8M steps

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df31e7eaa1c9dc0ce2630bc04be97af5a30cf137edd6656c45b236774f466347
+oid sha256:713a2f495696f30149027304681bfc08942132dc4b4ee25be89144b6e70e6d98
 size 2820313

SoccerTwos/SoccerTwos-7499981.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554fe1cc7db6885122ac32f9f857af6e0b7dd7e06e789cd43a1cb9b2d8084413
+size 2820313

SoccerTwos/SoccerTwos-7499981.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc5bd69ca06bbb337f4b8bb4fcc2f751ebd7cc840fcb9cc9715f318e5566bc8c
+size 34740902

SoccerTwos/SoccerTwos-7999987.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:713a2f495696f30149027304681bfc08942132dc4b4ee25be89144b6e70e6d98
+size 2820313

SoccerTwos/SoccerTwos-7999987.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71ceceb528ec8e49165cb90deda6eb383715823e31fe41b19ec4a787753807dd
+size 34740902

SoccerTwos/SoccerTwos-8000116.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:713a2f495696f30149027304681bfc08942132dc4b4ee25be89144b6e70e6d98
+size 2820313

SoccerTwos/SoccerTwos-8000116.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce1d19f4a277eb9bb2add58a87a879c09bb65ec73e257038ec2bc5c2ffe0b0f1
+size 34740902

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c7f7a5b3c8ee9065e39d7c6fb908c5f14432f5823eb48307da0861815f45870
+oid sha256:3c473a67348e7e8ef54c8433ef5c1e17c4b3207af9022791173924b88b3adc82
 size 34739782

SoccerTwos/events.out.tfevents.1718528868.412f5050b3f8.28429.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e12fc98020884e3607d1ebd88a23f5523aa84e72cdefdbbce51b0f064f54da
+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": 7000000, "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": 8000000, "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: 7000000
+    max_steps: 8000000
     time_horizon: 2048
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ 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
@@ -34,7 +31,7 @@ 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  0.084 seconds
+- Completed reload, in  0.083 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)
@@ -59,7 +56,7 @@ 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: 0.699797 ms
+UnloadTime: 0.776744 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
@@ -68,7 +65,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 37673 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 18859 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
@@ -190,13 +187,13 @@ 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]: 37674 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 18860 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]: 37674 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18860 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.6 MB
@@ -228,13 +225,13 @@ 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]: 37673 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18859 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]: 37674 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 18860 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -246,16 +243,16 @@ 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]: 37674 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 18860 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]: 37673 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 18859 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
+      Peak Allocated memory 4.4 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -264,13 +261,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 37674 frames
+      Peak usage frame count: [0-1.0 KB]: 18860 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]: 37673 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18859 frames, [2.0 KB-4.0 KB]: 1 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 KB

run_logs/timers.json

@@ -2,201 +2,201 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 2.1015546321868896,
-            "min": 1.9260947704315186,
-            "max": 2.2162485122680664,
-            "count": 200
+            "value": 2.075274705886841,
+            "min": 1.9769662618637085,
+            "max": 2.1356256008148193,
+            "count": 100
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 40013.6015625,
-            "min": 36403.37890625,
-            "max": 48694.53125,
-            "count": 200
+            "value": 44361.0703125,
+            "min": 37098.953125,
+            "max": 47907.8203125,
+            "count": 100
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 67.5774647887324,
-            "min": 49.686868686868685,
-            "max": 98.2,
-            "count": 200
+            "value": 61.65,
+            "min": 58.48192771084337,
+            "max": 92.0909090909091,
+            "count": 100
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19192.0,
-            "min": 18508.0,
-            "max": 20980.0,
-            "count": 200
+            "value": 19728.0,
+            "min": 18868.0,
+            "max": 20624.0,
+            "count": 100
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1501.2183115300984,
-            "min": 1458.23807506226,
-            "max": 1542.6958683603368,
-            "count": 200
+            "value": 1524.5437885884257,
+            "min": 1483.835614572962,
+            "max": 1546.1724846117934,
+            "count": 100
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 213173.00023727398,
-            "min": 152618.49962697105,
-            "max": 299146.18093298224,
-            "count": 200
+            "value": 243927.00617414812,
+            "min": 159117.6904437962,
+            "max": 262436.1696640847,
+            "count": 100
         },
         "SoccerTwos.Step.mean": {
-            "value": 6999977.0,
-            "min": 5009884.0,
-            "max": 6999977.0,
-            "count": 200
+            "value": 7999987.0,
+            "min": 7009937.0,
+            "max": 7999987.0,
+            "count": 100
         },
         "SoccerTwos.Step.sum": {
-            "value": 6999977.0,
-            "min": 5009884.0,
-            "max": 6999977.0,
-            "count": 200
+            "value": 7999987.0,
+            "min": 7009937.0,
+            "max": 7999987.0,
+            "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.021804125979542732,
-            "min": -0.16370217502117157,
-            "max": 0.09212000668048859,
-            "count": 200
+            "value": -0.03398745507001877,
+            "min": -0.09914720058441162,
+            "max": 0.13625411689281464,
+            "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -3.117990016937256,
-            "min": -22.918304443359375,
-            "max": 12.161711692810059,
-            "count": 200
+            "value": -5.437993049621582,
+            "min": -14.673786163330078,
+            "max": 19.211830139160156,
+            "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.021971693262457848,
-            "min": -0.16531510651111603,
-            "max": 0.09050528705120087,
-            "count": 200
+            "value": -0.03569308668375015,
+            "min": -0.09992273896932602,
+            "max": 0.1381271630525589,
+            "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -3.1419520378112793,
-            "min": -23.144115447998047,
-            "max": 12.065362930297852,
-            "count": 200
+            "value": -5.710893630981445,
+            "min": -14.788565635681152,
+            "max": 19.475929260253906,
+            "count": 100
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 200
+            "count": 100
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 200
+            "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.116802798701333,
-            "min": -0.31984999863540425,
-            "max": 0.2896556258201599,
-            "count": 200
+            "value": -0.12503499761223794,
+            "min": -0.2998081628157168,
+            "max": 0.31528510692271783,
+            "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -16.70280021429062,
-            "min": -43.49959981441498,
-            "max": 43.73799949884415,
-            "count": 200
+            "value": -20.00559961795807,
+            "min": -44.07179993391037,
+            "max": 44.45520007610321,
+            "count": 100
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.116802798701333,
-            "min": -0.31984999863540425,
-            "max": 0.2896556258201599,
-            "count": 200
+            "value": -0.12503499761223794,
+            "min": -0.2998081628157168,
+            "max": 0.31528510692271783,
+            "count": 100
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -16.70280021429062,
-            "min": -43.49959981441498,
-            "max": 43.73799949884415,
-            "count": 200
+            "value": -20.00559961795807,
+            "min": -44.07179993391037,
+            "max": 44.45520007610321,
+            "count": 100
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 200
+            "count": 100
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 200
+            "count": 100
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.02735576434788527,
-            "min": 0.019240433953867372,
-            "max": 0.03233269830446564,
-            "count": 193
+            "value": 0.030147571766671415,
+            "min": 0.01926161778101232,
+            "max": 0.030572262380155736,
+            "count": 96
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.02735576434788527,
-            "min": 0.019240433953867372,
-            "max": 0.03233269830446564,
-            "count": 193
+            "value": 0.030147571766671415,
+            "min": 0.01926161778101232,
+            "max": 0.030572262380155736,
+            "count": 96
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.08771065895756086,
-            "min": 0.06325821876525879,
-            "max": 0.10387932596107324,
-            "count": 193
+            "value": 0.07682948814084133,
+            "min": 0.06336750593036414,
+            "max": 0.09296437638501326,
+            "count": 96
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.08771065895756086,
-            "min": 0.06325821876525879,
-            "max": 0.10387932596107324,
-            "count": 193
+            "value": 0.07682948814084133,
+            "min": 0.06336750593036414,
+            "max": 0.09296437638501326,
+            "count": 96
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.09183911470075448,
-            "min": 0.06676506791263818,
-            "max": 0.11285836957395076,
-            "count": 193
+            "value": 0.08455546280990044,
+            "min": 0.06803815892587105,
+            "max": 0.09906086499492327,
+            "count": 96
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.09183911470075448,
-            "min": 0.06676506791263818,
-            "max": 0.11285836957395076,
-            "count": 193
+            "value": 0.08455546280990044,
+            "min": 0.06803815892587105,
+            "max": 0.09906086499492327,
+            "count": 96
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.00010000000000000003,
             "min": 0.00010000000000000003,
             "max": 0.00010000000000000003,
-            "count": 193
+            "count": 96
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.00010000000000000003,
             "min": 0.00010000000000000003,
             "max": 0.00010000000000000003,
-            "count": 193
+            "count": 96
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.30000000000000004,
             "min": 0.30000000000000004,
             "max": 0.30000000000000004,
-            "count": 193
+            "count": 96
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.30000000000000004,
             "min": 0.30000000000000004,
             "max": 0.30000000000000004,
-            "count": 193
+            "count": 96
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.010000000000000002,
             "min": 0.010000000000000002,
             "max": 0.010000000000000002,
-            "count": 193
+            "count": 96
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.010000000000000002,
             "min": 0.010000000000000002,
             "max": 0.010000000000000002,
-            "count": 193
+            "count": 96
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1718522799",
+        "start_time_seconds": "1718528867",
         "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": "1718527806"
+        "end_time_seconds": "1718531380"
     },
-    "total": 5007.439330968,
+    "total": 2513.460860014,
     "count": 1,
-    "self": 0.7543871560001207,
+    "self": 0.4401936670001305,
     "children": {
         "run_training.setup": {
-            "total": 0.05655190099992069,
+            "total": 0.05471528700036288,
             "count": 1,
-            "self": 0.05655190099992069
+            "self": 0.05471528700036288
         },
         "TrainerController.start_learning": {
-            "total": 5006.628391911,
+            "total": 2512.9659510599995,
             "count": 1,
-            "self": 3.198314339836543,
+            "self": 1.490757568070876,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.5251714379982104,
-                    "count": 11,
-                    "self": 3.5251714379982104
+                    "total": 3.2961464449999767,
+                    "count": 6,
+                    "self": 3.2961464449999767
                 },
                 "TrainerController.advance": {
-                    "total": 4999.476015936164,
-                    "count": 137066,
-                    "self": 3.4961768883786135,
+                    "total": 2507.874844134928,
+                    "count": 68266,
+                    "self": 1.6193601259265051,
                     "children": {
                         "env_step": {
-                            "total": 3411.0316363288134,
-                            "count": 137066,
-                            "self": 2609.0772045809367,
+                            "total": 1724.4243835979332,
+                            "count": 68266,
+                            "self": 1315.2181860693017,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 800.1073373739822,
-                                    "count": 137066,
-                                    "self": 21.254987563703594,
+                                    "total": 408.35218750368676,
+                                    "count": 68266,
+                                    "self": 10.641594466639617,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 778.8523498102786,
-                                            "count": 251158,
-                                            "self": 778.8523498102786
+                                            "total": 397.71059303704715,
+                                            "count": 125734,
+                                            "self": 397.71059303704715
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.8470943738943788,
-                                    "count": 137066,
+                                    "total": 0.8540100249447278,
+                                    "count": 68266,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 4998.292369874953,
-                                            "count": 137066,
+                                            "total": 2508.0644017046725,
+                                            "count": 68266,
                                             "is_parallel": true,
-                                            "self": 2805.5120150558128,
+                                            "self": 1395.3086283079301,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.006566367000004902,
+                                                            "total": 0.0045858560006308835,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.004183040999919285,
+                                                            "self": 0.0010015730003942735,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.002383326000085617,
+                                                                    "total": 0.00358428300023661,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.002383326000085617
+                                                                    "self": 0.00358428300023661
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03895461900003738,
+                                                            "total": 0.08159472399984224,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.001148698999941189,
+                                                            "self": 0.0012141500001234817,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0008545309999590245,
+                                                                    "total": 0.000845034999656491,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008545309999590245
+                                                                    "self": 0.000845034999656491
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.033607563000032314,
+                                                                    "total": 0.07599764299993694,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.033607563000032314
+                                                                    "self": 0.07599764299993694
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0033438260001048548,
+                                                                    "total": 0.003537896000125329,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006034259997704794,
+                                                                    "self": 0.0007051100001262967,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0027404000003343754,
+                                                                            "total": 0.0028327859999990324,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0027404000003343754
+                                                                            "self": 0.0028327859999990324
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.021407936998798505,
-                                                    "count": 20,
+                                                    "total": 0.014440796003327705,
+                                                    "count": 10,
                                                     "is_parallel": true,
-                                                    "self": 0.004499890997408329,
+                                                    "self": 0.002628185005960404,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.016908046001390176,
-                                                            "count": 80,
+                                                            "total": 0.011812610997367301,
+                                                            "count": 40,
                                                             "is_parallel": true,
-                                                            "self": 0.016908046001390176
+                                                            "self": 0.011812610997367301
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 2192.758946882141,
-                                                    "count": 137065,
+                                                    "total": 1112.741332600739,
+                                                    "count": 68265,
                                                     "is_parallel": true,
-                                                    "self": 138.32599547621658,
+                                                    "self": 69.125073950775,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 91.2733081709871,
-                                                            "count": 137065,
+                                                            "total": 46.844077149783516,
+                                                            "count": 68265,
                                                             "is_parallel": true,
-                                                            "self": 91.2733081709871
+                                                            "self": 46.844077149783516
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1532.1396728770892,
-                                                            "count": 137065,
+                                                            "total": 779.4261883112313,
+                                                            "count": 68265,
                                                             "is_parallel": true,
-                                                            "self": 1532.1396728770892
+                                                            "self": 779.4261883112313
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 431.019970357848,
-                                                            "count": 274130,
+                                                            "total": 217.34599318894925,
+                                                            "count": 136530,
                                                             "is_parallel": true,
-                                                            "self": 72.08200654269149,
+                                                            "self": 36.30777866155131,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 358.93796381515654,
-                                                                    "count": 1096520,
+                                                                    "total": 181.03821452739794,
+                                                                    "count": 546120,
                                                                     "is_parallel": true,
-                                                                    "self": 358.93796381515654
+                                                                    "self": 181.03821452739794
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1584.948202718972,
-                            "count": 137066,
-                            "self": 24.71473832306583,
+                            "total": 781.8311004110683,
+                            "count": 68266,
+                            "self": 11.795448302335899,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 438.04711281591324,
-                                    "count": 137066,
-                                    "self": 436.77035079591235,
+                                    "total": 212.03827831372382,
+                                    "count": 68266,
+                                    "self": 211.50231669172354,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.2767620200008878,
-                                            "count": 4,
-                                            "self": 1.2767620200008878
+                                            "total": 0.5359616220002863,
+                                            "count": 2,
+                                            "self": 0.5359616220002863
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1122.186351579993,
-                                    "count": 193,
-                                    "self": 610.287240083011,
+                                    "total": 557.9973737950086,
+                                    "count": 96,
+                                    "self": 306.94090527201297,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 511.89911149698196,
-                                            "count": 11580,
-                                            "self": 511.89911149698196
+                                            "total": 251.0564685229956,
+                                            "count": 5760,
+                                            "self": 251.0564685229956
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.1520005500642583e-06,
+                    "total": 9.480008884565905e-07,
                     "count": 1,
-                    "self": 1.1520005500642583e-06
+                    "self": 9.480008884565905e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.4288890450006875,
+                    "total": 0.30420196399973065,
                     "count": 1,
-                    "self": 0.005406617000517144,
+                    "self": 0.0056103690003510565,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.42348242800017033,
+                            "total": 0.2985915949993796,
                             "count": 1,
-                            "self": 0.42348242800017033
+                            "self": 0.2985915949993796
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 5499958,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5499958.onnx",
+                "steps": 6999977,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6999977.onnx",
                 "reward": 0.0,
-                "creation_time": 1718524039.1005392,
+                "creation_time": 1718527805.757467,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5499958.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-6999977.pt"
                 ]
             },
             {
-                "steps": 5999962,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5999962.onnx",
+                "steps": 7000094,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-7000094.onnx",
                 "reward": 0.0,
-                "creation_time": 1718525261.7350626,
+                "creation_time": 1718527806.2096646,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5999962.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-7000094.pt"
                 ]
             },
             {
-                "steps": 6499901,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6499901.onnx",
+                "steps": 7499981,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-7499981.onnx",
                 "reward": 0.0,
-                "creation_time": 1718526533.052647,
+                "creation_time": 1718530154.6861358,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-6499901.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-7499981.pt"
                 ]
             },
             {
-                "steps": 6999977,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6999977.onnx",
+                "steps": 7999987,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-7999987.onnx",
                 "reward": 0.0,
-                "creation_time": 1718527805.757467,
+                "creation_time": 1718531380.0453746,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-6999977.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-7999987.pt"
                 ]
             },
             {
-                "steps": 7000094,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-7000094.onnx",
+                "steps": 8000116,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8000116.onnx",
                 "reward": 0.0,
-                "creation_time": 1718527806.2096646,
+                "creation_time": 1718531380.3644996,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-7000094.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8000116.pt"
                 ]
             }
         ],
-        "elo": 1496.2597108583236,
+        "elo": 1518.8109240735298,
         "final_checkpoint": {
-            "steps": 7000094,
+            "steps": 8000116,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1718527806.2096646,
+            "creation_time": 1718531380.3644996,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-7000094.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-8000116.pt"
             ]
         }
     },