438153453,
+            "value": 1.7795036924106102,
             "min": -1.0000000521540642,
-            "max": 1.7008144079717165,
-            "count": 33
+            "max": 1.7966783059226883,
+            "count": 66
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 161.7851984500885,
-            "min": -32.000001668930054,
-            "max": 171.49519822001457,
-            "count": 33
+            "value": 240.2329984754324,
+            "min": -31.998801663517952,
+            "max": 267.112998560071,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.6678886438153453,
+            "value": 1.7795036924106102,
             "min": -1.0000000521540642,
-            "max": 1.7008144079717165,
-            "count": 33
+            "max": 1.7966783059226883,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 161.7851984500885,
-            "min": -32.000001668930054,
-            "max": 171.49519822001457,
-            "count": 33
+            "value": 240.2329984754324,
+            "min": -31.998801663517952,
+            "max": 267.112998560071,
+            "count": 66
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.04730263440680724,
-            "min": 0.04710952983495142,
-            "max": 9.47126466408372,
-            "count": 33
+            "value": 0.01889126900124312,
+            "min": 0.01764048443792935,
+            "max": 9.110685833729804,
+            "count": 66
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 4.588355537460302,
-            "min": 4.475405334320385,
-            "max": 151.5402346253395,
-            "count": 33
+            "value": 2.550321315167821,
+            "min": 2.4585653777612606,
+            "max": 145.77097333967686,
+            "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": "1673528805",
+        "start_time_seconds": "1673620315",
         "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",
         "mlagents_version": "0.29.0.dev0",
@@ -192,66 +192,66 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1673530772"
+        "end_time_seconds": "1673624710"
     },
-    "total": 1966.3738996270004,
+    "total": 4395.093876395001,
     "count": 1,
-    "self": 0.49645739900006447,
+    "self": 0.4241593910010124,
     "children": {
         "run_training.setup": {
-            "total": 0.10579771199991228,
+            "total": 0.11400399699999753,
             "count": 1,
-            "self": 0.10579771199991228
+            "self": 0.11400399699999753
         },
         "TrainerController.start_learning": {
-            "total": 1965.7716445160004,
+            "total": 4394.555713007,
             "count": 1,
-            "self": 1.0602195659812423,
+            "self": 2.4842224960120802,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.199408854000012,
+                    "total": 9.521725463999985,
                     "count": 1,
-                    "self": 6.199408854000012
+                    "self": 9.521725463999985
                 },
                 "TrainerController.advance": {
-                    "total": 1958.4230408650187,
-                    "count": 63998,
-                    "self": 1.132667132023471,
+                    "total": 4382.457732749988,
+                    "count": 129598,
+                    "self": 2.6425799711014406,
                     "children": {
                         "env_step": {
-                            "total": 1310.3801226359706,
-                            "count": 63998,
-                            "self": 1213.9086770880385,
+                            "total": 3061.4848862749936,
+                            "count": 129598,
+                            "self": 2858.441981782051,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 95.7857063379688,
-                                    "count": 63998,
-                                    "self": 3.9717181050377803,
+                                    "total": 201.47308610696194,
+                                    "count": 129598,
+                                    "self": 8.28559791601623,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 91.81398823293102,
-                                            "count": 62558,
-                                            "self": 31.29640524986371,
+                                            "total": 193.18748819094571,
+                                            "count": 125056,
+                                            "self": 65.43051573290359,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 60.517582983067314,
-                                                    "count": 62558,
-                                                    "self": 60.517582983067314
+                                                    "total": 127.75697245804213,
+                                                    "count": 125056,
+                                                    "self": 127.75697245804213
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.6857392099632307,
-                                    "count": 63998,
+                                    "total": 1.5698183859809092,
+                                    "count": 129598,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1961.749911086988,
-                                            "count": 63998,
+                                            "total": 4386.382064792113,
+                                            "count": 129598,
                                             "is_parallel": true,
-                                            "self": 837.9497522929596,
+                                            "self": 1720.7778098162344,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0016201389998968807,
+                                                            "total": 0.005104625999990731,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005881719994249579,
+                                                            "self": 0.0029805739999915204,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0010319670004719228,
+                                                                    "total": 0.0021240519999992102,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0010319670004719228
+                                                                    "self": 0.0021240519999992102
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04600281200009704,
+                                                            "total": 0.043102734999990844,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00046246700003393926,
+                                                            "self": 0.0004890889999842329,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00041897900018739165,
+                                                                    "total": 0.0004396570000153588,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00041897900018739165
+                                                                    "self": 0.0004396570000153588
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.043566015000124025,
+                                                                    "total": 0.04056606300002841,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.043566015000124025
+                                                                    "self": 0.04056606300002841
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0015553509997516812,
+                                                                    "total": 0.0016079259999628448,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003953139994337107,
+                                                                    "self": 0.00040968699994436975,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0011600370003179705,
+                                                                            "total": 0.001198239000018475,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0011600370003179705
+                                                                            "self": 0.001198239000018475
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1123.8001587940284,
-                                                    "count": 63997,
+                                                    "total": 2665.6042549758786,
+                                                    "count": 129597,
                                                     "is_parallel": true,
-                                                    "self": 26.777156282080796,
+                                                    "self": 55.36691782582648,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 21.308974685993235,
-                                                            "count": 63997,
+                                                            "total": 42.91561223704417,
+                                                            "count": 129597,
                                                             "is_parallel": true,
-                                                            "self": 21.308974685993235
+                                                            "self": 42.91561223704417
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 979.8572306959586,
-                                                            "count": 63997,
+                                                            "total": 2367.501065414963,
+                                                            "count": 129597,
                                                             "is_parallel": true,
-                                                            "self": 979.8572306959586
+                                                            "self": 2367.501065414963
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 95.85679712999581,
-                                                            "count": 63997,
+                                                            "total": 199.82065949804507,
+                                                            "count": 129597,
                                                             "is_parallel": true,
-                                                            "self": 20.548404130039216,
+                                                            "self": 43.54814323008969,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 75.3083929999566,
-                                                                    "count": 511976,
+                                                                    "total": 156.27251626795538,
+                                                                    "count": 1036776,
                                                                     "is_parallel": true,
-                                                                    "self": 75.3083929999566
+                                                                    "self": 156.27251626795538
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 646.9102510970247,
-                            "count": 63998,
-                            "self": 1.9911681770117866,
+                            "total": 1318.3302665038937,
+                            "count": 129598,
+                            "self": 4.844167717961227,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 140.85580570400953,
-                                    "count": 63998,
-                                    "self": 140.67063031000998,
+                                    "total": 292.83526258293523,
+                                    "count": 129598,
+                                    "self": 292.46484278993603,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.1851753939995433,
-                                            "count": 2,
-                                            "self": 0.1851753939995433
+                                            "total": 0.3704197929992006,
+                                            "count": 4,
+                                            "self": 0.3704197929992006
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 504.06327721600337,
-                                    "count": 445,
-                                    "self": 194.87653440804206,
+                                    "total": 1020.6508362029972,
+                                    "count": 917,
+                                    "self": 392.9678273220085,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 309.1867428079613,
-                                            "count": 22827,
-                                            "self": 309.1867428079613
+                                            "total": 627.6830088809887,
+                                            "count": 45675,
+                                            "self": 627.6830088809887
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.180004442692734e-07,
+                    "total": 8.609995347796939e-07,
                     "count": 1,
-                    "self": 8.180004442692734e-07
+                    "self": 8.609995347796939e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0889744129999599,
+                    "total": 0.09203143600007024,
                     "count": 1,
-                    "self": 0.0014549489997079945,
+                    "self": 0.0015091730001586257,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.0875194640002519,
+                            "total": 0.09052226299991162,
                             "count": 1,
-                            "self": 0.0875194640002519
+                            "self": 0.09052226299991162
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499958,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499958.onnx",
-                "reward": 1.3272499591112137,
-                "creation_time": 1673529726.5166636,
+                "steps": 499891,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499891.onnx",
+                "reward": 1.2749999314546585,
+                "creation_time": 1673621267.9806664,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499958.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499891.pt"
                 ]
             },
             {
-                "steps": 999963,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999963.onnx",
-                "reward": 1.8639999777078629,
-                "creation_time": 1673530771.6924765,
+                "steps": 999988,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999988.onnx",
+                "reward": 1.1575599789619446,
+                "creation_time": 1673622356.0174062,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999963.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999988.pt"
                 ]
             },
             {
-                "steps": 1000033,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000033.onnx",
-                "reward": 1.8974999859929085,
-                "creation_time": 1673530771.7897606,
+                "steps": 1499956,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499956.onnx",
+                "reward": 1.7286666880051296,
+                "creation_time": 1673623531.6753519,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000033.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1499956.pt"
+                ]
+            },
+            {
+                "steps": 1999953,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999953.onnx",
+                "reward": 1.617000013589859,
+                "creation_time": 1673624710.1036067,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999953.pt"
+                ]
+            },
+            {
+                "steps": 2000081,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2000081.onnx",
+                "reward": 1.617000013589859,
+                "creation_time": 1673624710.2094188,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2000081.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000033,
+            "steps": 2000081,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.8974999859929085,
-            "creation_time": 1673530771.7897606,
+            "reward": 1.617000013589859,
+            "creation_time": 1673624710.2094188,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000033.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-2000081.pt"
             ]
         }
     },