update model

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db16257a16d8a5edcec5cfda3d1d520fbb836725aa82b59309b92f87be582670
+oid sha256:f0b3efc441ea564a011f371ebc808239f417d3394c170e805a65078aed3677d7
 size 2820312

SoccerTwos/SoccerTwos-14999989.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:db16257a16d8a5edcec5cfda3d1d520fbb836725aa82b59309b92f87be582670
-size 2820312

SoccerTwos/SoccerTwos-14999989.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:387f25ee8aa4491c7d2678e170b3b3f25ce61e41c2dfcdb9c22cae9974e8311d
-size 34740585

SoccerTwos/SoccerTwos-15000204.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:db16257a16d8a5edcec5cfda3d1d520fbb836725aa82b59309b92f87be582670
-size 2820312

SoccerTwos/SoccerTwos-15000204.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e8080c7f1e685a51a013e788a4b2ca406415e1dcee7037b5b55391cbfe9c4f7d
-size 34740585

SoccerTwos/{SoccerTwos-13499887.onnx → SoccerTwos-39999991.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea266deee30c1f598db03b99409d79c0f9c584c91c2eaae9b366be0a775b2537
+oid sha256:f0b3efc441ea564a011f371ebc808239f417d3394c170e805a65078aed3677d7
 size 2820312

SoccerTwos/{SoccerTwos-14499962.pt → SoccerTwos-39999991.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c95e19e81e6475295a63436997d175037bfa6d105b1c65c54d4904090eb3ff
+oid sha256:34880d4cebae3f74acee897278631a690aa7dfb9a6d95002c9bed4ff83421871
 size 34740585

SoccerTwos/{SoccerTwos-14499962.onnx → SoccerTwos-40000002.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe74a9da39c26ef2e7ed23fd8d1af6b9f8d757e6512f76fbd7572c937dffb17a
+oid sha256:f0b3efc441ea564a011f371ebc808239f417d3394c170e805a65078aed3677d7
 size 2820312

SoccerTwos/{SoccerTwos-13499887.pt → SoccerTwos-40000002.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cafe7cece0e34c09ff25d73b47b958d85269c2e3df219906c56fb9549bfed67e
+oid sha256:5f917702fdb04abd0e425bbb8dc2a35e1bd32ee0dd4b831212d67c8f553cb7fc
 size 34740585

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145fc44486f0a53dbafa80488bd3e0bd24fcba6859f4878d2358149d11352cf5
+oid sha256:080d5b56b016042c198a9610e99697bd2df9a152f8b3dee33f105c7eb979d78c
 size 34739343

SoccerTwos/{SoccerTwos-13999935.onnx → events.out.tfevents.1684790929.Ubuntu-PC.766685.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7562b7a78507eead4fc61b0e7b2ed6e6811c4b5a3e06b174b1c254fbda5e9ff9
-size 2820312
+oid sha256:d71d05e951b0aea38fe54643b9e76f503e32088518c61fa0d694649baa16a67b
+size 1241

SoccerTwos/{SoccerTwos-13999935.pt → events.out.tfevents.1684790942.Ubuntu-PC.767076.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d00d4a509462692d9b7f8b14234271db853949b0b07d17928a5ebb19e64ad624
-size 34740585
+oid sha256:f7d1dc500faa8bd19bff9decd08fab2f9c46f21545af903776d4eeaa0d8a42c9
+size 25695939

config.json

@@ -1 +1 @@
-{"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": 3, "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": 15000000, "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/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cuda"}, "debug": false}
+{"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": 3, "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": 40000000, "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/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cuda"}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 15000000
+    max_steps: 40000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -11,7 +11,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.030 seconds
+- Completed reload, in  0.039 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)
@@ -36,7 +36,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.342024 ms
+UnloadTime: 0.518953 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
@@ -45,7 +45,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 188094 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 470742 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
@@ -90,12 +90,12 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 14]
+    [ALLOC_TEMP_Job.Worker 17]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 17]
+    [ALLOC_TEMP_Job.Worker 14]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -198,7 +198,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 5]
       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 9]
       Initial Block Size 32.0 KB
@@ -285,15 +285,15 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 15]
+    [ALLOC_TEMP_Job.Worker 24]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 24]
+    [ALLOC_TEMP_Job.Worker 15]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.7 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 12]
       Initial Block Size 256.0 KB
@@ -317,16 +317,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 188095 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 470743 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.1 MB
+      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]: 188095 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 470743 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.3 MB
+      Peak Allocated memory 17.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -355,13 +355,13 @@ 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]: 188094 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 470742 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]: 188095 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 470743 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -373,13 +373,13 @@ 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]: 188095 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 470743 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]: 188094 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 470742 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.5 MB
@@ -391,13 +391,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 188095 frames
+      Peak usage frame count: [0-1.0 KB]: 470743 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]: 188094 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 470742 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": 1.6099094152450562,
-            "min": 1.5207527875900269,
-            "max": 2.384139060974121,
-            "count": 1000
+            "value": 1.5536229610443115,
+            "min": 1.4646261930465698,
+            "max": 1.760551929473877,
+            "count": 2500
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 32404.255859375,
-            "min": 27570.814453125,
-            "max": 50887.06640625,
-            "count": 1000
+            "value": 33110.8125,
+            "min": 25699.720703125,
+            "max": 40227.5234375,
+            "count": 2500
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 63.177215189873415,
-            "min": 37.93076923076923,
-            "max": 77.25,
-            "count": 1000
+            "value": 59.1566265060241,
+            "min": 39.65040650406504,
+            "max": 107.93617021276596,
+            "count": 2500
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19964.0,
-            "min": 18560.0,
-            "max": 20964.0,
-            "count": 1000
+            "value": 19640.0,
+            "min": 17956.0,
+            "max": 21688.0,
+            "count": 2500
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1630.5526151676804,
-            "min": 1380.5516471633684,
-            "max": 1658.2405356683296,
-            "count": 1000
+            "value": 1750.8003723371896,
+            "min": 1593.0087183635371,
+            "max": 1780.794708391531,
+            "count": 2500
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 257627.31319649352,
-            "min": 196305.03927465307,
-            "max": 420312.2336165031,
-            "count": 1000
+            "value": 290632.8618079735,
+            "min": 146310.62343439288,
+            "max": 420852.7818264838,
+            "count": 2500
         },
         "SoccerTwos.Step.mean": {
-            "value": 14999989.0,
-            "min": 5009930.0,
-            "max": 14999989.0,
-            "count": 1000
+            "value": 39999991.0,
+            "min": 15009990.0,
+            "max": 39999991.0,
+            "count": 2500
         },
         "SoccerTwos.Step.sum": {
-            "value": 14999989.0,
-            "min": 5009930.0,
-            "max": 14999989.0,
-            "count": 1000
+            "value": 39999991.0,
+            "min": 15009990.0,
+            "max": 39999991.0,
+            "count": 2500
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.02849951945245266,
-            "min": -0.10880010575056076,
-            "max": 0.11400023102760315,
-            "count": 1000
+            "value": 0.008870936930179596,
+            "min": -0.1474827378988266,
+            "max": 0.09885743260383606,
+            "count": 2500
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -4.502923965454102,
-            "min": -19.710926055908203,
-            "max": 22.08706283569336,
-            "count": 1000
+            "value": 1.4725755453109741,
+            "min": -27.809024810791016,
+            "max": 19.67262840270996,
+            "count": 2500
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.024522004649043083,
-            "min": -0.11366839706897736,
-            "max": 0.10873111337423325,
-            "count": 1000
+            "value": 0.007196516264230013,
+            "min": -0.14821502566337585,
+            "max": 0.09854020178318024,
+            "count": 2500
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -3.874476671218872,
-            "min": -20.68764877319336,
-            "max": 22.398609161376953,
-            "count": 1000
+            "value": 1.1946216821670532,
+            "min": -28.603038787841797,
+            "max": 19.609500885009766,
+            "count": 2500
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 1000
+            "count": 2500
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 1000
+            "count": 2500
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.05733291069163552,
-            "min": -0.32792437817919906,
-            "max": 0.3206224626398341,
-            "count": 1000
+            "value": 0.15708433791815515,
+            "min": -0.41191186440193045,
+            "max": 0.3659299303145304,
+            "count": 2500
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -9.058599889278412,
-            "min": -65.91280001401901,
-            "max": 59.95640051364899,
-            "count": 1000
+            "value": 26.076000094413757,
+            "min": -60.09400010108948,
+            "max": 53.531400203704834,
+            "count": 2500
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.05733291069163552,
-            "min": -0.32792437817919906,
-            "max": 0.3206224626398341,
-            "count": 1000
+            "value": 0.15708433791815515,
+            "min": -0.41191186440193045,
+            "max": 0.3659299303145304,
+            "count": 2500
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -9.058599889278412,
-            "min": -65.91280001401901,
-            "max": 59.95640051364899,
-            "count": 1000
+            "value": 26.076000094413757,
+            "min": -60.09400010108948,
+            "max": 53.531400203704834,
+            "count": 2500
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 1000
+            "count": 2500
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 1000
+            "count": 2500
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.0149743233230159,
-            "min": 0.011443423058760041,
-            "max": 0.026090294665967424,
-            "count": 486
+            "value": 0.02259683023633746,
+            "min": 0.009940433162652577,
+            "max": 0.02742672897487258,
+            "count": 1213
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.0149743233230159,
-            "min": 0.011443423058760041,
-            "max": 0.026090294665967424,
-            "count": 486
+            "value": 0.02259683023633746,
+            "min": 0.009940433162652577,
+            "max": 0.02742672897487258,
+            "count": 1213
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.10135304778814316,
-            "min": 0.08815950925151507,
-            "max": 0.12917640407880146,
-            "count": 486
+            "value": 0.09963143567244212,
+            "min": 0.06914763388534387,
+            "max": 0.12024639075001081,
+            "count": 1213
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.10135304778814316,
-            "min": 0.08815950925151507,
-            "max": 0.12917640407880146,
-            "count": 486
+            "value": 0.09963143567244212,
+            "min": 0.06914763388534387,
+            "max": 0.12024639075001081,
+            "count": 1213
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.10274179776509602,
-            "min": 0.08971414019664128,
-            "max": 0.13080705429116884,
-            "count": 486
+            "value": 0.1010699396332105,
+            "min": 0.06972433105111123,
+            "max": 0.12211980223655701,
+            "count": 1213
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.10274179776509602,
-            "min": 0.08971414019664128,
-            "max": 0.13080705429116884,
-            "count": 486
+            "value": 0.1010699396332105,
+            "min": 0.06972433105111123,
+            "max": 0.12211980223655701,
+            "count": 1213
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 486
+            "count": 1213
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 486
+            "count": 1213
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 486
+            "count": 1213
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 486
+            "count": 1213
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 486
+            "count": 1213
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 486
+            "count": 1213
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1684779147",
+        "start_time_seconds": "1684790941",
         "python_version": "3.9.16 | packaged by conda-forge | (main, Feb  1 2023, 21:39:03) \n[GCC 11.3.0]",
         "command_line_arguments": "ml-agents/mlagents/trainers/learn.py ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cuda",
         "mlagents_version": "0.31.0.dev0",
@@ -204,59 +204,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.0.1+cu118",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1684784885"
+        "end_time_seconds": "1684811384"
     },
-    "total": 5738.293310943998,
+    "total": 20443.025759655,
     "count": 1,
-    "self": 0.16640525999901,
+    "self": 10.002160001997254,
     "children": {
         "run_training.setup": {
-            "total": 0.006291360001341673,
+            "total": 0.006411153997760266,
             "count": 1,
-            "self": 0.006291360001341673
+            "self": 0.006411153997760266
         },
         "TrainerController.start_learning": {
-            "total": 5738.120614323998,
+            "total": 20433.017188499005,
             "count": 1,
-            "self": 5.686786572623532,
+            "self": 25.589395618218987,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.5485932720075652,
-                    "count": 51,
-                    "self": 1.5485932720075652
+                    "total": 2.607153018034296,
+                    "count": 126,
+                    "self": 2.607153018034296
                 },
                 "TrainerController.advance": {
-                    "total": 5730.810328043368,
-                    "count": 700812,
-                    "self": 5.292680743667006,
+                    "total": 20404.732021175754,
+                    "count": 1724500,
+                    "self": 24.108064133695734,
                     "children": {
                         "env_step": {
-                            "total": 4235.785418268359,
-                            "count": 700812,
-                            "self": 3243.6642487515273,
+                            "total": 16088.52694243619,
+                            "count": 1724500,
+                            "self": 12762.514835455564,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 989.048752669034,
-                                    "count": 700812,
-                                    "self": 36.69071319253635,
+                                    "total": 3311.9066072354035,
+                                    "count": 1724500,
+                                    "self": 128.34764140984043,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 952.3580394764977,
-                                            "count": 1253978,
-                                            "self": 952.3580394764977
+                                            "total": 3183.558965825563,
+                                            "count": 3138322,
+                                            "self": 3183.558965825563
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 3.0724168477972853,
-                                    "count": 700812,
+                                    "total": 14.105499745222914,
+                                    "count": 1724500,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 5730.651753197661,
-                                            "count": 700812,
+                                            "total": 20393.824758301052,
+                                            "count": 1724500,
                                             "is_parallel": true,
-                                            "self": 3042.8718115734773,
+                                            "self": 9818.275900024593,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0015056480042403564,
+                                                            "total": 0.0016739630009396933,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.00041794100252445787,
+                                                            "self": 0.00043142000504303724,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0010877070017158985,
+                                                                    "total": 0.001242542995896656,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0010877070017158985
+                                                                    "self": 0.001242542995896656
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.011163593997480348,
+                                                            "total": 0.017040332000760827,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0002702169949770905,
+                                                            "self": 0.00039519099664175883,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.000198353998712264,
+                                                                    "total": 0.000521194000612013,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000198353998712264
+                                                                    "self": 0.000521194000612013
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.009959303002688102,
+                                                                    "total": 0.014854239001579117,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.009959303002688102
+                                                                    "self": 0.014854239001579117
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0007357200011028908,
+                                                                    "total": 0.0012697080019279383,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0001429900039511267,
+                                                                    "self": 0.0002921249979408458,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0005927299971517641,
+                                                                            "total": 0.0009775830039870925,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0005927299971517641
+                                                                            "self": 0.0009775830039870925
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.03402553797059227,
-                                                    "count": 100,
+                                                    "total": 0.13475248996110167,
+                                                    "count": 250,
                                                     "is_parallel": true,
-                                                    "self": 0.006169039937958587,
+                                                    "self": 0.02830800197989447,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.02785649803263368,
-                                                            "count": 400,
+                                                            "total": 0.1064444879812072,
+                                                            "count": 1000,
                                                             "is_parallel": true,
-                                                            "self": 0.02785649803263368
+                                                            "self": 0.1064444879812072
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 2687.7459160862127,
-                                                    "count": 700811,
+                                                    "total": 10575.414105786498,
+                                                    "count": 1724499,
                                                     "is_parallel": true,
-                                                    "self": 164.7059383653468,
+                                                    "self": 594.4687469570708,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 87.95222477414063,
-                                                            "count": 700811,
+                                                            "total": 533.7888713077118,
+                                                            "count": 1724499,
                                                             "is_parallel": true,
-                                                            "self": 87.95222477414063
+                                                            "self": 533.7888713077118
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2005.0622043327712,
-                                                            "count": 700811,
+                                                            "total": 7700.455723999505,
+                                                            "count": 1724499,
                                                             "is_parallel": true,
-                                                            "self": 2005.0622043327712
+                                                            "self": 7700.455723999505
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 430.025548613954,
-                                                            "count": 1401622,
+                                                            "total": 1746.7007635222108,
+                                                            "count": 3448998,
                                                             "is_parallel": true,
-                                                            "self": 77.20184635687838,
+                                                            "self": 370.921058991873,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 352.82370225707564,
-                                                                    "count": 5606488,
+                                                                    "total": 1375.7797045303378,
+                                                                    "count": 13795992,
                                                                     "is_parallel": true,
-                                                                    "self": 352.82370225707564
+                                                                    "self": 1375.7797045303378
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1489.7322290313423,
-                            "count": 700812,
-                            "self": 38.19949424334118,
+                            "total": 4292.097014605868,
+                            "count": 1724500,
+                            "self": 171.6146233105028,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 649.0925412990582,
-                                    "count": 700812,
-                                    "self": 647.4561120400504,
+                                    "total": 1799.4591496293579,
+                                    "count": 1724500,
+                                    "self": 1794.4988771283606,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.6364292590078549,
-                                            "count": 20,
-                                            "self": 1.6364292590078549
+                                            "total": 4.960272500997235,
+                                            "count": 50,
+                                            "self": 4.960272500997235
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 802.4401934889429,
-                                    "count": 486,
-                                    "self": 560.5196833143345,
+                                    "total": 2321.0232416660074,
+                                    "count": 1213,
+                                    "self": 1566.922360837445,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 241.92051017460835,
-                                            "count": 14580,
-                                            "self": 241.92051017460835
+                                            "total": 754.1008808285624,
+                                            "count": 36390,
+                                            "self": 754.1008808285624
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 4.2300234781578183e-07,
+                    "total": 3.800014383159578e-07,
                     "count": 1,
-                    "self": 4.2300234781578183e-07
+                    "self": 3.800014383159578e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.07490601299650734,
+                    "total": 0.08861830699606799,
                     "count": 1,
-                    "self": 0.0016170749950106256,
+                    "self": 0.0014972619974287227,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.07328893800149672,
+                            "total": 0.08712104499863926,
                             "count": 1,
-                            "self": 0.07328893800149672
+                            "self": 0.08712104499863926
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 13499887,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13499887.onnx",
+                "steps": 38499964,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-38499964.onnx",
                 "reward": 0.0,
-                "creation_time": 1684784025.8063636,
+                "creation_time": 1684810148.280004,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13499887.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-38499964.pt"
                 ]
             },
             {
-                "steps": 13999935,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13999935.onnx",
+                "steps": 38999920,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-38999920.onnx",
                 "reward": 0.0,
-                "creation_time": 1684784312.4536872,
+                "creation_time": 1684810557.3026223,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13999935.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-38999920.pt"
                 ]
             },
             {
-                "steps": 14499962,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14499962.onnx",
+                "steps": 39499976,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-39499976.onnx",
                 "reward": 0.0,
-                "creation_time": 1684784598.997238,
+                "creation_time": 1684810967.1962366,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14499962.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-39499976.pt"
                 ]
             },
             {
-                "steps": 14999989,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14999989.onnx",
+                "steps": 39999991,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-39999991.onnx",
                 "reward": 0.0,
-                "creation_time": 1684784885.1055276,
+                "creation_time": 1684811374.3563461,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14999989.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-39999991.pt"
                 ]
             },
             {
-                "steps": 15000204,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-15000204.onnx",
+                "steps": 40000002,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-40000002.onnx",
                 "reward": 0.0,
-                "creation_time": 1684784885.1875482,
+                "creation_time": 1684811374.4473386,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-15000204.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-40000002.pt"
                 ]
             }
         ],
-        "elo": 1629.846833513727,
+        "elo": 1756.599478811482,
         "final_checkpoint": {
-            "steps": 15000204,
+            "steps": 40000002,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1684784885.1875482,
+            "creation_time": 1684811374.4473386,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-15000204.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-40000002.pt"
             ]
         }
     },