Locally trained

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003015df141158aa5333077b185bdc06a011a964722a389e39b567ced2da4db1
+oid sha256:c136839c50c43d1a89ca20e4fb52160d94487a11dd62162f3fc51a7f9f412504
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b02ec6202b61d479ed1385f34db5e5a565fd3d852fe00ea8bff8e7d3cdc092
+oid sha256:5aff8db18b71c793eb658b5d68e22611328fcae92e46c0c8955cfd24c0f81cbb
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a2f6150c28114ccd04b78c6fa526b02653ba5053b8781f4505223fe3f1d7645
+oid sha256:1f1a713735f71a7ca16ae0937913ec6128773e1321279f992a0667c8a4888624
 size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003015df141158aa5333077b185bdc06a011a964722a389e39b567ced2da4db1
+oid sha256:c136839c50c43d1a89ca20e4fb52160d94487a11dd62162f3fc51a7f9f412504
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd119116315647f4fed9dd69ee683063e06602eb5fa9a6b5d519c221f180375b
+oid sha256:43c82a64d1b8f1fd9574de5fae158363e7b6c4b45ca29bc0514a0d6e27f94b1c
 size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003015df141158aa5333077b185bdc06a011a964722a389e39b567ced2da4db1
+oid sha256:c136839c50c43d1a89ca20e4fb52160d94487a11dd62162f3fc51a7f9f412504
 size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a050f5e1bbf4287f7b0d9b37d32ebc0249311a97b234fe02619e717b87ce263
+oid sha256:9267862e5e4324b0b8a24c276f59d292730644c7a0035178204f822a1766eecd
 size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43a49442ed497655eb039aa736eb9b10d8ce1bedf8201367dacfd244bc4ac9d5
+oid sha256:7f0147bccfa50d9f1e3d2050c4a673bb0a1437014b1e557d9296d77aef9f3998
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec32de3bbf105451493e81083f5971095627692abfab254dd4e5a1d65eac2c19
+oid sha256:d8263a13174026b67f0ca2157e0d4a2f2821f15b563c6c8a669939a0c1b1e28c
 size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b248ffdc732ea3dbdc75a9de579ccc76e4d76271ad37ea176a4a3ccb4f14d4
+oid sha256:3e95c5478b92e8006f43387c0b75b37f3335c990be40370e1b34e172933769cd
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b96f0574d3373b6e12d909ce88918f77f30b363de1a3ef76dab4308ef3ba031
+oid sha256:1a4619364406ea388c21254d6c5978334a342010313b5cb00ddb890eee0fdb2f
 size 3850000

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de8a2db69f78fd41dc069485aad643c7bd169fd92bda265544e302ac178778ea
+oid sha256:5da1c893a4caba0d87f8f21a1fec3130e5dd3f7e51ab7601beed14d1152bc26e
 size 3849250

SnowballTarget/events.out.tfevents.1718381420.pop-os.80903.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d806b0c2358b7a5e5a4b460e444fc1bb5a8e718324dc57399c89aee2cc321cf1
+size 23588

run_logs/Player-0.log

@@ -1,40 +1,20 @@
-Mono path[0] = '/content/ml-agents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
-Mono config path = '/content/ml-agents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Mono path[0] = '/home/ivan/Code/rl/hf/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/home/ivan/Code/rl/hf/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
+PlayerPrefs - Creating folder: /home/ivan/.config/unity3d/Hugging Face
+PlayerPrefs - Creating folder: /home/ivan/.config/unity3d/Hugging Face/SnowballTarget
 Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
-[Subsystems] Discovering subsystems at path /content/ml-agents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+[Subsystems] Discovering subsystems at path /home/ivan/Code/rl/hf/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
     Version:  NULL 1.0 [1.0]
     Renderer: Null Device
     Vendor:   Unity Technologies
-ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
-ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
-ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
-ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
-ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
-FMOD failed to initialize the output device.: "Error initializing output device. " (60)
-Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
-ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
-ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
-ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
-ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
-ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
-FMOD failed to initialize the output device.: "Error initializing output device. " (60)
-FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.092 seconds
+- Completed reload, in  0.059 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)
@@ -45,15 +25,15 @@ 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: 0.715933 ms
+UnloadTime: 0.438792 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.
+Setting up 4 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5369 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5370 frames, [16.0 KB-32.0 KB]: 91 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
@@ -61,7 +41,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 218 B
+      Peak Allocated Bytes 224 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
@@ -73,10 +53,10 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
-      Peak Allocated Bytes 0 B
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
@@ -88,6 +68,16 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [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_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -98,12 +88,22 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_EnlightenWorker]
+    [ALLOC_TEMP_EnlightenWorker] x 4
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
@@ -128,7 +128,7 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 7
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
@@ -143,12 +143,22 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 11]
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
       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 3]
+    [ALLOC_TEMP_Background Job.Worker 11]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -169,22 +179,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 44
+  Peak main deferred allocation count 36
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5462 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 6.6 MB
+      Peak Allocated memory 6.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.9 MB
+      Peak Allocated memory 17.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -213,13 +223,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4792 frames, [64.0 KB-128.0 KB]: 669 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4874 frames, [64.0 KB-128.0 KB]: 588 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.4 KB
+      Peak Allocated memory 67.3 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5462 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +241,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -249,13 +259,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5461 frames
+      Peak usage frame count: [0-1.0 KB]: 5462 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]: 5461 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5462 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.9329480528831482,
-            "min": 0.9265595078468323,
-            "max": 2.869509696960449,
+            "value": 0.8751007914543152,
+            "min": 0.8751007914543152,
+            "max": 2.851548910140991,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8907.7880859375,
-            "min": 8907.7880859375,
-            "max": 29386.6484375,
+            "value": 8393.966796875,
+            "min": 8393.966796875,
+            "max": 29296.8125,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 13.092435836791992,
-            "min": 0.28902819752693176,
-            "max": 13.092435836791992,
+            "value": 12.883551597595215,
+            "min": 0.3710114657878876,
+            "max": 12.933782577514648,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2553.02490234375,
-            "min": 56.071468353271484,
-            "max": 2609.0302734375,
+            "value": 2512.29248046875,
+            "min": 71.97622680664062,
+            "max": 2638.49169921875,
             "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -44,33 +44,33 @@
             "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 8756.0,
+            "value": 10945.0,
             "min": 8756.0,
             "max": 10945.0,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06686443029235199,
-            "min": 0.06335296537772771,
-            "max": 0.07359331315520275,
+            "value": 0.0667367311667191,
+            "min": 0.06220210300131892,
+            "max": 0.07385022185831878,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.26745772116940797,
-            "min": 0.25341186151091083,
-            "max": 0.3679665657760137,
+            "value": 0.2669469246668764,
+            "min": 0.25486488775099064,
+            "max": 0.3435277895677798,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.1908342984377169,
-            "min": 0.1238980646354749,
-            "max": 0.2679464461318418,
+            "value": 0.18553577195487772,
+            "min": 0.12687591150832161,
+            "max": 0.27973537935930143,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7633371937508676,
-            "min": 0.4955922585418996,
-            "max": 1.2962227060514337,
+            "value": 0.7421430878195109,
+            "min": 0.5075036460332865,
+            "max": 1.398676896796507,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 26.0,
-            "min": 3.2954545454545454,
-            "max": 26.0,
+            "value": 25.227272727272727,
+            "min": 3.5454545454545454,
+            "max": 25.563636363636363,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1144.0,
-            "min": 145.0,
-            "max": 1401.0,
+            "value": 1110.0,
+            "min": 156.0,
+            "max": 1406.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 26.0,
-            "min": 3.2954545454545454,
-            "max": 26.0,
+            "value": 25.227272727272727,
+            "min": 3.5454545454545454,
+            "max": 25.563636363636363,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1144.0,
-            "min": 145.0,
-            "max": 1401.0,
+            "value": 1110.0,
+            "min": 156.0,
+            "max": 1406.0,
             "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1718367692",
-        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "start_time_seconds": "1718381420",
+        "python_version": "3.10.14 (main, Jun 14 2024, 18:23:26) [GCC 11.4.0]",
+        "command_line_arguments": "/home/ivan/.env/hf310/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
-        "pytorch_version": "2.3.0+cu121",
+        "pytorch_version": "2.3.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1718368165"
+        "end_time_seconds": "1718381686"
     },
-    "total": 473.69982002200004,
+    "total": 266.73982527601765,
     "count": 1,
-    "self": 0.43986131099973136,
+    "self": 0.2217029849998653,
     "children": {
         "run_training.setup": {
-            "total": 0.06161612599998989,
+            "total": 0.01772404502844438,
             "count": 1,
-            "self": 0.06161612599998989
+            "self": 0.01772404502844438
         },
         "TrainerController.start_learning": {
-            "total": 473.1983425850003,
+            "total": 266.50039824598935,
             "count": 1,
-            "self": 0.64334971302128,
+            "self": 0.36665289383381605,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.2021853960000044,
+                    "total": 1.0074500190094113,
                     "count": 1,
-                    "self": 3.2021853960000044
+                    "self": 1.0074500190094113
                 },
                 "TrainerController.advance": {
-                    "total": 469.24406580497885,
-                    "count": 18201,
-                    "self": 0.317268440995349,
+                    "total": 265.04363459616434,
+                    "count": 18206,
+                    "self": 0.18115055077942088,
                     "children": {
                         "env_step": {
-                            "total": 468.9267973639835,
-                            "count": 18201,
-                            "self": 306.7133463549985,
+                            "total": 264.8624840453849,
+                            "count": 18206,
+                            "self": 183.88318983098725,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 161.90068791798421,
-                                    "count": 18201,
-                                    "self": 1.5550392809718687,
+                                    "total": 80.78306001168676,
+                                    "count": 18206,
+                                    "self": 0.8253579681040719,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 160.34564863701235,
-                                            "count": 18201,
-                                            "self": 160.34564863701235
+                                            "total": 79.95770204358269,
+                                            "count": 18206,
+                                            "self": 79.95770204358269
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.31276309100076105,
-                                    "count": 18201,
+                                    "total": 0.19623420271091163,
+                                    "count": 18206,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 471.8870832780142,
-                                            "count": 18201,
+                                            "total": 266.04770171339624,
+                                            "count": 18206,
                                             "is_parallel": true,
-                                            "self": 236.0582644770211,
+                                            "self": 130.5107266350533,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.009056251999936649,
+                                                            "total": 0.0011995669919997454,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.007394400999373829,
+                                                            "self": 0.0003199088969267905,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0016618510005628195,
+                                                                    "total": 0.0008796580950729549,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0016618510005628195
+                                                                    "self": 0.0008796580950729549
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03649030900010075,
+                                                            "total": 0.020269825006835163,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000790018000316195,
+                                                            "self": 0.00022742105647921562,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00035599099987848604,
+                                                                    "total": 0.0003777029924094677,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00035599099987848604
+                                                                    "self": 0.0003777029924094677
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.032916400999965845,
+                                                                    "total": 0.01894824398914352,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.032916400999965845
+                                                                    "self": 0.01894824398914352
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0024278989999402256,
+                                                                    "total": 0.0007164569688029587,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004333199995016912,
+                                                                    "self": 0.00016149604925885797,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0019945790004385344,
+                                                                            "total": 0.0005549609195441008,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0019945790004385344
+                                                                            "self": 0.0005549609195441008
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 235.82881880099308,
-                                                    "count": 18200,
+                                                    "total": 135.53697507834295,
+                                                    "count": 18205,
                                                     "is_parallel": true,
-                                                    "self": 10.696257846983144,
+                                                    "self": 7.385933380981442,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.538592961004497,
-                                                            "count": 18200,
+                                                            "total": 3.248280268686358,
+                                                            "count": 18205,
                                                             "is_parallel": true,
-                                                            "self": 5.538592961004497
+                                                            "self": 3.248280268686358
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 185.26412189502685,
-                                                            "count": 18200,
+                                                            "total": 104.01748923194828,
+                                                            "count": 18205,
                                                             "is_parallel": true,
-                                                            "self": 185.26412189502685
+                                                            "self": 104.01748923194828
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 34.32984609797859,
-                                                            "count": 18200,
+                                                            "total": 20.885272196726874,
+                                                            "count": 18205,
                                                             "is_parallel": true,
-                                                            "self": 6.657751770902678,
+                                                            "self": 3.612728105217684,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 27.67209432707591,
-                                                                    "count": 182000,
+                                                                    "total": 17.27254409150919,
+                                                                    "count": 182050,
                                                                     "is_parallel": true,
-                                                                    "self": 27.67209432707591
+                                                                    "self": 17.27254409150919
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00014192300022841664,
+                    "total": 7.50789768062532e-05,
                     "count": 1,
-                    "self": 0.00014192300022841664,
+                    "self": 7.50789768062532e-05,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 463.5746475970145,
-                                    "count": 705068,
+                                    "total": 264.6353142752778,
+                                    "count": 167784,
                                     "is_parallel": true,
-                                    "self": 14.702609201066707,
+                                    "self": 1.8442222691955976,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 256.91221596894593,
-                                            "count": 705068,
+                                            "total": 152.74305728869513,
+                                            "count": 167784,
                                             "is_parallel": true,
-                                            "self": 256.20339395294604,
+                                            "self": 152.3370479856385,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 0.7088220159998855,
+                                                    "total": 0.40600930305663496,
                                                     "count": 4,
                                                     "is_parallel": true,
-                                                    "self": 0.7088220159998855
+                                                    "self": 0.40600930305663496
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 191.95982242700188,
+                                            "total": 110.04803471738705,
                                             "count": 90,
                                             "is_parallel": true,
-                                            "self": 61.274015580998366,
+                                            "self": 27.158907177159563,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 130.68580684600352,
-                                                    "count": 4587,
+                                                    "total": 82.88912754022749,
+                                                    "count": 4584,
                                                     "is_parallel": true,
-                                                    "self": 130.68580684600352
+                                                    "self": 82.88912754022749
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.10859974799996053,
+                    "total": 0.08258565800497308,
                     "count": 1,
-                    "self": 0.0009852090001913894,
+                    "self": 0.0004328389768488705,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10761453899976914,
+                            "total": 0.08215281902812421,
                             "count": 1,
-                            "self": 0.10761453899976914
+                            "self": 0.08215281902812421
                         }
                     }
                 }

run_logs/training_status.json

@@ -4,8 +4,8 @@
             {
                 "steps": 49936,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 12.363636363636363,
-                "creation_time": 1718367816.6492157,
+                "reward": 13.727272727272727,
+                "creation_time": 1718381487.7609048,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
                 ]
@@ -13,8 +13,8 @@
             {
                 "steps": 99960,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 19.727272727272727,
-                "creation_time": 1718367931.0872524,
+                "reward": 20.636363636363637,
+                "creation_time": 1718381554.2328043,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
@@ -22,8 +22,8 @@
             {
                 "steps": 149984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 25.181818181818183,
-                "creation_time": 1718368052.026637,
+                "reward": 24.09090909090909,
+                "creation_time": 1718381620.6178563,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
@@ -31,8 +31,8 @@
             {
                 "steps": 199984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 24.454545454545453,
-                "creation_time": 1718368165.3066921,
+                "reward": 26.0,
+                "creation_time": 1718381686.422457,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
@@ -40,8 +40,8 @@
             {
                 "steps": 200112,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 24.454545454545453,
-                "creation_time": 1718368165.4400709,
+                "reward": 26.0,
+                "creation_time": 1718381686.5221062,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
@@ -50,8 +50,8 @@
         "final_checkpoint": {
             "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 24.454545454545453,
-            "creation_time": 1718368165.4400709,
+            "reward": 26.0,
+            "creation_time": 1718381686.5221062,
             "auxillary_file_paths": [
                 "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]
@@ -60,6 +60,6 @@
     "metadata": {
         "stats_format_version": "0.3.0",
         "mlagents_version": "1.1.0.dev0",
-        "torch_version": "2.3.0+cu121"
+        "torch_version": "2.3.1+cu121"
     }
 }