13th Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5e42ffb14033363e95c48e20ea11212cf53e6b917d8f5d64f9916e59b9f24a
+oid sha256:3ab0e9337b6f31cd3ff0be5c09d33b7878503e0b4eaa1f0144c60c8ea5342dad
 size 2351062

SoccerTwos/SoccerTwos-54189194.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab0e9337b6f31cd3ff0be5c09d33b7878503e0b4eaa1f0144c60c8ea5342dad
+size 2351062

SoccerTwos/SoccerTwos-54189194.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52e32097341cb2f8163e91bd6c1cbf81396eed2dcdcb3c7171e0ff5f7adaf97
+size 36303154

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3476b123adc441acee2026c24a520b5f8c85e13da0442d2aec0573b21fbd3584
+oid sha256:d67e6f98598541bd87f1d88261a8f3f615c8208474d09adea24e28f619505d8f
 size 36301318

SoccerTwos/events.out.tfevents.1725741373.Bretts-MacBook-Pro.local.57198.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1360f5c8f9e15cf6b9e191401eca5129e70308146df0a5014aecae798aa12d1f
-size 22284433
+oid sha256:929140c1cd31cd65140923776a7837a807987bbb10c7a5a2643f2131a59d9c61
+size 24563587

run_logs/Player-0.log

@@ -38,3 +38,282 @@ WARNING: Shader If subshaders removal was intentional, you may have forgotten tu
 UnloadTime: 0.230292 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+GRPC Exception: Status(StatusCode=Unknown, Detail="Exception calling application: [Errno 32] Broken pipe"). Disconnecting from trainer.
+Thread 0x16fca3000 may have been prematurely finalized
+Setting up 7 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]: 437419 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.1 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 78.8 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      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]
+      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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      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 6]
+      Initial Block Size 32.0 KB
+      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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      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] x 7
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      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 2]
+      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]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 13
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_OSX HID Input]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      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 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 15
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.1 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 437420 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.1 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 437420 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.3 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.1 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 437419 frames, [64.0 KB-128.0 KB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 65.6 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [128.0 KB-256.0 KB]: 437420 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.5 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.1 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 437420 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]: 437419 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.4 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.1 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 437420 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]: 437419 frames, [2.0 KB-4.0 KB]: 1 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -2,309 +2,309 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 2.1416494846343994,
-            "min": 2.0137786865234375,
-            "max": 2.151839017868042,
-            "count": 229
+            "value": 2.001605272293091,
+            "min": 1.9789596796035767,
+            "max": 2.2079057693481445,
+            "count": 2328
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 41599.3984375,
-            "min": 27844.923828125,
-            "max": 47085.4375,
-            "count": 229
+            "value": 38879.1796875,
+            "min": 18002.392578125,
+            "max": 50645.35546875,
+            "count": 2328
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 70.91304347826087,
-            "min": 50.824742268041234,
-            "max": 86.2280701754386,
-            "count": 229
+            "value": 63.63636363636363,
+            "min": 48.584158415841586,
+            "max": 102.3061224489796,
+            "count": 2328
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19572.0,
-            "min": 11252.0,
-            "max": 21360.0,
-            "count": 229
+            "value": 19600.0,
+            "min": 5596.0,
+            "max": 21380.0,
+            "count": 2328
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 90.32114998486692,
-            "min": 67.98246219987821,
-            "max": 106.5567773055241,
-            "count": 229
+            "value": 195.8465984461809,
+            "min": 75.29896745804021,
+            "max": 227.62322024749807,
+            "count": 2328
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 12464.318697911634,
-            "min": 7314.330712543377,
-            "max": 19099.755722564205,
-            "count": 229
+            "value": 30160.376160711858,
+            "min": 4495.842920529803,
+            "max": 44901.73591040075,
+            "count": 2328
         },
         "SoccerTwos.Step.mean": {
-            "value": 30899950.0,
-            "min": 28619966.0,
-            "max": 30899950.0,
-            "count": 229
+            "value": 54179992.0,
+            "min": 30909902.0,
+            "max": 54179992.0,
+            "count": 2328
         },
         "SoccerTwos.Step.sum": {
-            "value": 30899950.0,
-            "min": 28619966.0,
-            "max": 30899950.0,
-            "count": 229
+            "value": 54179992.0,
+            "min": 30909902.0,
+            "max": 54179992.0,
+            "count": 2328
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.04198051616549492,
-            "min": -0.12825024127960205,
-            "max": 0.05813853442668915,
-            "count": 229
+            "value": -0.029384715482592583,
+            "min": -0.25675803422927856,
+            "max": 0.19587919116020203,
+            "count": 2328
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -5.79331111907959,
-            "min": -16.676513671875,
-            "max": 8.662641525268555,
-            "count": 229
+            "value": -4.5252461433410645,
+            "min": -37.743431091308594,
+            "max": 28.20660400390625,
+            "count": 2328
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.04343034699559212,
-            "min": -0.12868726253509521,
-            "max": 0.057454075664281845,
-            "count": 229
+            "value": -0.029946662485599518,
+            "min": -0.25568994879722595,
+            "max": 0.194318026304245,
+            "count": 2328
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -5.993387699127197,
-            "min": -16.638057708740234,
-            "max": 8.560657501220703,
-            "count": 229
+            "value": -4.611785888671875,
+            "min": -37.586421966552734,
+            "max": 27.981796264648438,
+            "count": 2328
         },
         "SoccerTwos.Policy.CuriosityBaselineEstimate.mean": {
-            "value": 0.0024543115869164467,
-            "min": 0.00020709412638098001,
-            "max": 0.24234014749526978,
-            "count": 229
+            "value": 7.706054748268798e-05,
+            "min": -0.0007188767194747925,
+            "max": 0.0051978351548314095,
+            "count": 2328
         },
         "SoccerTwos.Policy.CuriosityBaselineEstimate.sum": {
-            "value": 0.3386949896812439,
-            "min": 0.03044283762574196,
-            "max": 44.54613494873047,
-            "count": 229
+            "value": 0.011867323890328407,
+            "min": -0.10208049416542053,
+            "max": 0.6841692924499512,
+            "count": 2328
         },
         "SoccerTwos.Policy.CuriosityValueEstimate.mean": {
-            "value": 0.002094687195494771,
-            "min": 0.0002014237834373489,
-            "max": 0.2422645092010498,
-            "count": 229
+            "value": 0.0001772618415998295,
+            "min": -0.0007160860113799572,
+            "max": 0.004996820818632841,
+            "count": 2328
         },
         "SoccerTwos.Policy.CuriosityValueEstimate.sum": {
-            "value": 0.2890668213367462,
-            "min": 0.031623534858226776,
-            "max": 44.569114685058594,
-            "count": 229
+            "value": 0.027298323810100555,
+            "min": -0.10168421268463135,
+            "max": 0.6836073398590088,
+            "count": 2328
         },
         "SoccerTwos.Policy.RndBaselineEstimate.mean": {
-            "value": 0.00014870119048282504,
-            "min": -0.00018489075591787696,
-            "max": 0.00017628517525736243,
-            "count": 229
+            "value": 2.2803717001806945e-05,
+            "min": -0.0007127210847102106,
+            "max": 0.0004282182489987463,
+            "count": 2328
         },
         "SoccerTwos.Policy.RndBaselineEstimate.sum": {
-            "value": 0.020520763471722603,
-            "min": -0.029478061944246292,
-            "max": 0.029439624398946762,
-            "count": 229
+            "value": 0.0035117724910378456,
+            "min": -0.11374851316213608,
+            "max": 0.07644464075565338,
+            "count": 2328
         },
         "SoccerTwos.Policy.RndValueEstimate.mean": {
-            "value": 0.00015831700875423849,
-            "min": -0.00018485976033844054,
-            "max": 0.0001771982351783663,
-            "count": 229
+            "value": 2.6185234673903324e-05,
+            "min": -0.000715779431629926,
+            "max": 0.0004273174563422799,
+            "count": 2328
         },
         "SoccerTwos.Policy.RndValueEstimate.sum": {
-            "value": 0.021847747266292572,
-            "min": -0.029127497225999832,
-            "max": 0.029592106118798256,
-            "count": 229
+            "value": 0.0040325261652469635,
+            "min": -0.11362162232398987,
+            "max": 0.07622122019529343,
+            "count": 2328
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 229
+            "count": 2328
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 229
+            "count": 2328
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.04998840801957725,
-            "min": -0.4002886958744215,
-            "max": 0.2771585784720246,
-            "count": 229
+            "value": -0.0681636356688165,
+            "min": -0.3762892068718835,
+            "max": 0.33065000329262173,
+            "count": 2328
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -6.89840030670166,
-            "min": -50.038799941539764,
-            "max": 46.839799761772156,
-            "count": 229
+            "value": -10.497199892997742,
+            "min": -59.05200004577637,
+            "max": 51.58140051364899,
+            "count": 2328
         },
         "SoccerTwos.Policy.CuriosityReward.mean": {
-            "value": 3.3735505580296747e-06,
+            "value": 2.6100170660580945e-06,
             "min": 0.0,
-            "max": 5.779475230838216e-06,
-            "count": 229
+            "max": 6.030737767756281e-06,
+            "count": 2328
         },
         "SoccerTwos.Policy.CuriosityReward.sum": {
-            "value": 0.0004655499770080951,
+            "value": 0.00040194262817294657,
             "min": 0.0,
-            "max": 0.0008388239721170976,
-            "count": 229
+            "max": 0.000809542730053181,
+            "count": 2328
         },
         "SoccerTwos.Policy.RndReward.mean": {
-            "value": 1.553490576139646e-06,
-            "min": 1.0619012450802476e-06,
-            "max": 1.9177394476529395e-06,
-            "count": 229
+            "value": 1.19658387680894e-06,
+            "min": 8.922438388125897e-07,
+            "max": 1.9774367168225843e-06,
+            "count": 2328
         },
         "SoccerTwos.Policy.RndReward.sum": {
-            "value": 0.00021438169950727115,
-            "min": 0.00013151309185133186,
-            "max": 0.00022558096927838278,
-            "count": 229
+            "value": 0.00018427391702857676,
+            "min": 6.0544335880763356e-05,
+            "max": 0.000219697240559924,
+            "count": 2328
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.04998840801957725,
-            "min": -0.4002886958744215,
-            "max": 0.2771585784720246,
-            "count": 229
+            "value": -0.0681636356688165,
+            "min": -0.3762892068718835,
+            "max": 0.33065000329262173,
+            "count": 2328
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -6.89840030670166,
-            "min": -50.038799941539764,
-            "max": 46.839799761772156,
-            "count": 229
+            "value": -10.497199892997742,
+            "min": -59.05200004577637,
+            "max": 51.58140051364899,
+            "count": 2328
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 229
+            "count": 2328
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 229
+            "count": 2328
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.011783653045616424,
-            "min": 0.0072254263698899495,
-            "max": 0.0510992972801129,
-            "count": 15
+            "value": 0.011342826396382103,
+            "min": 0.005190658658345153,
+            "max": 0.019213409415291,
+            "count": 157
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.011783653045616424,
-            "min": 0.0072254263698899495,
-            "max": 0.0510992972801129,
-            "count": 15
+            "value": 0.011342826396382103,
+            "min": 0.005190658658345153,
+            "max": 0.019213409415291,
+            "count": 157
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.02236808432886998,
-            "min": 0.02193430345505476,
-            "max": 0.025202005325506132,
-            "count": 15
+            "value": 0.0180530430128177,
+            "min": 0.016259409797688324,
+            "max": 0.023114188263813656,
+            "count": 157
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.02236808432886998,
-            "min": 0.02193430345505476,
-            "max": 0.025202005325506132,
-            "count": 15
+            "value": 0.0180530430128177,
+            "min": 0.016259409797688324,
+            "max": 0.023114188263813656,
+            "count": 157
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.02246675391991933,
-            "min": 0.02218010788783431,
-            "max": 0.025417460439105827,
-            "count": 15
+            "value": 0.01849161460995674,
+            "min": 0.016563859457770985,
+            "max": 0.02328170510008931,
+            "count": 157
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.02246675391991933,
-            "min": 0.02218010788783431,
-            "max": 0.025417460439105827,
-            "count": 15
+            "value": 0.01849161460995674,
+            "min": 0.016563859457770985,
+            "max": 0.02328170510008931,
+            "count": 157
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 15
+            "count": 157
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 15
+            "count": 157
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000004,
             "min": 0.20000000000000004,
             "max": 0.20000000000000004,
-            "count": 15
+            "count": 157
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000004,
             "min": 0.20000000000000004,
             "max": 0.20000000000000004,
-            "count": 15
+            "count": 157
         },
         "SoccerTwos.Policy.Beta.mean": {
-            "value": 0.006152085766,
-            "min": 0.006152085766,
-            "max": 0.00640850284225,
-            "count": 15
+            "value": 0.0032458374235,
+            "min": 0.0032458374235,
+            "max": 0.0061222651165,
+            "count": 157
         },
         "SoccerTwos.Policy.Beta.sum": {
-            "value": 0.006152085766,
-            "min": 0.006152085766,
-            "max": 0.00640850284225,
-            "count": 15
+            "value": 0.0032458374235,
+            "min": 0.0032458374235,
+            "max": 0.0061222651165,
+            "count": 157
         },
         "SoccerTwos.Losses.CuriosityForwardLoss.mean": {
-            "value": 0.044924141528705754,
-            "min": 0.044924141528705754,
-            "max": 0.12874181816975275,
-            "count": 15
+            "value": 0.04033469967544079,
+            "min": 0.03939711768180132,
+            "max": 0.13589541738231978,
+            "count": 157
         },
         "SoccerTwos.Losses.CuriosityForwardLoss.sum": {
-            "value": 0.044924141528705754,
-            "min": 0.044924141528705754,
-            "max": 0.12874181816975275,
-            "count": 15
+            "value": 0.04033469967544079,
+            "min": 0.03939711768180132,
+            "max": 0.13589541738231978,
+            "count": 157
         },
         "SoccerTwos.Losses.CuriosityInverseLoss.mean": {
-            "value": 1.5999893347422283,
-            "min": 1.5462068021297455,
-            "max": 1.7163931628068287,
-            "count": 15
+            "value": 1.4537008007367451,
+            "min": 1.4515005846818287,
+            "max": 1.8242186109224956,
+            "count": 157
         },
         "SoccerTwos.Losses.CuriosityInverseLoss.sum": {
-            "value": 1.5999893347422283,
-            "min": 1.5462068021297455,
-            "max": 1.7163931628068287,
-            "count": 15
+            "value": 1.4537008007367451,
+            "min": 1.4515005846818287,
+            "max": 1.8242186109224956,
+            "count": 157
         },
         "SoccerTwos.Losses.RNDLoss.mean": {
-            "value": 0.018670696765184402,
-            "min": 0.018668334931135178,
-            "max": 0.02088502235710621,
-            "count": 15
+            "value": 0.016839604824781418,
+            "min": 0.016614088788628578,
+            "max": 0.01993536204099655,
+            "count": 157
         },
         "SoccerTwos.Losses.RNDLoss.sum": {
-            "value": 0.018670696765184402,
-            "min": 0.018668334931135178,
-            "max": 0.02088502235710621,
-            "count": 15
+            "value": 0.016839604824781418,
+            "min": 0.016614088788628578,
+            "max": 0.01993536204099655,
+            "count": 157
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1725639262",
+        "start_time_seconds": "1725741370",
         "python_version": "3.10.12 (main, Aug 23 2024, 16:29:11) [Clang 15.0.0 (clang-1500.3.9.4)]",
         "command_line_arguments": "/Users/brettgohre/Desktop/huggingface/ml-agents/games/bin/mlagents-learn ./config/poca/sept/three.yaml --env=./SoccerTwos/SoccerTwos.app --run-id=sept-run-01 --resume --no-graphics",
         "mlagents_version": "1.1.0.dev0",
@@ -312,103 +312,103 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.4.0",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1725648389"
+        "end_time_seconds": "1725834732"
     },
-    "total": 9127.100674749992,
+    "total": 93361.07623400001,
     "count": 1,
-    "self": 0.15175625000847504,
+    "self": 0.2508249579987023,
     "children": {
         "run_training.setup": {
-            "total": 0.017048291978426278,
+            "total": 0.02454258399666287,
             "count": 1,
-            "self": 0.017048291978426278
+            "self": 0.02454258399666287
         },
         "TrainerController.start_learning": {
-            "total": 9126.931870208005,
+            "total": 93360.80086645801,
             "count": 1,
-            "self": 1.415727891610004,
+            "self": 14.692869420541683,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.5643327069701627,
-                    "count": 7,
-                    "self": 3.5643327069701627
+                    "total": 6.080348207993666,
+                    "count": 60,
+                    "self": 6.080348207993666
                 },
                 "TrainerController.advance": {
-                    "total": 9121.758065358445,
-                    "count": 158196,
-                    "self": 1.3677141138759907,
+                    "total": 93339.84131478748,
+                    "count": 1596200,
+                    "self": 12.974666123162024,
                     "children": {
                         "env_step": {
-                            "total": 6411.4115795473335,
-                            "count": 158196,
-                            "self": 6185.67660572668,
+                            "total": 64851.92356695773,
+                            "count": 1596200,
+                            "self": 62650.110620818625,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 224.9005823341431,
-                                    "count": 158196,
-                                    "self": 8.746982502460014,
+                                    "total": 2192.282666757237,
+                                    "count": 1596200,
+                                    "self": 89.96115429818747,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 216.1535998316831,
-                                            "count": 287128,
-                                            "self": 216.1535998316831
+                                            "total": 2102.3215124590497,
+                                            "count": 2916144,
+                                            "self": 2102.3215124590497
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.8343914865108673,
-                                    "count": 158195,
+                                    "total": 9.53027938187006,
+                                    "count": 1596199,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 9121.446049298218,
-                                            "count": 158195,
+                                            "total": 93334.78617089201,
+                                            "count": 1596199,
                                             "is_parallel": true,
-                                            "self": 3101.727182136703,
+                                            "self": 32393.573468669725,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.009650043997680768,
-                                                    "count": 14,
+                                                    "total": 0.08119578479090706,
+                                                    "count": 120,
                                                     "is_parallel": true,
-                                                    "self": 0.0012721649545710534,
+                                                    "self": 0.010500200296519324,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.008377879043109715,
-                                                            "count": 56,
+                                                            "total": 0.07069558449438773,
+                                                            "count": 480,
                                                             "is_parallel": true,
-                                                            "self": 0.008377879043109715
+                                                            "self": 0.07069558449438773
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 6019.709217117517,
-                                                    "count": 158195,
+                                                    "total": 60941.131506437494,
+                                                    "count": 1596199,
                                                     "is_parallel": true,
-                                                    "self": 15.64049137730035,
+                                                    "self": 159.10876413882943,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 118.73067298045498,
-                                                            "count": 158195,
+                                                            "total": 1219.8835514431412,
+                                                            "count": 1596199,
                                                             "is_parallel": true,
-                                                            "self": 118.73067298045498
+                                                            "self": 1219.8835514431412
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 5690.6334428538685,
-                                                            "count": 158195,
+                                                            "total": 57588.91226845488,
+                                                            "count": 1596199,
                                                             "is_parallel": true,
-                                                            "self": 5690.6334428538685
+                                                            "self": 57588.91226845488
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 194.70460990589345,
-                                                            "count": 316390,
+                                                            "total": 1973.226922400645,
+                                                            "count": 3192398,
                                                             "is_parallel": true,
-                                                            "self": 23.100591495400295,
+                                                            "self": 236.34830627954216,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 171.60401841049315,
-                                                                    "count": 1265560,
+                                                                    "total": 1736.8786161211028,
+                                                                    "count": 12769592,
                                                                     "is_parallel": true,
-                                                                    "self": 171.60401841049315
+                                                                    "self": 1736.8786161211028
                                                                 }
                                                             }
                                                         }
@@ -421,31 +421,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 2708.978771697235,
-                            "count": 158195,
-                            "self": 11.918968971876893,
+                            "total": 28474.943081706588,
+                            "count": 1596199,
+                            "self": 129.82655392051674,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 517.3845484333578,
-                                    "count": 158195,
-                                    "self": 516.6691328503366,
+                                    "total": 5061.878445453796,
+                                    "count": 1596199,
+                                    "self": 5053.8462954926945,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.7154155830212403,
-                                            "count": 4,
-                                            "self": 0.7154155830212403
+                                            "total": 8.032149961101823,
+                                            "count": 47,
+                                            "self": 8.032149961101823
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 2179.6752542920003,
-                                    "count": 15,
-                                    "self": 212.8977203327231,
+                                    "total": 23283.238082332275,
+                                    "count": 157,
+                                    "self": 2272.794731600414,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 1966.7775339592772,
-                                            "count": 180,
-                                            "self": 1966.7775339592772
+                                            "total": 21010.44335073186,
+                                            "count": 1884,
+                                            "self": 21010.44335073186
                                         }
                                     }
                                 }
@@ -454,19 +454,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 4.5899651013314724e-07,
+                    "total": 4.169996827840805e-07,
                     "count": 1,
-                    "self": 4.5899651013314724e-07
+                    "self": 4.169996827840805e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.19374379198416136,
+                    "total": 0.18633362499531358,
                     "count": 1,
-                    "self": 0.0005647509824484587,
+                    "self": 0.0009461659938097,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1931790410017129,
+                            "total": 0.18538745900150388,
                             "count": 1,
-                            "self": 0.1931790410017129
+                            "self": 0.18538745900150388
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,24 @@
 {
     "SoccerTwos": {
-        "elo": 90.32114998486692,
+        "elo": 195.29137434501916,
         "checkpoints": [
             {
-                "steps": 30907162,
-                "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-30907162.onnx",
+                "steps": 54189194,
+                "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-54189194.onnx",
                 "reward": 0.0,
-                "creation_time": 1725648389.335208,
+                "creation_time": 1725834731.7809012,
                 "auxillary_file_paths": [
-                    "results/sept-run-01/SoccerTwos/SoccerTwos-30907162.pt"
+                    "results/sept-run-01/SoccerTwos/SoccerTwos-54189194.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 30907162,
+            "steps": 54189194,
             "file_path": "results/sept-run-01/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1725648389.335208,
+            "creation_time": 1725834731.7809012,
             "auxillary_file_paths": [
-                "results/sept-run-01/SoccerTwos/SoccerTwos-30907162.pt"
+                "results/sept-run-01/SoccerTwos/SoccerTwos-54189194.pt"
             ]
         }
     },