First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde0272a25d9a0100d5eeaeb4b53f198ecdd3cb3d4b3e2815102d74c1b633711
+oid sha256:5e4572e032b4ad46ff0c7dafe95f4d25d809318d6fd2157a34357fcd2ed1608c
 size 650646

SnowballTarget/SnowballTarget-1599976.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a78d8686a40d1186da6f545ee04277a4da44d5c25513b4f7955fc26afd05849c
+oid sha256:ce752dd07b129f2b3531aff138c939d797fb617901eef78ab7a093169888fa84
 size 650646

SnowballTarget/SnowballTarget-1599976.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e189673dd1921d568b2dfa18b538aeb1998b927738f2c9275ab466c551195d1f
+oid sha256:821339943ee212e36d9aef72b36fcfdaa25b8b44767a576af8824944ea44f42e
 size 3850214

SnowballTarget/SnowballTarget-1649992.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd5e4f2442e537092e568ec25408808523820a4b81535048a5774b092d901ba
+oid sha256:a04959790c06c4a6197bd19dc97ce323d987c839393359841fa607142073ec70
 size 650646

SnowballTarget/SnowballTarget-1649992.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6bd8b590ac05bd8f8f5765aeeada7de722a0c21a3479072745dcb1c0f60066
+oid sha256:eb95b8e3285819a9f7806160dd7174bc50d96a427464437181fe1d388d42f13d
 size 3850214

SnowballTarget/SnowballTarget-1699936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad659e77ef97dc0a00a2b7c8bed95615cf8dd99c62d15a216e55367e273c3493
+oid sha256:1232367a0e7dd4de943a7d76d5a8ca38a402a688a8630e532d96fac75bec2001
 size 650646

SnowballTarget/SnowballTarget-1699936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e23b1995f4e419b3969b3f815857b62ebb67be7db5c4e9e642e5a297fb402ad3
+oid sha256:dc5d27add477046a65c04289e8559d36bb396b3a154647f1b0d747263b6b1085
 size 3850214

SnowballTarget/SnowballTarget-1749960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d88c89515ccd98337007b04b6cf15420cb9c23ae5893b353a5e1e6a737539255
+oid sha256:f0caa728c03460f30ba98072313b8be649d79c3054425627bc74e1b6e9e22adb
 size 650646

SnowballTarget/SnowballTarget-1749960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2007514842659e7f8c483b63aabf84fcc86da53944fce799027175c6dc7ac534
+oid sha256:841e0b0c37d205afbaf1b432c5060e866a67f7cad7116b03d3321b55fb30ffbe
 size 3850214

SnowballTarget/SnowballTarget-1799984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455d1bb49ad02009f8c2ebe6248ee93e275a5f3ef826abb2149bd557eda26318
+oid sha256:2915433e63808d6547d603179fc65c4d05b65098ba7d6794cc708519a7a85d78
 size 650646

SnowballTarget/SnowballTarget-1799984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d9d7656445dbe45f8f06c0e553bd994a9a422eb921e4126c355a1afefbc1a5a
+oid sha256:1af682106c9b68e31619dd7f89240a33a6cafea4db6b8443383fef2fce1345d7
 size 3850214

SnowballTarget/SnowballTarget-1849984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:511f9690313244ffedf5d578a5d1746372bbccd61023fd1f2ba22886ad4b8f18
+oid sha256:3a37dd7bd0924e4fe8b092880cc7a9ef93e66180680b143b5638a4a50d0844ca
 size 650646

SnowballTarget/SnowballTarget-1849984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c6e9854e439a4cd567d8d7203ec0864b320477375fb7254f19628aebcb646a
+oid sha256:054c10c1034ceca08a16d3026bb955e73ec4bb0492f5c005f0fa6b80f6856b6b
 size 3850214

SnowballTarget/SnowballTarget-1899944.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa3a63ad6bdcd2863c6466277d5565d6529be97f6aa67231461967d61e1ed23
+oid sha256:60da3983b40b9da007ff0d7434d65a739f5c2b7155e2105cd1c6a58f88111c08
 size 650646

SnowballTarget/SnowballTarget-1899944.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0463c6ecbf98318f58b23557c01c7641b6cd4d4864226217dad5d94efbf81c52
+oid sha256:fbc07ac1b3302ea37b3c565e2dc8262aab3be995efafc5588b69aa72b211c833
 size 3850214

SnowballTarget/SnowballTarget-1949968.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1222722e398d7da4fe4d1fb1788e634ee75cb1cdacba4794b9aa606345024b6
+oid sha256:36b164ab795c45cb2160baaf658a2236fa015055e45dab3231f99595a4617c2f
 size 650646

SnowballTarget/SnowballTarget-1949968.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03d979f20f886fe2bdd6f31b0409addf49f3864dbe41b2ac69aab75bc0ceaba8
+oid sha256:d6a86783d8d132835d548d91542bc7aa20ad7d162dba3ba66d64995af15a9d92
 size 3850214

SnowballTarget/SnowballTarget-1999992.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde0272a25d9a0100d5eeaeb4b53f198ecdd3cb3d4b3e2815102d74c1b633711
+oid sha256:5e4572e032b4ad46ff0c7dafe95f4d25d809318d6fd2157a34357fcd2ed1608c
 size 650646

SnowballTarget/SnowballTarget-1999992.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff19c157dc5d92f8dbe5aba0183f718aed72476d3cd50c6342a7561d92661361
+oid sha256:5993f6bceaf9594da04333f1acae4932e92c042b1330808769a6e75ff62fa989
 size 3850214

SnowballTarget/SnowballTarget-2000504.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde0272a25d9a0100d5eeaeb4b53f198ecdd3cb3d4b3e2815102d74c1b633711
+oid sha256:5e4572e032b4ad46ff0c7dafe95f4d25d809318d6fd2157a34357fcd2ed1608c
 size 650646

SnowballTarget/SnowballTarget-2000504.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f1c1a492c30ea8b6dd34b82d1548215ab5a0f439f3f2f9e13ae959a2951074
+oid sha256:02314d15ce4299de3c35b9d19c04d5aef57ebae97887e30e8ef8a64402c44fd6
 size 3850214

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6485d96c8209614b0364c33ccc31c1b6659bdf4410f576210b256c502b152ddd
+oid sha256:094d77115e89a10167574ab445c564a0dce4b825281bd56e9d2fd2db5981adb0
 size 3849250

SnowballTarget/events.out.tfevents.1739171467.446dc8fb7edc.3312.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de968e4ad9776e060714a03ff8e78d01b95915a5d85b7d1ced5c2077b40db281
+size 169248

run_logs/Player-0.log

@@ -34,7 +34,7 @@ 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  0.131 seconds
+- Completed reload, in  0.088 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)
@@ -45,7 +45,7 @@ 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: 0.918657 ms
+UnloadTime: 0.639071 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.
@@ -169,13 +169,13 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 42
+  Peak main deferred allocation count 40
     [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]: 12401 frames, [8.0 MB-16.0 MB]: 29819 frames, [16.0 MB-32.0 MB]: 12340 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 12414 frames, [8.0 MB-16.0 MB]: 29517 frames, [16.0 MB-32.0 MB]: 12629 frames
       Requested Block Size 16.0 MB
       Peak Block count 2
       Peak Allocated memory 24.1 MB
@@ -213,10 +213,10 @@ 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]: 53098 frames, [64.0 KB-128.0 KB]: 1462 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 52313 frames, [64.0 KB-128.0 KB]: 2247 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.8 KB
+      Peak Allocated memory 67.7 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
       Peak usage frame count: [32.0 KB-64.0 KB]: 54560 frames

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.524152934551239,
-            "min": 0.4763016998767853,
-            "max": 2.8322181701660156,
+            "value": 0.3314012587070465,
+            "min": 0.3270619213581085,
+            "max": 2.8598127365112305,
             "count": 200
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 5396.6787109375,
-            "min": 4644.7265625,
-            "max": 28911.283203125,
+            "value": 3412.107421875,
+            "min": 3157.62744140625,
+            "max": 29192.96875,
             "count": 200
         },
         "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
             "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 14.371801376342773,
-            "min": 0.4785648286342621,
-            "max": 14.50901985168457,
+            "value": 14.344200134277344,
+            "min": 0.4010504186153412,
+            "max": 14.36646556854248,
             "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2946.21923828125,
-            "min": 92.8415756225586,
-            "max": 2974.34912109375,
+            "value": 2940.56103515625,
+            "min": 77.80377960205078,
+            "max": 2945.12548828125,
             "count": 200
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07187990252357707,
-            "min": 0.058179320638599874,
-            "max": 0.07904893951319322,
+            "value": 0.0689329136448328,
+            "min": 0.058687101516018934,
+            "max": 0.0782569578932096,
             "count": 200
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.35939951261788533,
-            "min": 0.2327172825543995,
-            "max": 0.39097194441916044,
+            "value": 0.34466456822416397,
+            "min": 0.23474840606407574,
+            "max": 0.3795769412787266,
             "count": 200
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.143010379607771,
-            "min": 0.12749956878376942,
-            "max": 0.32456278164012764,
+            "value": 0.14288388405944788,
+            "min": 0.12275751165899576,
+            "max": 0.28038673731041885,
             "count": 200
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7150518980388549,
-            "min": 0.5225237790568202,
-            "max": 1.622813908200638,
+            "value": 0.7144194202972394,
+            "min": 0.5008412361711118,
+            "max": 1.3989377880797667,
             "count": 200
         },
         "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
             "count": 200
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 28.454545454545453,
-            "min": 4.159090909090909,
-            "max": 28.75,
+            "value": 28.345454545454544,
+            "min": 3.25,
+            "max": 28.545454545454547,
             "count": 200
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1565.0,
-            "min": 183.0,
-            "max": 1581.0,
+            "value": 1559.0,
+            "min": 143.0,
+            "max": 1565.0,
             "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 28.454545454545453,
-            "min": 4.159090909090909,
-            "max": 28.75,
+            "value": 28.345454545454544,
+            "min": 3.25,
+            "max": 28.545454545454547,
             "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1565.0,
-            "min": 183.0,
-            "max": 1581.0,
+            "value": 1559.0,
+            "min": 143.0,
+            "max": 1565.0,
             "count": 200
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,7 +148,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1739027360",
+        "start_time_seconds": "1739171466",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
@@ -156,59 +156,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.6.0+cu124",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1739031851"
+        "end_time_seconds": "1739175649"
     },
-    "total": 4490.287307371001,
+    "total": 4183.661267745,
     "count": 1,
-    "self": 0.7750314860013532,
+    "self": 0.43648233499970956,
     "children": {
         "run_training.setup": {
-            "total": 0.023354815999937273,
+            "total": 0.02431995300003109,
             "count": 1,
-            "self": 0.023354815999937273
+            "self": 0.02431995300003109
         },
         "TrainerController.start_learning": {
-            "total": 4489.488921069,
+            "total": 4183.200465457,
             "count": 1,
-            "self": 3.882278490979843,
+            "self": 3.2531446710881937,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.530226389999939,
+                    "total": 3.105925941999999,
                     "count": 1,
-                    "self": 3.530226389999939
+                    "self": 3.105925941999999
                 },
                 "TrainerController.advance": {
-                    "total": 4481.9175995000205,
+                    "total": 4176.7512573539125,
                     "count": 181864,
-                    "self": 3.960839377978118,
+                    "self": 3.368483168943385,
                     "children": {
                         "env_step": {
-                            "total": 3197.545528106069,
+                            "total": 2926.1088045370384,
                             "count": 181864,
-                            "self": 2430.500568809922,
+                            "self": 2217.6007750281565,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 764.6347027970888,
+                                    "total": 706.5077714289263,
                                     "count": 181864,
-                                    "self": 13.303806290257967,
+                                    "self": 12.2194095379989,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 751.3308965068309,
+                                            "total": 694.2883618909274,
                                             "count": 181864,
-                                            "self": 751.3308965068309
+                                            "self": 694.2883618909274
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.4102564990583915,
+                                    "total": 2.000258079955529,
                                     "count": 181864,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 4476.102863700005,
+                                            "total": 4171.048414529961,
                                             "count": 181864,
                                             "is_parallel": true,
-                                            "self": 2349.036411914997,
+                                            "self": 2229.178157453185,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0055430500000284155,
+                                                            "total": 0.005796984999960841,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0040133469998409055,
+                                                            "self": 0.004292478000138544,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.00152970300018751,
+                                                                    "total": 0.001504506999822297,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00152970300018751
+                                                                    "self": 0.001504506999822297
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03755052699989392,
+                                                            "total": 0.03626193700006297,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006714769999689452,
+                                                            "self": 0.0005792990000372811,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00039684599994416203,
+                                                                    "total": 0.0004130410000016127,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00039684599994416203
+                                                                    "self": 0.0004130410000016127
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.034491733999971075,
+                                                                    "total": 0.03317575500000203,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.034491733999971075
+                                                                    "self": 0.03317575500000203
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0019904700000097364,
+                                                                    "total": 0.0020938420000220503,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003866729998662777,
+                                                                    "self": 0.000398240999970767,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0016037970001434587,
+                                                                            "total": 0.0016956010000512833,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0016037970001434587
+                                                                            "self": 0.0016956010000512833
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 2127.066451785008,
+                                                    "total": 1941.8702570767757,
                                                     "count": 181863,
                                                     "is_parallel": true,
-                                                    "self": 100.25605371183883,
+                                                    "self": 94.18546899662215,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 56.752897272128735,
+                                                            "total": 51.843831393067035,
                                                             "count": 181863,
                                                             "is_parallel": true,
-                                                            "self": 56.752897272128735
+                                                            "self": 51.843831393067035
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1637.2649914389392,
+                                                            "total": 1496.533544256004,
                                                             "count": 181863,
                                                             "is_parallel": true,
-                                                            "self": 1637.2649914389392
+                                                            "self": 1496.533544256004
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 332.79250936210167,
+                                                            "total": 299.30741243108264,
                                                             "count": 181863,
                                                             "is_parallel": true,
-                                                            "self": 60.4091408381538,
+                                                            "self": 52.39333896434232,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 272.38336852394787,
+                                                                    "total": 246.91407346674032,
                                                                     "count": 1818630,
                                                                     "is_parallel": true,
-                                                                    "self": 272.38336852394787
+                                                                    "self": 246.91407346674032
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1280.4112320159734,
+                            "total": 1247.2739696479312,
                             "count": 181864,
-                            "self": 4.703083870106639,
+                            "self": 3.991147702065291,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 280.688801764873,
+                                    "total": 266.2548088678577,
                                     "count": 181864,
-                                    "self": 276.35493273887244,
+                                    "self": 262.2578423578582,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 4.333869026000571,
+                                            "total": 3.996966509999538,
                                             "count": 40,
-                                            "self": 4.333869026000571
+                                            "self": 3.996966509999538
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 995.0193463809936,
+                                    "total": 977.0280130780081,
                                     "count": 909,
-                                    "self": 400.7724190970566,
+                                    "self": 390.18840093102665,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 594.246927283937,
+                                            "total": 586.8396121469815,
                                             "count": 46356,
-                                            "self": 594.246927283937
+                                            "self": 586.8396121469815
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.374000021314714e-06,
+                    "total": 1.0949997886200435e-06,
                     "count": 1,
-                    "self": 1.374000021314714e-06
+                    "self": 1.0949997886200435e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.15881531399918458,
+                    "total": 0.0901363949997176,
                     "count": 1,
-                    "self": 0.0014243079995139851,
+                    "self": 0.0009759069998835912,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1573910059996706,
+                            "total": 0.089160487999834,
                             "count": 1,
-                            "self": 0.1573910059996706
+                            "self": 0.089160487999834
                         }
                     }
                 }

run_logs/training_status.json

@@ -4,8 +4,8 @@
             {
                 "steps": 1599976,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599976.onnx",
-                "reward": 27.454545454545453,
-                "creation_time": 1739030965.6672282,
+                "reward": 27.545454545454547,
+                "creation_time": 1739174824.4578924,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599976.pt"
                 ]
@@ -14,7 +14,7 @@
                 "steps": 1649992,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649992.onnx",
                 "reward": 28.0,
-                "creation_time": 1739031073.3075323,
+                "creation_time": 1739174926.6069896,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649992.pt"
                 ]
@@ -22,8 +22,8 @@
             {
                 "steps": 1699936,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699936.onnx",
-                "reward": 28.272727272727273,
-                "creation_time": 1739031183.4783473,
+                "reward": 26.454545454545453,
+                "creation_time": 1739175029.6447194,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699936.pt"
                 ]
@@ -31,8 +31,8 @@
             {
                 "steps": 1749960,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749960.onnx",
-                "reward": 28.454545454545453,
-                "creation_time": 1739031293.631006,
+                "reward": 27.363636363636363,
+                "creation_time": 1739175133.8361979,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749960.pt"
                 ]
@@ -40,8 +40,8 @@
             {
                 "steps": 1799984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799984.onnx",
-                "reward": 27.181818181818183,
-                "creation_time": 1739031403.3812432,
+                "reward": 28.727272727272727,
+                "creation_time": 1739175237.0682523,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799984.pt"
                 ]
@@ -49,8 +49,8 @@
             {
                 "steps": 1849984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849984.onnx",
-                "reward": 27.727272727272727,
-                "creation_time": 1739031513.7229192,
+                "reward": 28.181818181818183,
+                "creation_time": 1739175338.820569,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849984.pt"
                 ]
@@ -58,8 +58,8 @@
             {
                 "steps": 1899944,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899944.onnx",
-                "reward": 28.636363636363637,
-                "creation_time": 1739031623.314077,
+                "reward": 27.818181818181817,
+                "creation_time": 1739175442.3266115,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899944.pt"
                 ]
@@ -67,8 +67,8 @@
             {
                 "steps": 1949968,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949968.onnx",
-                "reward": 28.727272727272727,
-                "creation_time": 1739031739.5414386,
+                "reward": 27.636363636363637,
+                "creation_time": 1739175545.8721192,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949968.pt"
                 ]
@@ -76,8 +76,8 @@
             {
                 "steps": 1999992,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999992.onnx",
-                "reward": 28.727272727272727,
-                "creation_time": 1739031850.1225796,
+                "reward": 27.727272727272727,
+                "creation_time": 1739175649.3443346,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999992.pt"
                 ]
@@ -85,8 +85,8 @@
             {
                 "steps": 2000504,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000504.onnx",
-                "reward": 28.727272727272727,
-                "creation_time": 1739031850.358512,
+                "reward": 27.727272727272727,
+                "creation_time": 1739175649.4804049,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000504.pt"
                 ]
@@ -95,8 +95,8 @@
         "final_checkpoint": {
             "steps": 2000504,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 28.727272727272727,
-            "creation_time": 1739031850.358512,
+            "reward": 27.727272727272727,
+            "creation_time": 1739175649.4804049,
             "auxillary_file_paths": [
                 "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000504.pt"
             ]