Update model

SoccerTwos/SoccerTwos-130712.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc46e7c3a8ae976987e0d8263aea774c2d1ba3e7a92552de55cc4ca70b15efb3
+size 646709386

SoccerTwos/SoccerTwos-14160.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d41435150bf8066294d97f42bdbcc4daaac71c9f472c02ee463ce20a8f81e9a
+size 215565130

SoccerTwos/SoccerTwos-470490.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0e840234d497bfa7e8d15f51e624526c42d36b28a548b110a16a04aa67090b
+size 1768747

SoccerTwos/SoccerTwos-470490.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f763411ef7db6202a6b94fdf8070499d7e2d87a7b42649d254e574c957010553
+size 28431898

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3d6f8efb9422465ad2b4af990732935d6abe98d4231c252f04fe48c52940ad5
-size 28431030
+oid sha256:1e47db37c9c05736730ca607b9cc6fd6da24c20f38eca97b7bfd2e35fb0b199f
+size 646697542

SoccerTwos/events.out.tfevents.1703591227.cybertron.29738.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063d8ad9f924e7e5d433747d4ddf8906d5a9323d010354a3a977613d499ee81a
+size 113286

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 9048, "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}, "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": 4096, "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": 100, "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": 40000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 100, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,7 +3,7 @@ behaviors:
   SoccerTwos:
     trainer_type: poca
     hyperparameters:
-      batch_size: 9048
+      batch_size: 4096
       buffer_size: 20480
       learning_rate: 0.0003
       beta: 0.005
@@ -17,14 +17,14 @@ behaviors:
     network_settings:
       normalize: false
       hidden_units: 512
-      num_layers: 2
+      num_layers: 100
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
       deterministic: false
     reward_signals:
       extrinsic:
-        gamma: 0.99
+        gamma: 0.95
         strength: 1.0
         network_settings:
           normalize: false
@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 50000000
+    max_steps: 40000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false
@@ -45,7 +45,7 @@ behaviors:
       save_steps: 50000
       team_change: 200000
       swap_steps: 2000
-      window: 10
+      window: 100
       play_against_latest_model_ratio: 0.5
       initial_elo: 1200.0
     behavioral_cloning: null
@@ -73,8 +73,8 @@ checkpoint_settings:
   run_id: SoccerTwos
   initialize_from: null
   load_model: false
-  resume: true
-  force: false
+  resume: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -11,7 +11,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.072 seconds
+- Completed reload, in  0.059 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: 0.448741 ms
+UnloadTime: 1.112902 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
@@ -45,12 +45,51 @@ 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
+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]: 436 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 2555 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
@@ -158,7 +197,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 9]
       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 13]
       Initial Block Size 32.0 KB
@@ -173,7 +212,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 7]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.7 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 1]
       Initial Block Size 256.0 KB
@@ -216,19 +255,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 4
+  Peak main deferred allocation count 2
     [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]: 437 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 2556 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 437 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 2556 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.5 MB
@@ -260,13 +299,13 @@ 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]: 436 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 2555 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]: 437 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 2556 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -278,13 +317,13 @@ 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]: 437 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 2556 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]: 436 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 2555 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
@@ -296,13 +335,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 437 frames
+      Peak usage frame count: [0-1.0 KB]: 2556 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]: 436 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 2555 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

@@ -2,189 +2,261 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 3.237346649169922,
-            "min": 3.237346649169922,
-            "max": 3.237346649169922,
-            "count": 1
+            "value": 3.2872161865234375,
+            "min": 3.283947467803955,
+            "max": 3.2958364486694336,
+            "count": 13
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 103595.09375,
-            "min": 103595.09375,
-            "max": 103595.09375,
-            "count": 1
+            "value": 43759.421875,
+            "min": 42781.015625,
+            "max": 105466.765625,
+            "count": 13
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 673.2,
-            "min": 673.2,
-            "max": 673.2,
-            "count": 1
+            "value": 811.5,
+            "min": 494.7142857142857,
+            "max": 906.6,
+            "count": 13
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 26928.0,
-            "min": 26928.0,
-            "max": 26928.0,
-            "count": 1
+            "value": 19476.0,
+            "min": 13852.0,
+            "max": 27716.0,
+            "count": 13
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1207.6368942738368,
-            "min": 1207.6368942738368,
-            "max": 1207.6368942738368,
-            "count": 1
+            "value": 1202.1297790220663,
+            "min": 1198.6916415169974,
+            "max": 1202.9673173073832,
+            "count": 13
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 12076.368942738369,
-            "min": 12076.368942738369,
-            "max": 12076.368942738369,
-            "count": 1
+            "value": 7212.778674132397,
+            "min": 4798.067989990133,
+            "max": 14399.635556919653,
+            "count": 13
         },
         "SoccerTwos.Step.mean": {
-            "value": 209569.0,
-            "min": 209569.0,
-            "max": 209569.0,
-            "count": 1
+            "value": 129712.0,
+            "min": 9876.0,
+            "max": 129712.0,
+            "count": 13
         },
         "SoccerTwos.Step.sum": {
-            "value": 209569.0,
-            "min": 209569.0,
-            "max": 209569.0,
-            "count": 1
+            "value": 129712.0,
+            "min": 9876.0,
+            "max": 129712.0,
+            "count": 13
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.016558969393372536,
-            "min": 0.016558969393372536,
-            "max": 0.016558969393372536,
-            "count": 1
+            "value": -0.0014713257551193237,
+            "min": -0.0014713257551193237,
+            "max": 0.05451347306370735,
+            "count": 13
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 0.21526660025119781,
-            "min": 0.21526660025119781,
-            "max": 0.21526660025119781,
-            "count": 1
+            "value": -0.017655909061431885,
+            "min": -0.017655909061431885,
+            "max": 0.8722155690193176,
+            "count": 13
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.0151954535394907,
-            "min": 0.0151954535394907,
-            "max": 0.0151954535394907,
-            "count": 1
+            "value": -0.0014713257551193237,
+            "min": -0.0014713257551193237,
+            "max": 0.05451347306370735,
+            "count": 13
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 0.19754089415073395,
-            "min": 0.19754089415073395,
-            "max": 0.19754089415073395,
-            "count": 1
+            "value": -0.017655909061431885,
+            "min": -0.017655909061431885,
+            "max": 0.8722155690193176,
+            "count": 13
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 1
+            "count": 13
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 1
+            "count": 13
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.28603077164063084,
-            "min": -0.28603077164063084,
-            "max": -0.28603077164063084,
-            "count": 1
+            "value": -0.5,
+            "min": -0.5,
+            "max": 0.2147230735191932,
+            "count": 13
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -3.7184000313282013,
-            "min": -3.7184000313282013,
-            "max": -3.7184000313282013,
-            "count": 1
+            "value": -6.0,
+            "min": -6.0,
+            "max": 2.7913999557495117,
+            "count": 13
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.28603077164063084,
-            "min": -0.28603077164063084,
-            "max": -0.28603077164063084,
-            "count": 1
+            "value": -0.5,
+            "min": -0.5,
+            "max": 0.2147230735191932,
+            "count": 13
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -3.7184000313282013,
-            "min": -3.7184000313282013,
-            "max": -3.7184000313282013,
-            "count": 1
+            "value": -6.0,
+            "min": -6.0,
+            "max": 2.7913999557495117,
+            "count": 13
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 1
+            "count": 13
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 1
+            "count": 13
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.012890987443582465,
+            "min": 0.00523900882108137,
+            "max": 0.013176202323908608,
+            "count": 5
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.012890987443582465,
+            "min": 0.00523900882108137,
+            "max": 0.013176202323908608,
+            "count": 5
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.001682706782594323,
+            "min": 0.0012276781412462394,
+            "max": 0.003556596456716458,
+            "count": 5
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.001682706782594323,
+            "min": 0.0012276781412462394,
+            "max": 0.003556596456716458,
+            "count": 5
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.001682706782594323,
+            "min": 0.0012276781412462394,
+            "max": 0.003556596456716458,
+            "count": 5
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.001682706782594323,
+            "min": 0.0012276781412462394,
+            "max": 0.003556596456716458,
+            "count": 5
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 5
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 5
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 5
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 5
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005,
+            "min": 0.005,
+            "max": 0.005,
+            "count": 5
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005,
+            "min": 0.005,
+            "max": 0.005,
+            "count": 5
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1703589972",
+        "start_time_seconds": "1703591226",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/home/cybertron/anaconda3/envs/rl/bin/mlagents-learn /home/cybertron/Desktop/ml-agents/config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
+        "command_line_arguments": "/home/cybertron/anaconda3/envs/rl/bin/mlagents-learn /home/cybertron/Desktop/ml-agents/config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force",
         "mlagents_version": "1.0.0",
         "mlagents_envs_version": "1.0.0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.1.1",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1703589997"
+        "end_time_seconds": "1703591510"
     },
-    "total": 25.27916620600081,
+    "total": 284.3635966809961,
     "count": 1,
-    "self": 0.030008082998392638,
+    "self": 0.21882801299216226,
     "children": {
         "run_training.setup": {
-            "total": 0.011635144001047593,
+            "total": 0.012106276000849903,
             "count": 1,
-            "self": 0.011635144001047593
+            "self": 0.012106276000849903
         },
         "TrainerController.start_learning": {
-            "total": 25.23752297900137,
+            "total": 284.1326623920031,
             "count": 1,
-            "self": 0.02163675902193063,
+            "self": 0.13699659491248894,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.8909534080012236,
-                    "count": 2,
-                    "self": 1.8909534080012236
+                    "total": 2.0738567980006337,
+                    "count": 1,
+                    "self": 2.0738567980006337
                 },
                 "TrainerController.advance": {
-                    "total": 23.136872530980327,
-                    "count": 1461,
-                    "self": 0.021862540888832882,
+                    "total": 279.10317788109387,
+                    "count": 8577,
+                    "self": 0.1445215416897554,
                     "children": {
                         "env_step": {
-                            "total": 22.047475695031608,
-                            "count": 1461,
-                            "self": 16.652173617960216,
+                            "total": 198.89272247839108,
+                            "count": 8577,
+                            "self": 100.6482229002795,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 5.3811991840047995,
-                                    "count": 1461,
-                                    "self": 0.12078593808109872,
+                                    "total": 98.15602654993563,
+                                    "count": 8577,
+                                    "self": 0.9458562079526018,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 5.260413245923701,
-                                            "count": 2908,
-                                            "self": 5.260413245923701
+                                            "total": 97.21017034198303,
+                                            "count": 17038,
+                                            "self": 97.21017034198303
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.014102893066592515,
-                                    "count": 1460,
+                                    "total": 0.08847302817594027,
+                                    "count": 8577,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 25.02045437198103,
-                                            "count": 1460,
+                                            "total": 279.9393852657813,
+                                            "count": 8577,
                                             "is_parallel": true,
-                                            "self": 11.028041653993569,
+                                            "self": 195.6091849016957,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -193,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0017820489993027877,
+                                                            "total": 0.0018885289973695762,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.00039754300451022573,
+                                                            "self": 0.0004485460085561499,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001384505994792562,
+                                                                    "total": 0.0014399829888134263,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001384505994792562
+                                                                    "self": 0.0014399829888134263
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.019492260998958955,
+                                                            "total": 0.019859125000948552,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0004075500000908505,
+                                                            "self": 0.00042441000550752506,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003197090009052772,
+                                                                    "total": 0.0005746079987147823,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003197090009052772
+                                                                    "self": 0.0005746079987147823
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.017475802000262775,
+                                                                    "total": 0.017522023001220077,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.017475802000262775
+                                                                    "self": 0.017522023001220077
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0012891999977000523,
+                                                                    "total": 0.0013380839955061674,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002657109980646055,
+                                                                    "self": 0.0002767289915936999,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0010234889996354468,
+                                                                            "total": 0.0010613550039124675,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0010234889996354468
+                                                                            "self": 0.0010613550039124675
                                                                         }
                                                                     }
                                                                 }
@@ -242,49 +314,35 @@
                                                         }
                                                     }
                                                 },
-                                                "steps_from_proto": {
-                                                    "total": 0.0012812650020350702,
-                                                    "count": 2,
-                                                    "is_parallel": true,
-                                                    "self": 0.0002530899982957635,
-                                                    "children": {
-                                                        "_process_rank_one_or_two_observation": {
-                                                            "total": 0.0010281750037393067,
-                                                            "count": 8,
-                                                            "is_parallel": true,
-                                                            "self": 0.0010281750037393067
-                                                        }
-                                                    }
-                                                },
                                                 "UnityEnvironment.step": {
-                                                    "total": 13.991131452985428,
-                                                    "count": 1459,
+                                                    "total": 84.33020036408561,
+                                                    "count": 8576,
                                                     "is_parallel": true,
-                                                    "self": 0.7237382169769262,
+                                                    "self": 4.363296162802726,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.41074541095804307,
-                                                            "count": 1459,
+                                                            "total": 2.5144244331968366,
+                                                            "count": 8576,
                                                             "is_parallel": true,
-                                                            "self": 0.41074541095804307
+                                                            "self": 2.5144244331968366
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 10.776612414010742,
-                                                            "count": 1459,
+                                                            "total": 64.61790556683991,
+                                                            "count": 8576,
                                                             "is_parallel": true,
-                                                            "self": 10.776612414010742
+                                                            "self": 64.61790556683991
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 2.0800354110397166,
-                                                            "count": 2918,
+                                                            "total": 12.834574201246141,
+                                                            "count": 17152,
                                                             "is_parallel": true,
-                                                            "self": 0.384538546029944,
+                                                            "self": 2.373371579713421,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 1.6954968650097726,
-                                                                    "count": 11672,
+                                                                    "total": 10.46120262153272,
+                                                                    "count": 68608,
                                                                     "is_parallel": true,
-                                                                    "self": 1.6954968650097726
+                                                                    "self": 10.46120262153272
                                                                 }
                                                             }
                                                         }
@@ -297,33 +355,40 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1.067534295059886,
-                            "count": 1460,
-                            "self": 0.10599143002400524,
+                            "total": 80.06593386101304,
+                            "count": 8577,
+                            "self": 1.3821683759160805,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 0.9615428650358808,
-                                    "count": 1460,
-                                    "self": 0.9615428650358808
+                                    "total": 11.169169155109557,
+                                    "count": 8577,
+                                    "self": 11.169169155109557
+                                },
+                                "_update_policy": {
+                                    "total": 67.5145963299874,
+                                    "count": 6,
+                                    "self": 12.408137330006866,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 55.10645899998053,
+                                            "count": 76,
+                                            "self": 55.10645899998053
+                                        }
+                                    }
                                 }
                             }
                         }
                     }
                 },
-                "trainer_threads": {
-                    "total": 8.399983926210552e-07,
-                    "count": 1,
-                    "self": 8.399983926210552e-07
-                },
                 "TrainerController._save_models": {
-                    "total": 0.18805944099949556,
+                    "total": 2.8186311179961194,
                     "count": 1,
-                    "self": 0.0014082630004850216,
+                    "self": 2.9962000553496182e-05,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.18665117799901054,
+                            "total": 2.818601155995566,
                             "count": 1,
-                            "self": 0.18665117799901054
+                            "self": 2.818601155995566
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,35 +1,6 @@
 {
     "SoccerTwos": {
-        "elo": 1205.850037125567,
-        "checkpoints": [
-            {
-                "steps": 203078,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-203078.onnx",
-                "reward": 0.0,
-                "creation_time": 1703589965.3602862,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-203078.pt"
-                ]
-            },
-            {
-                "steps": 218994,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-218994.onnx",
-                "reward": 0.0,
-                "creation_time": 1703589997.6629596,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-218994.pt"
-                ]
-            }
-        ],
-        "final_checkpoint": {
-            "steps": 218994,
-            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
-            "reward": 0.0,
-            "creation_time": 1703589997.6629596,
-            "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-218994.pt"
-            ]
-        }
+        "elo": 1200.953350551564
     },
     "metadata": {
         "stats_format_version": "0.3.0",