Second Push

SoccerTwos.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c05d4171b2264e38e2266e44f6051c78a8327ed5c398e02d59cdec05fb5a135
+size 1768747

SoccerTwos/SoccerTwos-48499979.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01b0f98665d47b3efa3906ba779d4230c1e2155f3e3c7ddbd1f05c2a68ea84c
+size 1768747

SoccerTwos/SoccerTwos-48499979.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bad0c419f23420ac2d3a8dd7bd262ca2cdfb824ad1f59eb801400f504357d77
+size 28430482

SoccerTwos/SoccerTwos-48999818.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90977ea9f471f74b1d87d62144730f17985d9ebba281161a1c269795d7079e68
+size 1768747

SoccerTwos/SoccerTwos-48999818.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c51e25f0b07a55d01a59a9b47634b5e3b71631e3bbe79f120bf01ac69e051a5e
+size 28430482

SoccerTwos/SoccerTwos-49499986.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1a7d1dcff64ff645c561cce29a7368be26359c46ac9935545e1d2f4eb8f607
+size 1768747

SoccerTwos/SoccerTwos-49499986.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df65c1674dbaff3865de4947a9f9cbaa121ccd45726668aaf6da8dbf74931f1
+size 28430482

SoccerTwos/SoccerTwos-49999960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c05d4171b2264e38e2266e44f6051c78a8327ed5c398e02d59cdec05fb5a135
+size 1768747

SoccerTwos/SoccerTwos-49999960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06738d43b64de1a2fe2773631b8f1aac3db7699b7824cf86ba44c1f96d486a21
+size 28430482

SoccerTwos/SoccerTwos-50000052.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c05d4171b2264e38e2266e44f6051c78a8327ed5c398e02d59cdec05fb5a135
+size 1768747

SoccerTwos/SoccerTwos-50000052.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10424dab4e243cf176f40861bd168f693aa2476b2d88c2afb356bbaf58a78a1e
+size 28430482

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9887aa5c2c0b5810419e84c9c21f78f9ad68d6af36be1e983b4b59bf030c65c5
+oid sha256:2a0e7cfdb3f670640148f6f5d2f0d63d904aabbdcae514cb9142fcfe6eb18c78
 size 28429366

SoccerTwos/events.out.tfevents.1700343726.WINDOWS-O7926TH.16772.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11c8bf7af33df0ace270dd701994af579abf1659e92c9e2b77778e8786460d70
-size 1051678
+oid sha256:b4b1f10d1c20352c9280a512c4e3d812e9d0aaf95611e8bb25349e630874852c
+size 51243425

config.json

@@ -1 +1 @@
-{"behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple"}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0}}, "keep_checkpoints": 5, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}}}}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -1,3 +1,4 @@
+default_settings: null
 behaviors:
   SoccerTwos:
     trainer_type: poca
@@ -10,19 +11,36 @@ behaviors:
       lambd: 0.95
       num_epoch: 3
       learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
     network_settings:
       normalize: false
       hidden_units: 512
       num_layers: 2
       vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
     reward_signals:
       extrinsic:
         gamma: 0.99
         strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
     keep_checkpoints: 5
+    even_checkpoints: false
     max_steps: 50000000
     time_horizon: 1000
     summary_freq: 10000
+    threaded: false
     self_play:
       save_steps: 50000
       team_change: 200000
@@ -30,3 +48,36 @@ behaviors:
       window: 10
       play_against_latest_model_ratio: 0.5
       initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos.exe
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -427,3 +427,266 @@ TOO LONG
 TOO LONG
 TOO LONG
 TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+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]: 941811 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 309 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 67.1 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 54 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 B
+      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 54 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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 4
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] 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 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 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 54 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 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 4
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 941812 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.8 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 941812 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.6 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 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 941811 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]: 941812 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.6 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 2
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 941812 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]: 941811 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 MB
+      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 0.9 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 941812 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]: 941811 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

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.355676531791687,
+            "min": 1.2595282793045044,
+            "max": 3.2957334518432617,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 27503.96484375,
+            "min": 18434.8828125,
+            "max": 136131.90625,
+            "count": 5000
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 63.753246753246756,
+            "min": 38.04651162790697,
+            "max": 999.0,
+            "count": 5000
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19636.0,
+            "min": 16352.0,
+            "max": 26792.0,
+            "count": 5000
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1753.9429907197841,
+            "min": 1202.1977274614337,
+            "max": 1760.1562520316327,
+            "count": 4997
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 270107.22057084675,
+            "min": 2423.3702738040024,
+            "max": 433800.0533564773,
+            "count": 4997
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 49999960.0,
+            "min": 9418.0,
+            "max": 49999960.0,
+            "count": 5000
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 49999960.0,
+            "min": 9418.0,
+            "max": 49999960.0,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.011028742417693138,
+            "min": -0.14795070886611938,
+            "max": 0.2025386244058609,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 1.709455132484436,
+            "min": -27.66678237915039,
+            "max": 36.051876068115234,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.0136345736682415,
+            "min": -0.1496773511171341,
+            "max": 0.20268335938453674,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2.113358974456787,
+            "min": -27.98966407775879,
+            "max": 36.07763671875,
+            "count": 5000
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 5000
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.0886129040871897,
+            "min": -0.4509333305888706,
+            "max": 0.4753636428804109,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 13.735000133514404,
+            "min": -65.7037997841835,
+            "max": 78.1201999783516,
+            "count": 5000
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.0886129040871897,
+            "min": -0.4509333305888706,
+            "max": 0.4753636428804109,
+            "count": 5000
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 13.735000133514404,
+            "min": -65.7037997841835,
+            "max": 78.1201999783516,
+            "count": 5000
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 5000
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 5000
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.019243442461205025,
+            "min": 0.010030461488349829,
+            "max": 0.02729246802239989,
+            "count": 2425
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.019243442461205025,
+            "min": 0.010030461488349829,
+            "max": 0.02729246802239989,
+            "count": 2425
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10468184426426888,
+            "min": 2.6213669601323395e-05,
+            "max": 0.13021189173062642,
+            "count": 2425
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10468184426426888,
+            "min": 2.6213669601323395e-05,
+            "max": 0.13021189173062642,
+            "count": 2425
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10552370697259902,
+            "min": 2.5664739465961852e-05,
+            "max": 0.1335003413259983,
+            "count": 2425
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10552370697259902,
+            "min": 2.5664739465961852e-05,
+            "max": 0.1335003413259983,
+            "count": 2425
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 2425
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 2425
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 2425
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 2425
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 2425
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 2425
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1700343720",
+        "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul  5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\C:\\Users\\Bart\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.1+cpu",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1700541470"
+    },
+    "total": 197750.01964850002,
+    "count": 1,
+    "self": 2.93624120001914,
+    "children": {
+        "run_training.setup": {
+            "total": 0.16958929999964312,
+            "count": 1,
+            "self": 0.16958929999964312
+        },
+        "TrainerController.start_learning": {
+            "total": 197746.913818,
+            "count": 1,
+            "self": 114.08844991368824,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 15.87249729965697,
+                    "count": 250,
+                    "self": 15.87249729965697
+                },
+                "TrainerController.advance": {
+                    "total": 197616.63309128664,
+                    "count": 3458165,
+                    "self": 121.2730981123168,
+                    "children": {
+                        "env_step": {
+                            "total": 92693.30244368566,
+                            "count": 3458165,
+                            "self": 68691.84114710255,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 23931.51071588529,
+                                    "count": 3458165,
+                                    "self": 664.9480715348036,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 23266.562644350488,
+                                            "count": 6278838,
+                                            "self": 23266.562644350488
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 69.95058069782681,
+                                    "count": 3458165,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 197573.14665168486,
+                                            "count": 3458165,
+                                            "is_parallel": true,
+                                            "self": 145118.66756776237,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.5794901004701387,
+                                                    "count": 500,
+                                                    "is_parallel": true,
+                                                    "self": 0.12235650054935832,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.4571335999207804,
+                                                            "count": 2000,
+                                                            "is_parallel": true,
+                                                            "self": 0.4571335999207804
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 52453.899593822,
+                                                    "count": 3458165,
+                                                    "is_parallel": true,
+                                                    "self": 2489.8652344180155,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 2045.738513398479,
+                                                            "count": 3458165,
+                                                            "is_parallel": true,
+                                                            "self": 2045.738513398479
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 39605.51885173192,
+                                                            "count": 3458165,
+                                                            "is_parallel": true,
+                                                            "self": 39605.51885173192
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 8312.77699427359,
+                                                            "count": 6916330,
+                                                            "is_parallel": true,
+                                                            "self": 1717.371448144404,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 6595.405546129186,
+                                                                    "count": 27665320,
+                                                                    "is_parallel": true,
+                                                                    "self": 6595.405546129186
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 104802.05754948867,
+                            "count": 3458165,
+                            "self": 1222.6277214249421,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 24035.652533464032,
+                                    "count": 3458165,
+                                    "self": 24009.69206736404,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 25.9604660999903,
+                                            "count": 100,
+                                            "self": 25.9604660999903
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 79543.7772945997,
+                                    "count": 2425,
+                                    "self": 9002.741671698313,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 70541.03562290139,
+                                            "count": 72750,
+                                            "self": 70541.03562290139
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.100008375942707e-06,
+                    "count": 1,
+                    "self": 1.100008375942707e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.31977840000763535,
+                    "count": 1,
+                    "self": 0.051443700038362294,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.26833469996927306,
+                            "count": 1,
+                            "self": 0.26833469996927306
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 48499979,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-48499979.onnx",
+                "reward": 0.0,
+                "creation_time": 1700534824.340948,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-48499979.pt"
+                ]
+            },
+            {
+                "steps": 48999818,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-48999818.onnx",
+                "reward": 0.0,
+                "creation_time": 1700537075.3018277,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-48999818.pt"
+                ]
+            },
+            {
+                "steps": 49499986,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-49499986.onnx",
+                "reward": 0.0,
+                "creation_time": 1700539256.8020291,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-49499986.pt"
+                ]
+            },
+            {
+                "steps": 49999960,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-49999960.onnx",
+                "reward": 0.0,
+                "creation_time": 1700541467.137239,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-49999960.pt"
+                ]
+            },
+            {
+                "steps": 50000052,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-50000052.onnx",
+                "reward": 0.0,
+                "creation_time": 1700541467.448456,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-50000052.pt"
+                ]
+            }
+        ],
+        "elo": 1758.9320744488416,
+        "final_checkpoint": {
+            "steps": 50000052,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1700541467.448456,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-50000052.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.1.1+cpu"
+    }
+}