max_steps = 5e7

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b68d8ded7e782d2d13417503c2e276b51d5748897f78a40ac4a76236c7fc38
+oid sha256:ea84d713dd9a5281cd930a0d557bbfb84f2fcca51513d3659754f2061fe201ba
 size 1768747

SoccerTwos/SoccerTwos-48499998.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a632f9d437986f866df0e9c41de74c60b58cde35c2d38c9b56683389d5a91c56
+size 1768747

SoccerTwos/SoccerTwos-48499998.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2744057ff1d8c91e10ada09da48730ce2ec563f211020d15090731133fb328d1
+size 28430482

SoccerTwos/SoccerTwos-48999968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c803315c2d900301adfa59c6eaaf5db739902c0ae8cd3ed079ae74de7dc81a2
+size 1768747

SoccerTwos/SoccerTwos-48999968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6d3c6b1bd144548e5e76620d8cdc583ebe726598302b036901b79c6f3ce0471
+size 28430482

SoccerTwos/SoccerTwos-49499924.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee95f2d18b6c8548904903ec5a2d9020ab8c0a976c81c8d393a9c07be39937e
+size 1768747

SoccerTwos/SoccerTwos-49499924.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1ebbf664de0a26e01bc351807d02a9c2e20856ebf10bfa8e6ae235da45f76b
+size 28430482

SoccerTwos/SoccerTwos-49999946.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea84d713dd9a5281cd930a0d557bbfb84f2fcca51513d3659754f2061fe201ba
+size 1768747

SoccerTwos/SoccerTwos-49999946.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c6d956026c65edda48ea588ba26dcbd94045d5f715613e420b5468cf44e9a5
+size 28430482

SoccerTwos/SoccerTwos-50000232.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea84d713dd9a5281cd930a0d557bbfb84f2fcca51513d3659754f2061fe201ba
+size 1768747

SoccerTwos/SoccerTwos-50000232.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d88bbe9c30236802eea4de9d920539dc36eddff32cd40b33b639fe2b14fa8b85
+size 28430482

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41dd465419f2769ff8a76dae4a39b8c04f665683e81f046abdc8ac3d55ee9b7b
+oid sha256:73da84a4f8eefc4c1e90361e8d017348638e724b91698e9938ddd316d87e6406
 size 28429366

SoccerTwos/events.out.tfevents.1711023583.magixn.925.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:502b3d2536ca3bb25fbd6df9b2b1bd514ce1366ceba912f22ce4d1ef91d979c2
+size 30835017

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": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 20000000, "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, "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": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/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: 20000000
+    max_steps: 50000000
     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  0.196 seconds
+- Completed reload, in  0.119 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: 1.655146 ms
+UnloadTime: 0.923190 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]: 75308 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 564796 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
@@ -191,22 +191,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 4
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 75309 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 564797 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.8 MB
+      Peak Allocated memory 4.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 75309 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 564797 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.5 MB
+      Peak Allocated memory 17.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -235,13 +235,13 @@ 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]: 75308 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 564796 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]: 75309 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 564797 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -253,13 +253,13 @@ 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]: 75309 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 564797 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]: 75308 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 564796 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
@@ -271,13 +271,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 75309 frames
+      Peak usage frame count: [0-1.0 KB]: 564797 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]: 75308 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 564796 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": 1.2998497486114502,
-            "min": 1.2559539079666138,
-            "max": 1.5693966150283813,
-            "count": 400
+            "value": 1.4757105112075806,
+            "min": 1.215389370918274,
+            "max": 1.5331782102584839,
+            "count": 3000
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 26121.78125,
-            "min": 24519.349609375,
-            "max": 35746.3984375,
-            "count": 400
+            "value": 30458.6640625,
+            "min": 22295.75390625,
+            "max": 35608.2890625,
+            "count": 3000
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 52.87096774193548,
-            "min": 37.63358778625954,
-            "max": 76.18181818181819,
-            "count": 400
+            "value": 63.25974025974026,
+            "min": 36.84090909090909,
+            "max": 103.41666666666667,
+            "count": 3000
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19668.0,
-            "min": 18492.0,
-            "max": 20832.0,
-            "count": 400
+            "value": 19484.0,
+            "min": 18048.0,
+            "max": 21840.0,
+            "count": 3000
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1551.4217371963712,
-            "min": 1492.1606811671516,
-            "max": 1581.0444189500447,
-            "count": 400
+            "value": 1573.6766903110993,
+            "min": 1442.8773657611414,
+            "max": 1663.9050228287604,
+            "count": 3000
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 288564.443118525,
-            "min": 203722.34391217664,
-            "max": 411420.54125740804,
-            "count": 400
+            "value": 242346.2103079093,
+            "min": 154046.1627968983,
+            "max": 402418.1796228269,
+            "count": 3000
         },
         "SoccerTwos.Step.mean": {
-            "value": 19999982.0,
-            "min": 16009962.0,
-            "max": 19999982.0,
-            "count": 400
+            "value": 49999946.0,
+            "min": 20009996.0,
+            "max": 49999946.0,
+            "count": 3000
         },
         "SoccerTwos.Step.sum": {
-            "value": 19999982.0,
-            "min": 16009962.0,
-            "max": 19999982.0,
-            "count": 400
+            "value": 49999946.0,
+            "min": 20009996.0,
+            "max": 49999946.0,
+            "count": 3000
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.011256443336606026,
-            "min": -0.09370145946741104,
-            "max": 0.08059979230165482,
-            "count": 400
+            "value": -0.027925865724682808,
+            "min": -0.13085119426250458,
+            "max": 0.09527774900197983,
+            "count": 3000
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -2.093698501586914,
-            "min": -19.864709854125977,
-            "max": 14.185564041137695,
-            "count": 400
+            "value": -4.328509330749512,
+            "min": -28.29364776611328,
+            "max": 18.740930557250977,
+            "count": 3000
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.0030689886771142483,
-            "min": -0.09180419147014618,
-            "max": 0.08833260834217072,
-            "count": 400
+            "value": -0.027023281902074814,
+            "min": -0.1322842240333557,
+            "max": 0.09797108918428421,
+            "count": 3000
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -0.5708318948745728,
-            "min": -18.918811798095703,
-            "max": 15.546539306640625,
-            "count": 400
+            "value": -4.188608646392822,
+            "min": -28.20203399658203,
+            "max": 19.740550994873047,
+            "count": 3000
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 400
+            "count": 3000
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 400
+            "count": 3000
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.0055612921714782715,
-            "min": -0.3871712427513272,
-            "max": 0.2819730072665068,
-            "count": 400
+            "value": 0.08620903222791611,
+            "min": -0.4535480030377706,
+            "max": 0.3041645398376681,
+            "count": 3000
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 1.0344003438949585,
-            "min": -63.5331996679306,
-            "max": 45.96160018444061,
-            "count": 400
+            "value": 13.362399995326996,
+            "min": -68.32039994001389,
+            "max": 55.68720030784607,
+            "count": 3000
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.0055612921714782715,
-            "min": -0.3871712427513272,
-            "max": 0.2819730072665068,
-            "count": 400
+            "value": 0.08620903222791611,
+            "min": -0.4535480030377706,
+            "max": 0.3041645398376681,
+            "count": 3000
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 1.0344003438949585,
-            "min": -63.5331996679306,
-            "max": 45.96160018444061,
-            "count": 400
+            "value": 13.362399995326996,
+            "min": -68.32039994001389,
+            "max": 55.68720030784607,
+            "count": 3000
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 400
+            "count": 3000
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 400
+            "count": 3000
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.016720845216574767,
-            "min": 0.011207520195360606,
-            "max": 0.02337836337586244,
-            "count": 194
+            "value": 0.01824698790248173,
+            "min": 0.010630287903283412,
+            "max": 0.02478914411816125,
+            "count": 1456
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.016720845216574767,
-            "min": 0.011207520195360606,
-            "max": 0.02337836337586244,
-            "count": 194
+            "value": 0.01824698790248173,
+            "min": 0.010630287903283412,
+            "max": 0.02478914411816125,
+            "count": 1456
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.11774471799532572,
-            "min": 0.0912114014228185,
-            "max": 0.13491709729035695,
-            "count": 194
+            "value": 0.08349171156684558,
+            "min": 0.07642882963021597,
+            "max": 0.13404745186368625,
+            "count": 1456
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.11774471799532572,
-            "min": 0.0912114014228185,
-            "max": 0.13491709729035695,
-            "count": 194
+            "value": 0.08349171156684558,
+            "min": 0.07642882963021597,
+            "max": 0.13404745186368625,
+            "count": 1456
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.12099931662281355,
-            "min": 0.09311052610476812,
-            "max": 0.13741760924458504,
-            "count": 194
+            "value": 0.08438854391376177,
+            "min": 0.0767000397046407,
+            "max": 0.13709546675284703,
+            "count": 1456
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.12099931662281355,
-            "min": 0.09311052610476812,
-            "max": 0.13741760924458504,
-            "count": 194
+            "value": 0.08438854391376177,
+            "min": 0.0767000397046407,
+            "max": 0.13709546675284703,
+            "count": 1456
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 194
+            "count": 1456
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 194
+            "count": 1456
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 194
+            "count": 1456
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 194
+            "count": 1456
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 194
+            "count": 1456
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 194
+            "count": 1456
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1709787594",
+        "start_time_seconds": "1711023582",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
         "command_line_arguments": "/home/magixn/anaconda3/envs/rl/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": "2.2.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1709801928"
+        "end_time_seconds": "1711133055"
     },
-    "total": 14333.158269389001,
+    "total": 109472.44741512701,
     "count": 1,
-    "self": 10.016362172002118,
+    "self": 10.013290245013195,
     "children": {
         "run_training.setup": {
-            "total": 0.06452869899976577,
+            "total": 0.03806096100001355,
             "count": 1,
-            "self": 0.06452869899976577
+            "self": 0.03806096100001355
         },
         "TrainerController.start_learning": {
-            "total": 14323.077378517999,
+            "total": 109462.396063921,
             "count": 1,
-            "self": 9.385132886722204,
+            "self": 73.4563194719085,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.194977257005576,
-                    "count": 21,
-                    "self": 4.194977257005576
+                    "total": 7.119639347978875,
+                    "count": 151,
+                    "self": 7.119639347978875
                 },
                 "TrainerController.advance": {
-                    "total": 14309.164552801274,
-                    "count": 279516,
-                    "self": 10.31230627066725,
+                    "total": 109381.6259710041,
+                    "count": 2082683,
+                    "self": 80.5391434408084,
                     "children": {
                         "env_step": {
-                            "total": 7397.765251276178,
-                            "count": 279516,
-                            "self": 5978.570261366578,
+                            "total": 53412.314257703205,
+                            "count": 2082683,
+                            "self": 43623.686861552116,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 1413.2513013149528,
-                                    "count": 279516,
-                                    "self": 51.43123356630622,
+                                    "total": 9743.353611256794,
+                                    "count": 2082683,
+                                    "self": 376.12653230122123,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 1361.8200677486466,
-                                            "count": 502066,
-                                            "self": 1361.8200677486466
+                                            "total": 9367.227078955573,
+                                            "count": 3765364,
+                                            "self": 9367.227078955573
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 5.943688594647028,
-                                    "count": 279516,
+                                    "total": 45.2737848942956,
+                                    "count": 2082683,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 14302.20405525057,
-                                            "count": 279516,
+                                            "total": 109318.56385391075,
+                                            "count": 2082683,
                                             "is_parallel": true,
-                                            "self": 9312.454614155993,
+                                            "self": 73007.71565440437,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.00290756300000794,
+                                                            "total": 0.004155171999968843,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0007694570003877743,
+                                                            "self": 0.0018411529999582399,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0021381059996201657,
+                                                                    "total": 0.002314019000010603,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0021381059996201657
+                                                                    "self": 0.002314019000010603
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.049522353999691404,
+                                                            "total": 0.04638103199999932,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000622523999936675,
+                                                            "self": 0.0008324190000053022,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0013176359998396947,
+                                                                    "total": 0.000863132000006317,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013176359998396947
+                                                                    "self": 0.000863132000006317
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.045636842000021716,
+                                                                    "total": 0.04250551100000166,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.045636842000021716
+                                                                    "self": 0.04250551100000166
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0019453519998933189,
+                                                                    "total": 0.0021799699999860422,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004454060008356464,
+                                                                    "self": 0.0005233989999737787,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014999459990576725,
+                                                                            "total": 0.0016565710000122635,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014999459990576725
+                                                                            "self": 0.0016565710000122635
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.04136546200470548,
-                                                    "count": 40,
+                                                    "total": 0.3322439869853895,
+                                                    "count": 300,
                                                     "is_parallel": true,
-                                                    "self": 0.008764717003941769,
+                                                    "self": 0.07504584902235933,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.03260074500076371,
-                                                            "count": 160,
+                                                            "total": 0.25719813796303015,
+                                                            "count": 1200,
                                                             "is_parallel": true,
-                                                            "self": 0.03260074500076371
+                                                            "self": 0.25719813796303015
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 4989.708075632572,
-                                                    "count": 279515,
+                                                    "total": 36310.51595551938,
+                                                    "count": 2082682,
                                                     "is_parallel": true,
-                                                    "self": 222.54898978506753,
+                                                    "self": 1637.2535055873159,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 176.63297709643302,
-                                                            "count": 279515,
+                                                            "total": 1251.8232436233416,
+                                                            "count": 2082682,
                                                             "is_parallel": true,
-                                                            "self": 176.63297709643302
+                                                            "self": 1251.8232436233416
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 3960.788864381723,
-                                                            "count": 279515,
+                                                            "total": 29081.51631062065,
+                                                            "count": 2082682,
                                                             "is_parallel": true,
-                                                            "self": 3960.788864381723
+                                                            "self": 29081.51631062065
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 629.7372443693484,
-                                                            "count": 559030,
+                                                            "total": 4339.9228956880725,
+                                                            "count": 4165364,
                                                             "is_parallel": true,
-                                                            "self": 128.39045988277303,
+                                                            "self": 926.6103741319807,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 501.3467844865754,
-                                                                    "count": 2236120,
+                                                                    "total": 3413.3125215560917,
+                                                                    "count": 16661456,
                                                                     "is_parallel": true,
-                                                                    "self": 501.3467844865754
+                                                                    "self": 3413.3125215560917
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 6901.086995254429,
-                            "count": 279516,
-                            "self": 81.25708046768159,
+                            "total": 55888.772569860084,
+                            "count": 2082683,
+                            "self": 638.9373073734241,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 1546.4408861167535,
-                                    "count": 279516,
-                                    "self": 1543.6242334457525,
+                                    "total": 10660.703185951563,
+                                    "count": 2082683,
+                                    "self": 10646.131815530573,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 2.8166526710010658,
-                                            "count": 8,
-                                            "self": 2.8166526710010658
+                                            "total": 14.571370420989979,
+                                            "count": 60,
+                                            "self": 14.571370420989979
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 5273.389028669993,
-                                    "count": 194,
-                                    "self": 727.7533321649835,
+                                    "total": 44589.1320765351,
+                                    "count": 1456,
+                                    "self": 6212.25272581703,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 4545.63569650501,
-                                            "count": 5820,
-                                            "self": 4545.63569650501
+                                            "total": 38376.87935071807,
+                                            "count": 43680,
+                                            "self": 38376.87935071807
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.819988579489291e-07,
+                    "total": 2.2040039766579866e-06,
                     "count": 1,
-                    "self": 8.819988579489291e-07
+                    "self": 2.2040039766579866e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.33271469099781825,
+                    "total": 0.1941318930039415,
                     "count": 1,
-                    "self": 0.012085155998647679,
+                    "self": 0.0017999340052483603,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.3206295349991706,
+                            "total": 0.19233195899869315,
                             "count": 1,
-                            "self": 0.3206295349991706
+                            "self": 0.19233195899869315
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 18499959,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-18499959.onnx",
+                "steps": 48499998,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48499998.onnx",
                 "reward": 0.0,
-                "creation_time": 1709796467.9607494,
+                "creation_time": 1711127187.6734087,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-18499959.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-48499998.pt"
                 ]
             },
             {
-                "steps": 18999954,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-18999954.onnx",
+                "steps": 48999968,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48999968.onnx",
                 "reward": 0.0,
-                "creation_time": 1709798335.1910672,
+                "creation_time": 1711129147.367645,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-18999954.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-48999968.pt"
                 ]
             },
             {
-                "steps": 19499975,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-19499975.onnx",
+                "steps": 49499924,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49499924.onnx",
                 "reward": 0.0,
-                "creation_time": 1709800148.8099773,
+                "creation_time": 1711131090.5125165,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-19499975.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-49499924.pt"
                 ]
             },
             {
-                "steps": 19999982,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-19999982.onnx",
+                "steps": 49999946,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49999946.onnx",
                 "reward": 0.0,
-                "creation_time": 1709801917.7176123,
+                "creation_time": 1711133044.7667835,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-19999982.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-49999946.pt"
                 ]
             },
             {
-                "steps": 20000060,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-20000060.onnx",
+                "steps": 50000232,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-50000232.onnx",
                 "reward": 0.0,
-                "creation_time": 1709801918.085361,
+                "creation_time": 1711133045.0290792,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-20000060.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-50000232.pt"
                 ]
             }
         ],
-        "elo": 1557.0544952910404,
+        "elo": 1576.864615609649,
         "final_checkpoint": {
-            "steps": 20000060,
+            "steps": 50000232,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1709801918.085361,
+            "creation_time": 1711133045.0290792,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-20000060.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-50000232.pt"
             ]
         }
     },