Update_agent

SoccerTwos/SoccerTwos-12999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f93b6669593f49c412135b23198e6d658c6c97e02c6b7b5293e313cd9b5e35b3
+size 886472

SoccerTwos/SoccerTwos-12999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda3347955b883fed4d1fa5ca1722187aec70d6589706dc8c24e66c27c984612
+size 10303217

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b11adee6bf39e673617f454e397dd59a5db227b67574367d546436c086cec006
+oid sha256:cda3347955b883fed4d1fa5ca1722187aec70d6589706dc8c24e66c27c984612
 size 10303217

SoccerTwos/events.out.tfevents.1691410109.d33d669e7b9d.1474.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513664ebb34374666706c3031df5a23358466f84fa7fc01c9d55d0ea54f777b1
+size 905454

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": 0.99, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.95, "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": 12500000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 60000, "team_change": 225000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.25, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cpu"}, "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": 0.99, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.95, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 15000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 60000, "team_change": 225000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.25, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cpu"}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 12500000
+    max_steps: 15000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -2,6 +2,9 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/SoccerTwos_Data/Man
 Mono config path = '/content/ml-agents/training-envs-executables/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_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -31,7 +34,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.136 seconds
+- Completed reload, in  0.093 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -56,7 +59,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 1.028111 ms
+UnloadTime: 0.662542 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
@@ -65,7 +68,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 20725 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 16672 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
@@ -93,7 +96,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.7 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -187,16 +190,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 20726 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 16673 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.9 MB
+      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]: 20726 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 16673 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.4 MB
+      Peak Allocated memory 17.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -225,13 +228,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 20725 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 16672 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]: 20726 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 16673 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -243,16 +246,16 @@ 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]: 20726 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 16673 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]: 20725 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 16672 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.1 MB
+      Peak Allocated memory 4.3 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -261,13 +264,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 20726 frames
+      Peak usage frame count: [0-1.0 KB]: 16673 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]: 20725 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 16672 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": 2.1975553035736084,
-            "min": 2.0373876094818115,
-            "max": 2.252624750137329,
-            "count": 111
+            "value": 2.0170538425445557,
+            "min": 1.9972507953643799,
+            "max": 2.2256991863250732,
+            "count": 88
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 43388.53125,
-            "min": 11539.763671875,
-            "max": 48319.01953125,
-            "count": 111
+            "value": 40405.62109375,
+            "min": 37537.67578125,
+            "max": 46557.78515625,
+            "count": 88
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 47.13592233009709,
-            "min": 37.827586206896555,
-            "max": 59.72839506172839,
-            "count": 111
+            "value": 42.0,
+            "min": 39.12,
+            "max": 68.18055555555556,
+            "count": 88
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19420.0,
-            "min": 4388.0,
-            "max": 20112.0,
-            "count": 111
+            "value": 19320.0,
+            "min": 18824.0,
+            "max": 20548.0,
+            "count": 88
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1504.6784948269735,
-            "min": 1478.8434240860017,
-            "max": 1547.558003128173,
-            "count": 111
+            "value": 1498.7779997425816,
+            "min": 1471.804093027367,
+            "max": 1513.380500435241,
+            "count": 88
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 309963.76993435656,
-            "min": 87170.94541634181,
-            "max": 381647.0484520141,
-            "count": 111
+            "value": 344718.9399407938,
+            "min": 213823.54250999942,
+            "max": 371550.6815187331,
+            "count": 88
         },
         "SoccerTwos.Step.mean": {
-            "value": 12499998.0,
-            "min": 11399968.0,
-            "max": 12499998.0,
-            "count": 111
+            "value": 13379974.0,
+            "min": 12509994.0,
+            "max": 13379974.0,
+            "count": 88
         },
         "SoccerTwos.Step.sum": {
-            "value": 12499998.0,
-            "min": 11399968.0,
-            "max": 12499998.0,
-            "count": 111
+            "value": 13379974.0,
+            "min": 12509994.0,
+            "max": 13379974.0,
+            "count": 88
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.034507688134908676,
-            "min": -0.09850272536277771,
-            "max": 0.10206205397844315,
-            "count": 111
+            "value": 0.02328161522746086,
+            "min": -0.07533109933137894,
+            "max": 0.06940919160842896,
+            "count": 88
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -7.143091201782227,
-            "min": -20.685571670532227,
-            "max": 19.595914840698242,
-            "count": 111
+            "value": 5.401334762573242,
+            "min": -15.442874908447266,
+            "max": 14.36770248413086,
+            "count": 88
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.042147111147642136,
-            "min": -0.09934258460998535,
-            "max": 0.09995047003030777,
-            "count": 111
+            "value": 0.023491045460104942,
+            "min": -0.07633703947067261,
+            "max": 0.07690165936946869,
+            "count": 88
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -8.724452018737793,
-            "min": -20.861942291259766,
-            "max": 19.19049072265625,
-            "count": 111
+            "value": 5.449922561645508,
+            "min": -15.649093627929688,
+            "max": 15.9186429977417,
+            "count": 88
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 111
+            "count": 88
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 111
+            "count": 88
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.1782685987615355,
-            "min": -0.28665177834215505,
-            "max": 0.25223191336114353,
-            "count": 111
+            "value": 0.028268965667691725,
+            "min": -0.37212292857286405,
+            "max": 0.1393845412466261,
+            "count": 88
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -36.90159994363785,
-            "min": -59.35199987888336,
-            "max": 47.41959971189499,
-            "count": 111
+            "value": 6.55840003490448,
+            "min": -76.28520035743713,
+            "max": 28.852600038051605,
+            "count": 88
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.1782685987615355,
-            "min": -0.28665177834215505,
-            "max": 0.25223191336114353,
-            "count": 111
+            "value": 0.028268965667691725,
+            "min": -0.37212292857286405,
+            "max": 0.1393845412466261,
+            "count": 88
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -36.90159994363785,
-            "min": -59.35199987888336,
-            "max": 47.41959971189499,
-            "count": 111
+            "value": 6.55840003490448,
+            "min": -76.28520035743713,
+            "max": 28.852600038051605,
+            "count": 88
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 111
+            "count": 88
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 111
+            "count": 88
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.016760872232650097,
-            "min": 0.012540093262214214,
-            "max": 0.021946661923235904,
-            "count": 53
+            "value": 0.01801625022975107,
+            "min": 0.011879822385465862,
+            "max": 0.02180827030679211,
+            "count": 42
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.016760872232650097,
-            "min": 0.012540093262214214,
-            "max": 0.021946661923235904,
-            "count": 53
+            "value": 0.01801625022975107,
+            "min": 0.011879822385465862,
+            "max": 0.02180827030679211,
+            "count": 42
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.08545334686835607,
-            "min": 0.07352821032206218,
-            "max": 0.08939586058259011,
-            "count": 53
+            "value": 0.08463414534926414,
+            "min": 0.07863207459449768,
+            "max": 0.09561808233459791,
+            "count": 42
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.08545334686835607,
-            "min": 0.07352821032206218,
-            "max": 0.08939586058259011,
-            "count": 53
+            "value": 0.08463414534926414,
+            "min": 0.07863207459449768,
+            "max": 0.09561808233459791,
+            "count": 42
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.08727932895223299,
-            "min": 0.07501178334156672,
-            "max": 0.09038200850288074,
-            "count": 53
+            "value": 0.08579889833927154,
+            "min": 0.07998814011613528,
+            "max": 0.0967168872555097,
+            "count": 42
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.08727932895223299,
-            "min": 0.07501178334156672,
-            "max": 0.09038200850288074,
-            "count": 53
+            "value": 0.08579889833927154,
+            "min": 0.07998814011613528,
+            "max": 0.0967168872555097,
+            "count": 42
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 53
+            "count": 42
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 53
+            "count": 42
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 53
+            "count": 42
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 53
+            "count": 42
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 53
+            "count": 42
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 53
+            "count": 42
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1691333799",
+        "start_time_seconds": "1691410106",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cpu",
         "mlagents_version": "0.31.0.dev0",
@@ -204,59 +204,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1691337965"
+        "end_time_seconds": "1691413365"
     },
-    "total": 4166.746141003998,
+    "total": 3259.086342517,
     "count": 1,
-    "self": 0.5836922629987384,
+    "self": 0.7392523739999888,
     "children": {
         "run_training.setup": {
-            "total": 0.07324457199865719,
+            "total": 0.0587807919999932,
             "count": 1,
-            "self": 0.07324457199865719
+            "self": 0.0587807919999932
         },
         "TrainerController.start_learning": {
-            "total": 4166.089204169,
+            "total": 3258.288309351,
             "count": 1,
-            "self": 3.1761226611160964,
+            "self": 1.7680477739754679,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.028336847997707,
-                    "count": 6,
-                    "self": 2.028336847997707
+                    "total": 2.445354537000469,
+                    "count": 5,
+                    "self": 2.445354537000469
                 },
                 "TrainerController.advance": {
-                    "total": 4160.680842743883,
-                    "count": 77894,
-                    "self": 3.1256917527553014,
+                    "total": 3254.074117151024,
+                    "count": 62738,
+                    "self": 1.533715553028287,
                     "children": {
                         "env_step": {
-                            "total": 2317.5797028738634,
-                            "count": 77894,
-                            "self": 1979.8674866570218,
+                            "total": 1273.310644220974,
+                            "count": 62738,
+                            "self": 1062.8171075409816,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 335.9226087098323,
-                                    "count": 77894,
-                                    "self": 15.090959516541261,
+                                    "total": 209.46814199198388,
+                                    "count": 62738,
+                                    "self": 7.206732080007555,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 320.831649193291,
-                                            "count": 138170,
-                                            "self": 320.831649193291
+                                            "total": 202.26140991197633,
+                                            "count": 111152,
+                                            "self": 202.26140991197633
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.7896075070093502,
-                                    "count": 77894,
+                                    "total": 1.0253946880084754,
+                                    "count": 62737,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 4150.210422646147,
-                                            "count": 77894,
+                                            "total": 3254.072856265011,
+                                            "count": 62737,
                                             "is_parallel": true,
-                                            "self": 2503.58676581701,
+                                            "self": 2366.7271369250225,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005130403000293882,
+                                                            "total": 0.00983552799999643,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0010273069983668393,
+                                                            "self": 0.00724677799996698,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.004103096001927042,
+                                                                    "total": 0.0025887500000294494,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.004103096001927042
+                                                                    "self": 0.0025887500000294494
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.10228872500010766,
+                                                            "total": 0.04980938699998205,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0013711459996557096,
+                                                            "self": 0.0012535100000832244,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0009328020005341386,
+                                                                    "total": 0.0007586599999740429,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0009328020005341386
+                                                                    "self": 0.0007586599999740429
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.09588967299896467,
+                                                                    "total": 0.044380516999979136,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.09588967299896467
+                                                                    "self": 0.044380516999979136
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0040951040009531425,
+                                                                    "total": 0.0034166999999456493,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006900650005263742,
+                                                                    "self": 0.000673259999871334,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0034050390004267683,
+                                                                            "total": 0.0027434400000743153,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0034050390004267683
+                                                                            "self": 0.0027434400000743153
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.01923490499939362,
-                                                    "count": 10,
+                                                    "total": 0.008660468999892146,
+                                                    "count": 8,
                                                     "is_parallel": true,
-                                                    "self": 0.003280105995145277,
+                                                    "self": 0.0016107209999631777,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.015954799004248343,
-                                                            "count": 40,
+                                                            "total": 0.007049747999928968,
+                                                            "count": 32,
                                                             "is_parallel": true,
-                                                            "self": 0.015954799004248343
+                                                            "self": 0.007049747999928968
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1646.6044219241376,
-                                                    "count": 77893,
+                                                    "total": 887.3370588709888,
+                                                    "count": 62736,
                                                     "is_parallel": true,
-                                                    "self": 99.4243430186234,
+                                                    "self": 55.339384674010375,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 51.82752819974303,
-                                                            "count": 77893,
+                                                            "total": 27.926248527957114,
+                                                            "count": 62736,
                                                             "is_parallel": true,
-                                                            "self": 51.82752819974303
+                                                            "self": 27.926248527957114
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1174.5112396781096,
-                                                            "count": 77893,
+                                                            "total": 637.3668925890175,
+                                                            "count": 62736,
                                                             "is_parallel": true,
-                                                            "self": 1174.5112396781096
+                                                            "self": 637.3668925890175
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 320.8413110276615,
-                                                            "count": 155786,
+                                                            "total": 166.70453308000378,
+                                                            "count": 125472,
                                                             "is_parallel": true,
-                                                            "self": 56.20767449019331,
+                                                            "self": 30.377168298046172,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 264.6336365374682,
-                                                                    "count": 623144,
+                                                                    "total": 136.3273647819576,
+                                                                    "count": 501888,
                                                                     "is_parallel": true,
-                                                                    "self": 264.6336365374682
+                                                                    "self": 136.3273647819576
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1839.975448117264,
-                            "count": 77894,
-                            "self": 20.360098037423086,
+                            "total": 1979.2297573770218,
+                            "count": 62737,
+                            "self": 12.382054871022092,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 385.70859332684813,
-                                    "count": 77894,
-                                    "self": 385.09017827284515,
+                                    "total": 311.74384310800116,
+                                    "count": 62737,
+                                    "self": 311.2617028940011,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.6184150540029805,
-                                            "count": 3,
-                                            "self": 0.6184150540029805
+                                            "total": 0.4821402140000828,
+                                            "count": 1,
+                                            "self": 0.4821402140000828
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1433.9067567529928,
-                                    "count": 53,
-                                    "self": 273.3484064769691,
+                                    "total": 1655.1038593979986,
+                                    "count": 43,
+                                    "self": 144.60367413699691,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 1160.5583502760237,
-                                            "count": 1590,
-                                            "self": 1160.5583502760237
+                                            "total": 1510.5001852610017,
+                                            "count": 1290,
+                                            "self": 1510.5001852610017
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0690018825698644e-06,
+                    "total": 1.0690000635804608e-06,
                     "count": 1,
-                    "self": 1.0690018825698644e-06
+                    "self": 1.0690000635804608e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.20390084700193256,
+                    "total": 0.0007888199997978518,
                     "count": 1,
-                    "self": 0.002047485002549365,
+                    "self": 3.7939999856462236e-05,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.2018533619993832,
+                            "total": 0.0007508799999413895,
                             "count": 1,
-                            "self": 0.2018533619993832
+                            "self": 0.0007508799999413895
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,15 +1,6 @@
 {
     "SoccerTwos": {
         "checkpoints": [
-            {
-                "steps": 11397816,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-11397816.onnx",
-                "reward": null,
-                "creation_time": 1691333783.8306155,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-11397816.pt"
-                ]
-            },
             {
                 "steps": 11499962,
                 "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-11499962.onnx",
@@ -45,9 +36,18 @@
                 "auxillary_file_paths": [
                     "results/SoccerTwos/SoccerTwos/SoccerTwos-12500022.pt"
                 ]
+            },
+            {
+                "steps": 12999992,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-12999992.onnx",
+                "reward": 0.0,
+                "creation_time": 1691411948.116917,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-12999992.pt"
+                ]
             }
         ],
-        "elo": 1501.2307928593602,
+        "elo": 1501.5317486329445,
         "final_checkpoint": {
             "steps": 12500022,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",