5M steps

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d19979a6c74f3f6a781d1e12bc1c3fc9c275ed185f423dd4ec9b5efac43cdd2
+oid sha256:e676dd6d074cfcc8a945a987063c776bba8def9aec143efe544091ba6bce9c6b
 size 2820313

SoccerTwos/SoccerTwos-4499964.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b274e6b6d548721a6933d5c370476767ab9a00b2ebaf36917e7f86ac595db83e
+size 2820313

SoccerTwos/SoccerTwos-4499964.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e4b3fe7f2b14ef71530dba6048a95ff2fbc83854e3685d1de567a0a08653b4
+size 34740902

SoccerTwos/SoccerTwos-4999989.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e676dd6d074cfcc8a945a987063c776bba8def9aec143efe544091ba6bce9c6b
+size 2820313

SoccerTwos/SoccerTwos-4999989.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d7a291198d4da778ab042ca512fc187b3af2082abebfebfc5559d0820d8a68
+size 34740902

SoccerTwos/SoccerTwos-5000036.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e676dd6d074cfcc8a945a987063c776bba8def9aec143efe544091ba6bce9c6b
+size 2820313

SoccerTwos/SoccerTwos-5000036.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf11e04f9130b274a0aea20a1f59e4e6c2cc6ae3dfe587bc62e7d2bf75dd6bb
+size 34740902

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ebe9e952fde5a549c3d3500d5b5d8cdf308bbff706cf8c316207083204e89d
+oid sha256:c567ea842f38b762c58f1d3f2ebcf0574e6cc509f0397b6cdca983855e1b2c6f
 size 34739782

SoccerTwos/events.out.tfevents.1718354771.9a5b644a23c3.1619.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca370126450d2d48a27e89b7c45b195ec2a99956202380b39b44207913c5b0bc
+size 1045456

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 1024, "buffer_size": 10240, "learning_rate": 0.0001, "beta": 0.01, "epsilon": 0.3, "lambd": 0.95, "num_epoch": 6, "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": 0.995, "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": 4000000, "time_horizon": 2048, "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, "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, "no_graphics_monitor": false}, "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": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 1024, "buffer_size": 10240, "learning_rate": 0.0001, "beta": 0.01, "epsilon": 0.3, "lambd": 0.95, "num_epoch": 6, "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": 0.995, "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": 5000000, "time_horizon": 2048, "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, "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, "no_graphics_monitor": false}, "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": null}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 4000000
+    max_steps: 5000000
     time_horizon: 2048
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -2,6 +2,9 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/SoccerTwos/SoccerTw
 Mono config path = '/content/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/SoccerTwos
+Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -31,7 +34,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.081 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)
@@ -56,7 +59,7 @@ 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: 0.671783 ms
+UnloadTime: 0.721597 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
@@ -65,7 +68,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 18858 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 18827 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
@@ -187,13 +190,13 @@ 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]: 18859 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 18828 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 4.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18859 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18828 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.6 MB
@@ -225,13 +228,13 @@ 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]: 18858 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18827 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]: 18859 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 18828 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -243,13 +246,13 @@ 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]: 18859 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 18828 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]: 18858 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 18827 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
@@ -261,13 +264,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18859 frames
+      Peak usage frame count: [0-1.0 KB]: 18828 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]: 18858 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18827 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

@@ -2,75 +2,75 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 2.223773241043091,
-            "min": 2.0722453594207764,
-            "max": 2.236091136932373,
+            "value": 2.1875576972961426,
+            "min": 2.144973039627075,
+            "max": 2.2713446617126465,
             "count": 100
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 45258.234375,
-            "min": 38056.3828125,
-            "max": 50514.96875,
+            "value": 45571.203125,
+            "min": 34911.1328125,
+            "max": 50452.00390625,
             "count": 100
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 77.578125,
-            "min": 51.44086021505376,
-            "max": 87.10344827586206,
+            "value": 70.14285714285714,
+            "min": 55.79545454545455,
+            "max": 105.46808510638297,
             "count": 100
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19860.0,
-            "min": 18568.0,
-            "max": 20516.0,
+            "value": 19640.0,
+            "min": 19072.0,
+            "max": 20416.0,
             "count": 100
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1488.8218073264109,
-            "min": 1468.8339752147765,
-            "max": 1508.8299624178053,
+            "value": 1475.7673077529762,
+            "min": 1455.5852748018806,
+            "max": 1495.4709782409363,
             "count": 100
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 190569.1913377806,
-            "min": 172079.39408491494,
-            "max": 276200.57098956243,
+            "value": 206607.42308541667,
+            "min": 138573.4318195411,
+            "max": 258146.97528522566,
             "count": 100
         },
         "SoccerTwos.Step.mean": {
-            "value": 3999748.0,
-            "min": 3009969.0,
-            "max": 3999748.0,
+            "value": 4999989.0,
+            "min": 4009955.0,
+            "max": 4999989.0,
             "count": 100
         },
         "SoccerTwos.Step.sum": {
-            "value": 3999748.0,
-            "min": 3009969.0,
-            "max": 3999748.0,
+            "value": 4999989.0,
+            "min": 4009955.0,
+            "max": 4999989.0,
             "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.0115288607776165,
-            "min": -0.1206521987915039,
-            "max": 0.09617013484239578,
+            "value": -0.008360597304999828,
+            "min": -0.13213926553726196,
+            "max": 0.047096967697143555,
             "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -1.475694179534912,
-            "min": -20.629596710205078,
-            "max": 17.022113800048828,
+            "value": -1.1704835891723633,
+            "min": -19.013656616210938,
+            "max": 6.358090400695801,
             "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.015976352617144585,
-            "min": -0.12377264350652695,
-            "max": 0.10104299336671829,
+            "value": -0.005427720490843058,
+            "min": -0.13081811368465424,
+            "max": 0.04446444660425186,
             "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -2.044973134994507,
-            "min": -21.404094696044922,
-            "max": 17.88460922241211,
+            "value": -0.7598809003829956,
+            "min": -19.144575119018555,
+            "max": 6.002700328826904,
             "count": 100
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
@@ -86,27 +86,27 @@
             "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.03146406123414636,
-            "min": -0.27117222133609986,
-            "max": 0.32952272575913055,
+            "value": 0.07113428797040666,
+            "min": -0.37446071580052376,
+            "max": 0.30961999893188474,
             "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -4.027399837970734,
-            "min": -46.406399846076965,
-            "max": 43.49699980020523,
+            "value": 9.958800315856934,
+            "min": -41.93960016965866,
+            "max": 37.15439987182617,
             "count": 100
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.03146406123414636,
-            "min": -0.27117222133609986,
-            "max": 0.32952272575913055,
+            "value": 0.07113428797040666,
+            "min": -0.37446071580052376,
+            "max": 0.30961999893188474,
             "count": 100
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -4.027399837970734,
-            "min": -46.406399846076965,
-            "max": 43.49699980020523,
+            "value": 9.958800315856934,
+            "min": -41.93960016965866,
+            "max": 37.15439987182617,
             "count": 100
         },
         "SoccerTwos.IsTraining.mean": {
@@ -122,39 +122,39 @@
             "count": 100
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.026185355508156743,
-            "min": 0.020323997944554625,
-            "max": 0.03133109582704492,
+            "value": 0.024346959691805146,
+            "min": 0.020130672054559304,
+            "max": 0.030631732359567346,
             "count": 96
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.026185355508156743,
-            "min": 0.020323997944554625,
-            "max": 0.03133109582704492,
+            "value": 0.024346959691805146,
+            "min": 0.020130672054559304,
+            "max": 0.030631732359567346,
             "count": 96
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.08392822475483021,
-            "min": 0.08149543609470129,
-            "max": 0.1144369309147199,
+            "value": 0.08962117247283459,
+            "min": 0.06291260526825984,
+            "max": 0.1022199623286724,
             "count": 96
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.08392822475483021,
-            "min": 0.08149543609470129,
-            "max": 0.1144369309147199,
+            "value": 0.08962117247283459,
+            "min": 0.06291260526825984,
+            "max": 0.1022199623286724,
             "count": 96
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.08637854494154454,
-            "min": 0.08300136315325896,
-            "max": 0.11914086317022642,
+            "value": 0.09580556737879913,
+            "min": 0.06390505886326234,
+            "max": 0.10687999129295349,
             "count": 96
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.08637854494154454,
-            "min": 0.08300136315325896,
-            "max": 0.11914086317022642,
+            "value": 0.09580556737879913,
+            "min": 0.06390505886326234,
+            "max": 0.10687999129295349,
             "count": 96
         },
         "SoccerTwos.Policy.LearningRate.mean": {
@@ -196,7 +196,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1718279492",
+        "start_time_seconds": "1718354770",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
         "mlagents_version": "1.1.0.dev0",
@@ -204,59 +204,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1718282010"
+        "end_time_seconds": "1718357413"
     },
-    "total": 2517.969767197,
+    "total": 2643.438411529,
     "count": 1,
-    "self": 0.43776554199985185,
+    "self": 0.44061282700022275,
     "children": {
         "run_training.setup": {
-            "total": 0.0542554039998322,
+            "total": 0.05524954800000614,
             "count": 1,
-            "self": 0.0542554039998322
+            "self": 0.05524954800000614
         },
         "TrainerController.start_learning": {
-            "total": 2517.477746251,
+            "total": 2642.9425491539996,
             "count": 1,
-            "self": 1.6043100350693749,
+            "self": 1.7481662440723085,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.372079333999409,
+                    "total": 3.148299596000129,
                     "count": 6,
-                    "self": 2.372079333999409
+                    "self": 3.148299596000129
                 },
                 "TrainerController.advance": {
-                    "total": 2513.2097595329315,
-                    "count": 68847,
-                    "self": 1.6440261898642348,
+                    "total": 2637.7337122209274,
+                    "count": 67963,
+                    "self": 1.899848016994838,
                     "children": {
                         "env_step": {
-                            "total": 1719.6449874930577,
-                            "count": 68847,
-                            "self": 1312.8831236869564,
+                            "total": 1835.5979456299804,
+                            "count": 67963,
+                            "self": 1395.1376912010285,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 405.8213756830296,
-                                    "count": 68847,
-                                    "self": 9.936953617958352,
+                                    "total": 439.4613840100016,
+                                    "count": 67963,
+                                    "self": 11.93888216498624,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 395.88442206507125,
-                                            "count": 125724,
-                                            "self": 395.88442206507125
+                                            "total": 427.52250184501537,
+                                            "count": 125514,
+                                            "self": 427.52250184501537
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.9404881230716455,
-                                    "count": 68847,
+                                    "total": 0.9988704189502755,
+                                    "count": 67963,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2512.8244949230334,
-                                            "count": 68847,
+                                            "total": 2638.251060065022,
+                                            "count": 67963,
                                             "is_parallel": true,
-                                            "self": 1408.677215260032,
+                                            "self": 1467.0694028729831,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.003062387000227318,
+                                                            "total": 0.007002816000010625,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.000803287000508135,
+                                                            "self": 0.0037053229999628456,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.002259099999719183,
+                                                                    "total": 0.00329749300004778,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.002259099999719183
+                                                                    "self": 0.00329749300004778
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03823810899984892,
+                                                            "total": 0.042755231000001004,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00118418300007761,
+                                                            "self": 0.0011683379999567478,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0008255600000666163,
+                                                                    "total": 0.0008768920000079561,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008255600000666163
+                                                                    "self": 0.0008768920000079561
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03281173899995338,
+                                                                    "total": 0.037155740999992304,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03281173899995338
+                                                                    "self": 0.037155740999992304
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0034166269997513155,
+                                                                    "total": 0.003554260000043996,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007046189994071028,
+                                                                    "self": 0.0006907179999871005,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0027120080003442126,
+                                                                            "total": 0.0028635420000568956,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0027120080003442126
+                                                                            "self": 0.0028635420000568956
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.01150233199905415,
+                                                    "total": 0.010347326000214707,
                                                     "count": 10,
                                                     "is_parallel": true,
-                                                    "self": 0.0023311429945351847,
+                                                    "self": 0.0023058779999587387,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.009171189004518965,
+                                                            "total": 0.008041448000255969,
                                                             "count": 40,
                                                             "is_parallel": true,
-                                                            "self": 0.009171189004518965
+                                                            "self": 0.008041448000255969
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1104.1357773310024,
-                                                    "count": 68846,
+                                                    "total": 1171.1713098660387,
+                                                    "count": 67962,
                                                     "is_parallel": true,
-                                                    "self": 68.31497311213025,
+                                                    "self": 72.15924076098236,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 46.387385405968416,
-                                                            "count": 68846,
+                                                            "total": 50.23150113503095,
+                                                            "count": 67962,
                                                             "is_parallel": true,
-                                                            "self": 46.387385405968416
+                                                            "self": 50.23150113503095
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 773.3335762869528,
-                                                            "count": 68846,
+                                                            "total": 815.8509057829692,
+                                                            "count": 67962,
                                                             "is_parallel": true,
-                                                            "self": 773.3335762869528
+                                                            "self": 815.8509057829692
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 216.09984252595086,
-                                                            "count": 137692,
+                                                            "total": 232.92966218705607,
+                                                            "count": 135924,
                                                             "is_parallel": true,
-                                                            "self": 36.31782842980056,
+                                                            "self": 39.79592852296594,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 179.7820140961503,
-                                                                    "count": 550768,
+                                                                    "total": 193.13373366409013,
+                                                                    "count": 543696,
                                                                     "is_parallel": true,
-                                                                    "self": 179.7820140961503
+                                                                    "self": 193.13373366409013
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 791.9207458500096,
-                            "count": 68847,
-                            "self": 12.895249707110906,
+                            "total": 800.2359185739523,
+                            "count": 67963,
+                            "self": 13.141391972977772,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 225.82177020290283,
-                                    "count": 68847,
-                                    "self": 225.14665546390233,
+                                    "total": 223.8453884169735,
+                                    "count": 67963,
+                                    "self": 223.12084548197345,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.6751147390004917,
+                                            "total": 0.724542935000045,
                                             "count": 2,
-                                            "self": 0.6751147390004917
+                                            "self": 0.724542935000045
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 553.2037259399958,
+                                    "total": 563.249138184001,
                                     "count": 96,
-                                    "self": 297.6213310639955,
+                                    "self": 308.2580305080081,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 255.5823948760003,
+                                            "total": 254.9911076759929,
                                             "count": 5760,
-                                            "self": 255.5823948760003
+                                            "self": 254.9911076759929
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.069999578059651e-07,
+                    "total": 1.0160001693293452e-06,
                     "count": 1,
-                    "self": 9.069999578059651e-07
+                    "self": 1.0160001693293452e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.2915964419999,
+                    "total": 0.3123700769997413,
                     "count": 1,
-                    "self": 0.0039638009993723244,
+                    "self": 0.004324635999637394,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.28763264100052766,
+                            "total": 0.3080454410001039,
                             "count": 1,
-                            "self": 0.28763264100052766
+                            "self": 0.3080454410001039
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 2999970,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2999970.onnx",
+                "steps": 3999748,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3999748.onnx",
                 "reward": 0.0,
-                "creation_time": 1718279377.628169,
+                "creation_time": 1718282009.9757707,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2999970.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3999748.pt"
                 ]
             },
             {
-                "steps": 3000068,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3000068.onnx",
+                "steps": 4000084,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4000084.onnx",
                 "reward": 0.0,
-                "creation_time": 1718279377.951402,
+                "creation_time": 1718282010.2985783,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3000068.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4000084.pt"
                 ]
             },
             {
-                "steps": 3499958,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3499958.onnx",
+                "steps": 4499964,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4499964.onnx",
                 "reward": 0.0,
-                "creation_time": 1718280764.2535863,
+                "creation_time": 1718356086.3615174,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3499958.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4499964.pt"
                 ]
             },
             {
-                "steps": 3999748,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3999748.onnx",
+                "steps": 4999989,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4999989.onnx",
                 "reward": 0.0,
-                "creation_time": 1718282009.9757707,
+                "creation_time": 1718357412.9373324,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3999748.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4999989.pt"
                 ]
             },
             {
-                "steps": 4000084,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4000084.onnx",
+                "steps": 5000036,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5000036.onnx",
                 "reward": 0.0,
-                "creation_time": 1718282010.2985783,
+                "creation_time": 1718357413.2604034,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4000084.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5000036.pt"
                 ]
             }
         ],
-        "elo": 1489.2215205434777,
+        "elo": 1480.663296751519,
         "final_checkpoint": {
-            "steps": 4000084,
+            "steps": 5000036,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1718282010.2985783,
+            "creation_time": 1718357413.2604034,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-4000084.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-5000036.pt"
             ]
         }
     },