update: second push

SoccerTwos/events.out.tfevents.1680454290.Pouti-Pouti.11220.0 → SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6ac2bd53f806edbbd3ad281252579a4b088099ce5ed4394b9594be8f7675b3
-size 360002
+oid sha256:223f39bc664b25b9402c4d4ea3d8cd77c98e7d323963f478a3bc4df57463383e
+size 1768746

SoccerTwos/{SoccerTwos-499298.pt → SoccerTwos-1499972.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be1d8ccc20212f69750464bbd12737583a51c7729fee7c025d0f3a266e2466e6
-size 28429781
+oid sha256:1d2334bd8b55d1dad7f39a6b4cd37bf721f16801f928afc564ec521467231d14
+size 1768746

SoccerTwos/SoccerTwos-1499972.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911e5a845fee72b285abd371e6d8e1972cd1b318c834b9fc10279f08a5b9d415
+size 28429903

SoccerTwos/SoccerTwos-1999872.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67304d4f793354c0f7c999dd715fb1115b351547148965958923b616dc97835e
+size 1768746

SoccerTwos/SoccerTwos-1999872.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c8c71f7babca08e1cc885bb97c9c9397f535044fdaf6ca45f46879864ca21ba
+size 28429903

SoccerTwos/SoccerTwos-2005444.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223f39bc664b25b9402c4d4ea3d8cd77c98e7d323963f478a3bc4df57463383e
+size 1768746

SoccerTwos/SoccerTwos-2005444.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a30cd69fa38e03b8e85a7acd844d599a430cb93d8b1311e1c547465456ec7a3
+size 28429903

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8d358e50668fa0d51bfa9b0e42d33c129e73751b49d06dd463cca0c60476f0
+oid sha256:a4c52531f4fac073e6c7a4f9ba692f6983bc64e728aa42afa91cc4123fd535bf
 size 28428927

SoccerTwos/events.out.tfevents.1680456577.Pouti-Pouti.3324.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca0a8a98766fba3195aa649f179612957410fd2b12cb2bb260fad89a32f5b0d
+size 1924201

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": 3, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"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": 3, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos-1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -69,7 +69,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SoccerTwos
+  run_id: SoccerTwos-1
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -9,7 +9,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.128 seconds
+- Completed reload, in  0.131 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -35,7 +35,7 @@ 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: 0.837800 ms
+UnloadTime: 0.755000 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 TOO LONG
@@ -239,12 +239,38 @@ TOO LONG
 TOO LONG
 TOO LONG
 TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
 Setting up 6 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 9801 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 38141 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -272,7 +298,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -392,7 +418,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 10]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 54 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
@@ -410,22 +436,22 @@ Memory Statistics:
       Peak Allocated Bytes 54 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 2
+  Peak main deferred allocation count 3
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 9802 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 38142 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.0 MB
+      Peak Allocated memory 5.2 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9802 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 38142 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.4 MB
+      Peak Allocated memory 17.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -454,13 +480,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 9801 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 38141 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]: 9802 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 38142 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.6 KB
@@ -472,13 +498,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 9802 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 38142 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]: 9801 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 38141 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -490,13 +516,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9802 frames
+      Peak usage frame count: [0-1.0 KB]: 38142 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]: 9801 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 38141 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

@@ -2,305 +2,305 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 3.2145214080810547,
-            "min": 3.1970012187957764,
-            "max": 3.295757532119751,
-            "count": 49
+            "value": 2.4587490558624268,
+            "min": 2.4587490558624268,
+            "max": 3.2955703735351562,
+            "count": 200
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 42380.25,
-            "min": 24957.275390625,
-            "max": 109557.1796875,
-            "count": 49
+            "value": 51299.33984375,
+            "min": 19900.1484375,
+            "max": 126558.3125,
+            "count": 200
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 766.1428571428571,
-            "min": 437.3636363636364,
+            "value": 49.56,
+            "min": 44.5045045045045,
             "max": 999.0,
-            "count": 49
+            "count": 200
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 21452.0,
-            "min": 9112.0,
-            "max": 31584.0,
-            "count": 49
+            "value": 19824.0,
+            "min": 16572.0,
+            "max": 24560.0,
+            "count": 200
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1201.4370622202903,
-            "min": 1196.1127207229522,
-            "max": 1204.995993621269,
-            "count": 45
+            "value": 1420.799245535332,
+            "min": 1202.0873838193381,
+            "max": 1443.5014426511523,
+            "count": 198
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 4805.748248881161,
-            "min": 2396.2191409978036,
-            "max": 14406.32282709728,
-            "count": 45
+            "value": 284159.8491070664,
+            "min": 2404.1747676386763,
+            "max": 316867.58937857405,
+            "count": 198
         },
         "SoccerTwos.Step.mean": {
-            "value": 499298.0,
-            "min": 9196.0,
-            "max": 499298.0,
-            "count": 50
+            "value": 1999872.0,
+            "min": 9300.0,
+            "max": 1999872.0,
+            "count": 200
         },
         "SoccerTwos.Step.sum": {
-            "value": 499298.0,
-            "min": 9196.0,
-            "max": 499298.0,
-            "count": 50
+            "value": 1999872.0,
+            "min": 9300.0,
+            "max": 1999872.0,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.02189152128994465,
-            "min": -0.02189152128994465,
-            "max": 0.02519119344651699,
-            "count": 50
+            "value": -0.09114526957273483,
+            "min": -0.09893187880516052,
+            "max": 0.17886286973953247,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -0.2845897674560547,
-            "min": -0.3264758288860321,
-            "max": 0.3273664712905884,
-            "count": 50
+            "value": -18.229053497314453,
+            "min": -18.229053497314453,
+            "max": 26.296974182128906,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.023025278002023697,
-            "min": -0.023025278002023697,
-            "max": 0.02517625316977501,
-            "count": 50
+            "value": -0.09215054661035538,
+            "min": -0.09215054661035538,
+            "max": 0.17882710695266724,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -0.29932862520217896,
-            "min": -0.3107862174510956,
-            "max": 0.3628310561180115,
-            "count": 50
+            "value": -18.43010902404785,
+            "min": -18.43010902404785,
+            "max": 26.81424903869629,
+            "count": 200
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 50
+            "count": 200
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 50
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.00449231037726769,
-            "min": -0.5384615384615384,
-            "max": 0.2093230735224027,
-            "count": 50
+            "value": -0.06616399943828583,
+            "min": -0.5683428570628166,
+            "max": 0.48688000440597534,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -0.05840003490447998,
-            "min": -7.0,
-            "max": 2.721199955791235,
-            "count": 50
+            "value": -13.232799887657166,
+            "min": -51.6116002202034,
+            "max": 49.42099976539612,
+            "count": 200
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.00449231037726769,
-            "min": -0.5384615384615384,
-            "max": 0.2093230735224027,
-            "count": 50
+            "value": -0.06616399943828583,
+            "min": -0.5683428570628166,
+            "max": 0.48688000440597534,
+            "count": 200
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -0.05840003490447998,
-            "min": -7.0,
-            "max": 2.721199955791235,
-            "count": 50
+            "value": -13.232799887657166,
+            "min": -51.6116002202034,
+            "max": 49.42099976539612,
+            "count": 200
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 50
+            "count": 200
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 50
+            "count": 200
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.016243750545739507,
-            "min": 0.010632850139518268,
-            "max": 0.021078815214180698,
-            "count": 22
+            "value": 0.018388708156029072,
+            "min": 0.01115456733678002,
+            "max": 0.02551558626194795,
+            "count": 95
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.016243750545739507,
-            "min": 0.010632850139518268,
-            "max": 0.021078815214180698,
-            "count": 22
+            "value": 0.018388708156029072,
+            "min": 0.01115456733678002,
+            "max": 0.02551558626194795,
+            "count": 95
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.003202572336886078,
-            "min": 0.00038679564992586773,
-            "max": 0.005716715706512332,
-            "count": 22
+            "value": 0.0900604156156381,
+            "min": 5.6578859584988095e-05,
+            "max": 0.10245133017500242,
+            "count": 95
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.003202572336886078,
-            "min": 0.00038679564992586773,
-            "max": 0.005716715706512332,
-            "count": 22
+            "value": 0.0900604156156381,
+            "min": 5.6578859584988095e-05,
+            "max": 0.10245133017500242,
+            "count": 95
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.0032397882547229528,
-            "min": 0.0003874195773581353,
-            "max": 0.005753304110839963,
-            "count": 22
+            "value": 0.09202444056669871,
+            "min": 5.740506312577054e-05,
+            "max": 0.10415451750159263,
+            "count": 95
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.0032397882547229528,
-            "min": 0.0003874195773581353,
-            "max": 0.005753304110839963,
-            "count": 22
+            "value": 0.09202444056669871,
+            "min": 5.740506312577054e-05,
+            "max": 0.10415451750159263,
+            "count": 95
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 22
+            "count": 95
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 22
+            "count": 95
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
-            "min": 0.19999999999999993,
+            "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 22
+            "count": 95
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
-            "min": 0.19999999999999993,
+            "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 22
+            "count": 95
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
-            "min": 0.005,
+            "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 22
+            "count": 95
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
-            "min": 0.005,
+            "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 22
+            "count": 95
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1680454285",
+        "start_time_seconds": "1680456573",
         "python_version": "3.9.16 (main, Mar  8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]",
-        "command_line_arguments": "C:\\Users\\rbass\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
+        "command_line_arguments": "C:\\Users\\rbass\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos-1 --no-graphics",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.0.0+cpu",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1680456370"
+        "end_time_seconds": "1680466836"
     },
-    "total": 2084.2229049,
+    "total": 10260.995134499999,
     "count": 1,
-    "self": 0.3876915000000736,
+    "self": 0.011409799997636583,
     "children": {
         "run_training.setup": {
-            "total": 0.13345050000000036,
+            "total": 0.11660950000000003,
             "count": 1,
-            "self": 0.13345050000000036
+            "self": 0.11660950000000003
         },
         "TrainerController.start_learning": {
-            "total": 2083.7017628999997,
+            "total": 10260.8671152,
             "count": 1,
-            "self": 0.9942415999807963,
+            "self": 4.240169000251626,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.505686199999925,
-                    "count": 3,
-                    "self": 4.505686199999925
+                    "total": 4.682091400000161,
+                    "count": 11,
+                    "self": 4.682091400000161
                 },
                 "TrainerController.advance": {
-                    "total": 2078.0462259000187,
-                    "count": 32913,
-                    "self": 0.9323881000204892,
+                    "total": 10251.770931799749,
+                    "count": 135303,
+                    "self": 4.521766099771412,
                     "children": {
                         "env_step": {
-                            "total": 753.8917008999985,
-                            "count": 32913,
-                            "self": 579.6705003999763,
+                            "total": 3271.345131000132,
+                            "count": 135303,
+                            "self": 2514.6715345999537,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 173.55510090001474,
-                                    "count": 32913,
-                                    "self": 5.641603699978447,
+                                    "total": 753.7358583002034,
+                                    "count": 135303,
+                                    "self": 26.92504450029594,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 167.9134972000363,
-                                            "count": 65342,
-                                            "self": 167.9134972000363
+                                            "total": 726.8108137999075,
+                                            "count": 254280,
+                                            "self": 726.8108137999075
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.6660996000074544,
-                                    "count": 32913,
+                                    "total": 2.9377380999748244,
+                                    "count": 135303,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2077.5069623999775,
-                                            "count": 32913,
+                                            "total": 10224.751616000043,
+                                            "count": 135303,
                                             "is_parallel": true,
-                                            "self": 1619.7835751999683,
+                                            "self": 8236.737314099955,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.011470499999833628,
-                                                    "count": 6,
+                                                    "total": 0.02831179999729727,
+                                                    "count": 22,
                                                     "is_parallel": true,
-                                                    "self": 0.002861200000391584,
+                                                    "self": 0.005608299988335119,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.008609299999442044,
-                                                            "count": 24,
+                                                            "total": 0.022703500008962152,
+                                                            "count": 88,
                                                             "is_parallel": true,
-                                                            "self": 0.008609299999442044
+                                                            "self": 0.022703500008962152
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 457.71191670000934,
-                                                    "count": 32913,
+                                                    "total": 1987.9859901000912,
+                                                    "count": 135303,
                                                     "is_parallel": true,
-                                                    "self": 23.642432399957897,
+                                                    "self": 108.04710420038919,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 21.748385499992864,
-                                                            "count": 32913,
+                                                            "total": 94.99340020020244,
+                                                            "count": 135303,
                                                             "is_parallel": true,
-                                                            "self": 21.748385499992864
+                                                            "self": 94.99340020020244
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 338.05674560003393,
-                                                            "count": 32913,
+                                                            "total": 1447.0073781996425,
+                                                            "count": 135303,
                                                             "is_parallel": true,
-                                                            "self": 338.05674560003393
+                                                            "self": 1447.0073781996425
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 74.26435320002463,
-                                                            "count": 65826,
+                                                            "total": 337.93810749985715,
+                                                            "count": 270606,
                                                             "is_parallel": true,
-                                                            "self": 14.761290999960266,
+                                                            "self": 68.86850160019975,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 59.50306220006436,
-                                                                    "count": 263304,
+                                                                    "total": 269.0696058996574,
+                                                                    "count": 1082424,
                                                                     "is_parallel": true,
-                                                                    "self": 59.50306220006436
+                                                                    "self": 269.0696058996574
                                                                 }
                                                             }
                                                         }
@@ -313,31 +313,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1323.2221368999997,
-                            "count": 32913,
-                            "self": 6.794951299985996,
+                            "total": 6975.904034699846,
+                            "count": 135303,
+                            "self": 31.88413280000077,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 171.32710230001373,
-                                    "count": 32913,
-                                    "self": 170.8665625000134,
+                                    "total": 1001.472424199842,
+                                    "count": 135303,
+                                    "self": 1000.5807250998428,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.46053980000033334,
-                                            "count": 1,
-                                            "self": 0.46053980000033334
+                                            "total": 0.8916990999991867,
+                                            "count": 4,
+                                            "self": 0.8916990999991867
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1145.1000833,
-                                    "count": 22,
-                                    "self": 103.37883499999998,
+                                    "total": 5942.547477700004,
+                                    "count": 96,
+                                    "self": 456.4403053000142,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 1041.7212483,
-                                            "count": 678,
-                                            "self": 1041.7212483
+                                            "total": 5486.107172399989,
+                                            "count": 2864,
+                                            "self": 5486.107172399989
                                         }
                                     }
                                 }
@@ -345,15 +345,20 @@
                         }
                     }
                 },
+                "trainer_threads": {
+                    "total": 1.7000002117129043e-06,
+                    "count": 1,
+                    "self": 1.7000002117129043e-06
+                },
                 "TrainerController._save_models": {
-                    "total": 0.15560920000007172,
+                    "total": 0.17392130000007455,
                     "count": 1,
-                    "self": 4.03999997615756e-05,
+                    "self": 0.010430099999211961,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.15556880000031015,
+                            "total": 0.1634912000008626,
                             "count": 1,
-                            "self": 0.15556880000031015
+                            "self": 0.1634912000008626
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,6 +1,44 @@
 {
     "SoccerTwos": {
-        "elo": 1200.797829965766
+        "checkpoints": [
+            {
+                "steps": 1499972,
+                "file_path": "results\\SoccerTwos-1\\SoccerTwos\\SoccerTwos-1499972.onnx",
+                "reward": 0.0,
+                "creation_time": 1680464326.0622303,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos-1\\SoccerTwos\\SoccerTwos-1499972.pt"
+                ]
+            },
+            {
+                "steps": 1999872,
+                "file_path": "results\\SoccerTwos-1\\SoccerTwos\\SoccerTwos-1999872.onnx",
+                "reward": 0.0,
+                "creation_time": 1680466800.390422,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos-1\\SoccerTwos\\SoccerTwos-1999872.pt"
+                ]
+            },
+            {
+                "steps": 2005444,
+                "file_path": "results\\SoccerTwos-1\\SoccerTwos\\SoccerTwos-2005444.onnx",
+                "reward": null,
+                "creation_time": 1680466836.2969263,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos-1\\SoccerTwos\\SoccerTwos-2005444.pt"
+                ]
+            }
+        ],
+        "elo": 1418.3841796544066,
+        "final_checkpoint": {
+            "steps": 2005444,
+            "file_path": "results\\SoccerTwos-1\\SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1680466836.2969263,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos-1\\SoccerTwos\\SoccerTwos-2005444.pt"
+            ]
+        }
     },
     "metadata": {
         "stats_format_version": "0.3.0",