6.5 million steps

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a643cbf7b2ac8d5478e93ccde9824c7b6fc525a66c00d6034f86fc3542f487a6
+oid sha256:938451bcaff44acbe51f407c436b7194c2536f33414a46d8c63a8ec4ebef6e4c
 size 2815689

SoccerTwos/{SoccerTwos-1999296.onnx → SoccerTwos-6555492.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac47805af8d5542ee031595400e2556ed067c74675337a54764fdd6820a44bc7
+oid sha256:938451bcaff44acbe51f407c436b7194c2536f33414a46d8c63a8ec4ebef6e4c
 size 2815689

SoccerTwos/{SoccerTwos-1999296.pt → SoccerTwos-6555492.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7c86154f343e186e65f0e9b4a79f1f7f17a41fa98d0cb9a878f05650adcdf03
+oid sha256:6b24686f444a9a2ee6005e0fd0ff7cd1e4f3675c1c6be7372b906f496a971669
 size 34728689

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0603acde269a37bfb4e99f923fb838c0ea5533012c6a4a336945182df7c1331b
+oid sha256:6b24686f444a9a2ee6005e0fd0ff7cd1e4f3675c1c6be7372b906f496a971669
 size 34728689

SoccerTwos/events.out.tfevents.1683487711.CLM-FVFF611QQ05P.local.92718.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27550dbaccbad0cf343c9ddfc637656823ec6bdd24d93662738cef04f49c4a1c
+size 381197

run_logs/Player-0.log

@@ -10,7 +10,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.094 seconds
+- Completed reload, in  0.097 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)
@@ -35,17 +35,16 @@ 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: 0.641916 ms
+UnloadTime: 1.679917 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 0x17144f000 may have been prematurely finalized
+Thread 0x16e6df000 may have been prematurely finalized
 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]: 14298 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 6919 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
@@ -73,7 +72,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.7 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -196,22 +195,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 2
     [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]: 14299 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 6920 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.8 MB
+      Peak Allocated memory 5.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 14299 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 6920 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.5 MB
+      Peak Allocated memory 17.4 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -240,13 +239,13 @@ 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]: 14298 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 6919 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]: 14299 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 6920 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -258,13 +257,13 @@ 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]: 14299 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 6920 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]: 14298 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 6919 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
@@ -276,13 +275,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 14299 frames
+      Peak usage frame count: [0-1.0 KB]: 6920 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]: 14298 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 6919 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

run_logs/timers.json

@@ -2,201 +2,201 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 2.479091167449951,
-            "min": 2.4658448696136475,
-            "max": 2.58561635017395,
-            "count": 76
+            "value": 2.503404140472412,
+            "min": 2.4523873329162598,
+            "max": 2.5370821952819824,
+            "count": 37
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 49899.1484375,
-            "min": 8394.09375,
-            "max": 59788.078125,
-            "count": 76
+            "value": 47905.140625,
+            "min": 16055.9697265625,
+            "max": 55159.47265625,
+            "count": 37
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 55.18681318681319,
-            "min": 35.1875,
-            "max": 83.23728813559322,
-            "count": 76
+            "value": 64.93333333333334,
+            "min": 49.91752577319588,
+            "max": 76.84375,
+            "count": 37
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 20088.0,
-            "min": 2252.0,
-            "max": 20324.0,
-            "count": 76
+            "value": 19480.0,
+            "min": 4772.0,
+            "max": 20184.0,
+            "count": 37
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1649.8954830393834,
-            "min": 1594.3697009364087,
-            "max": 1650.8506175397752,
-            "count": 76
+            "value": 1652.4748588887048,
+            "min": 1642.8951631352754,
+            "max": 1669.7917318437467,
+            "count": 37
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 300280.9779131678,
-            "min": 51997.66731364747,
-            "max": 331919.8479288847,
-            "count": 76
+            "value": 247871.2288333057,
+            "min": 76077.51671093542,
+            "max": 321056.13316160464,
+            "count": 37
         },
         "SoccerTwos.Step.mean": {
-            "value": 6179996.0,
-            "min": 5429978.0,
-            "max": 6179996.0,
-            "count": 76
+            "value": 6549982.0,
+            "min": 6189948.0,
+            "max": 6549982.0,
+            "count": 37
         },
         "SoccerTwos.Step.sum": {
-            "value": 6179996.0,
-            "min": 5429978.0,
-            "max": 6179996.0,
-            "count": 76
+            "value": 6549982.0,
+            "min": 6189948.0,
+            "max": 6549982.0,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.07872677594423294,
-            "min": -0.08215012401342392,
-            "max": 0.08388468623161316,
-            "count": 76
+            "value": 0.051142871379852295,
+            "min": -0.06000871956348419,
+            "max": 0.0756918340921402,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 14.249547004699707,
-            "min": -12.486818313598633,
-            "max": 14.249547004699707,
-            "count": 76
+            "value": 7.671430587768555,
+            "min": -9.386945724487305,
+            "max": 12.262077331542969,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.07752089947462082,
-            "min": -0.08446293324232101,
-            "max": 0.08493209630250931,
-            "count": 76
+            "value": 0.05099420249462128,
+            "min": -0.05922776460647583,
+            "max": 0.07353535294532776,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 14.031283378601074,
-            "min": -12.83836555480957,
-            "max": 14.031283378601074,
-            "count": 76
+            "value": 7.649130344390869,
+            "min": -9.559730529785156,
+            "max": 11.912727355957031,
+            "count": 37
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 76
+            "count": 37
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 76
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.18952817383392082,
-            "min": -0.30000479135684627,
-            "max": 0.28260000117800455,
-            "count": 76
+            "value": 0.07690666834513346,
+            "min": -0.2579976199638276,
+            "max": 0.22876027267273158,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 34.30459946393967,
-            "min": -50.10080015659332,
-            "max": 49.737600207328796,
-            "count": 76
+            "value": 11.53600025177002,
+            "min": -43.343600153923035,
+            "max": 35.7960000038147,
+            "count": 37
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.18952817383392082,
-            "min": -0.30000479135684627,
-            "max": 0.28260000117800455,
-            "count": 76
+            "value": 0.07690666834513346,
+            "min": -0.2579976199638276,
+            "max": 0.22876027267273158,
+            "count": 37
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 34.30459946393967,
-            "min": -50.10080015659332,
-            "max": 49.737600207328796,
-            "count": 76
+            "value": 11.53600025177002,
+            "min": -43.343600153923035,
+            "max": 35.7960000038147,
+            "count": 37
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 76
+            "count": 37
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 76
+            "count": 37
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.015399371163221076,
-            "min": 0.011844274809118361,
-            "max": 0.024232410235951345,
-            "count": 36
+            "value": 0.013742929190630093,
+            "min": 0.013162332853729216,
+            "max": 0.021872061599666873,
+            "count": 17
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.015399371163221076,
-            "min": 0.011844274809118361,
-            "max": 0.024232410235951345,
-            "count": 36
+            "value": 0.013742929190630093,
+            "min": 0.013162332853729216,
+            "max": 0.021872061599666873,
+            "count": 17
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.06767735456426939,
-            "min": 0.055261904994646706,
-            "max": 0.06967596064011256,
-            "count": 36
+            "value": 0.060539432987570765,
+            "min": 0.05456341157356898,
+            "max": 0.06828681615491708,
+            "count": 17
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.06767735456426939,
-            "min": 0.055261904994646706,
-            "max": 0.06967596064011256,
-            "count": 36
+            "value": 0.060539432987570765,
+            "min": 0.05456341157356898,
+            "max": 0.06828681615491708,
+            "count": 17
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.0684792855133613,
-            "min": 0.05549707127114137,
-            "max": 0.0708642177283764,
-            "count": 36
+            "value": 0.06114285662770271,
+            "min": 0.05531582894424598,
+            "max": 0.0692600845048825,
+            "count": 17
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.0684792855133613,
-            "min": 0.05549707127114137,
-            "max": 0.0708642177283764,
-            "count": 36
+            "value": 0.06114285662770271,
+            "min": 0.05531582894424598,
+            "max": 0.0692600845048825,
+            "count": 17
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.00025000000000000006,
             "min": 0.00025000000000000006,
             "max": 0.00025000000000000006,
-            "count": 36
+            "count": 17
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.00025000000000000006,
             "min": 0.00025000000000000006,
             "max": 0.00025000000000000006,
-            "count": 36
+            "count": 17
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.25,
             "min": 0.25,
             "max": 0.25,
-            "count": 36
+            "count": 17
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.25,
             "min": 0.25,
             "max": 0.25,
-            "count": 36
+            "count": 17
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.010000000000000002,
             "min": 0.010000000000000002,
             "max": 0.010000000000000002,
-            "count": 36
+            "count": 17
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.010000000000000002,
             "min": 0.010000000000000002,
             "max": 0.010000000000000002,
-            "count": 36
+            "count": 17
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1683484175",
+        "start_time_seconds": "1683487709",
         "python_version": "3.9.16 | packaged by conda-forge | (main, Feb  1 2023, 21:38:11) \n[Clang 14.0.6 ]",
         "command_line_arguments": "/Users/andreas.bjarlestam/mambaforge/envs/huggingface-rl-course/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
@@ -204,103 +204,103 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1683487657"
+        "end_time_seconds": "1683489353"
     },
-    "total": 3481.642826833,
+    "total": 1643.169040458,
     "count": 1,
-    "self": 0.266701749999811,
+    "self": 0.11722787500002596,
     "children": {
         "run_training.setup": {
-            "total": 0.03880720800000015,
+            "total": 0.013663792000000008,
             "count": 1,
-            "self": 0.03880720800000015
+            "self": 0.013663792000000008
         },
         "TrainerController.start_learning": {
-            "total": 3481.3373178750003,
+            "total": 1643.038148791,
             "count": 1,
-            "self": 0.7055969289958739,
+            "self": 0.31101058200579246,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.8457452910002883,
-                    "count": 5,
-                    "self": 1.8457452910002883
+                    "total": 2.2248240839999744,
+                    "count": 3,
+                    "self": 2.2248240839999744
                 },
                 "TrainerController.advance": {
-                    "total": 3478.6461231130047,
-                    "count": 52567,
-                    "self": 0.5951379080393053,
+                    "total": 1640.320858083994,
+                    "count": 25389,
+                    "self": 0.2661743909673078,
                     "children": {
                         "env_step": {
-                            "total": 2799.831084738981,
-                            "count": 52567,
-                            "self": 2701.921003805895,
+                            "total": 1330.830156340017,
+                            "count": 25389,
+                            "self": 1284.3852757490256,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 97.46038615304738,
-                                    "count": 52567,
-                                    "self": 2.8379347090271096,
+                                    "total": 46.23812745699054,
+                                    "count": 25389,
+                                    "self": 1.2487462569900671,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 94.62245144402027,
-                                            "count": 95322,
-                                            "self": 94.62245144402027
+                                            "total": 44.98938120000047,
+                                            "count": 46132,
+                                            "self": 44.98938120000047
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.4496947800386013,
-                                    "count": 52566,
+                                    "total": 0.20675313400085837,
+                                    "count": 25388,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 3478.3395808320347,
-                                            "count": 52566,
+                                            "total": 1640.2869981199963,
+                                            "count": 25388,
                                             "is_parallel": true,
-                                            "self": 853.5667974280468,
+                                            "self": 393.89563319499894,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.00852233499997479,
-                                                    "count": 10,
+                                                    "total": 0.005132874999992598,
+                                                    "count": 6,
                                                     "is_parallel": true,
-                                                    "self": 0.0010013339999064286,
+                                                    "self": 0.0006161679999161507,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.007521001000068361,
-                                                            "count": 40,
+                                                            "total": 0.0045167070000764475,
+                                                            "count": 24,
                                                             "is_parallel": true,
-                                                            "self": 0.007521001000068361
+                                                            "self": 0.0045167070000764475
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 2624.7642610689877,
-                                                    "count": 52566,
+                                                    "total": 1246.3862320499973,
+                                                    "count": 25388,
                                                     "is_parallel": true,
-                                                    "self": 7.129942069017943,
+                                                    "self": 3.1823133230072926,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 47.107922168025965,
-                                                            "count": 52566,
+                                                            "total": 22.304695663003482,
+                                                            "count": 25388,
                                                             "is_parallel": true,
-                                                            "self": 47.107922168025965
+                                                            "self": 22.304695663003482
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2473.9557799219765,
-                                                            "count": 52566,
+                                                            "total": 1175.0904308869885,
+                                                            "count": 25388,
                                                             "is_parallel": true,
-                                                            "self": 2473.9557799219765
+                                                            "self": 1175.0904308869885
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 96.57061690996699,
-                                                            "count": 105132,
+                                                            "total": 45.808792176997834,
+                                                            "count": 50776,
                                                             "is_parallel": true,
-                                                            "self": 10.97493528192777,
+                                                            "self": 5.091343413956125,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 85.59568162803922,
-                                                                    "count": 420528,
+                                                                    "total": 40.71744876304171,
+                                                                    "count": 203104,
                                                                     "is_parallel": true,
-                                                                    "self": 85.59568162803922
+                                                                    "self": 40.71744876304171
                                                                 }
                                                             }
                                                         }
@@ -313,31 +313,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 678.2199004659842,
-                            "count": 52566,
-                            "self": 4.748937736947255,
+                            "total": 309.2245273530094,
+                            "count": 25388,
+                            "self": 2.159055672025943,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 134.27234868403667,
-                                    "count": 52566,
-                                    "self": 134.07668543403662,
-                                    "children": {
-                                        "RLTrainer._checkpoint": {
-                                            "total": 0.19566325000005236,
-                                            "count": 1,
-                                            "self": 0.19566325000005236
-                                        }
-                                    }
+                                    "total": 68.22423439098337,
+                                    "count": 25388,
+                                    "self": 68.22423439098337
                                 },
                                 "_update_policy": {
-                                    "total": 539.1986140450002,
-                                    "count": 36,
-                                    "self": 65.58856171399077,
+                                    "total": 238.8412372900001,
+                                    "count": 17,
+                                    "self": 29.788104290999627,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 473.61005233100946,
-                                            "count": 1080,
-                                            "self": 473.61005233100946
+                                            "total": 209.05313299900047,
+                                            "count": 510,
+                                            "self": 209.05313299900047
                                         }
                                     }
                                 }
@@ -346,19 +339,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 4.5899969336460344e-07,
+                    "total": 4.1600014810683206e-07,
                     "count": 1,
-                    "self": 4.5899969336460344e-07
+                    "self": 4.1600014810683206e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.13985208299982332,
+                    "total": 0.18145562500012602,
                     "count": 1,
-                    "self": 0.003031791000012163,
+                    "self": 0.0011100420001639577,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.13682029199981116,
+                            "total": 0.18034558299996206,
                             "count": 1,
-                            "self": 0.13682029199981116
+                            "self": 0.18034558299996206
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,16 +1,7 @@
 {
     "SoccerTwos": {
-        "elo": 1653.8590589333792,
+        "elo": 1655.486498013031,
         "checkpoints": [
-            {
-                "steps": 1999296,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1999296.onnx",
-                "reward": 0.0,
-                "creation_time": 1683415133.0676868,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-1999296.pt"
-                ]
-            },
             {
                 "steps": 3999978,
                 "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3999978.onnx",
@@ -46,15 +37,24 @@
                 "auxillary_file_paths": [
                     "results/SoccerTwos/SoccerTwos/SoccerTwos-6187920.pt"
                 ]
+            },
+            {
+                "steps": 6555492,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6555492.onnx",
+                "reward": 0.0,
+                "creation_time": 1683489352.9770849,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-6555492.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 6187920,
+            "steps": 6555492,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1683487656.9546309,
+            "creation_time": 1683489352.9770849,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-6187920.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-6555492.pt"
             ]
         }
     },