7th Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b4697cfd89d5a5b0451dbf8040978bd98b46e7c7baa633f4b48291606bece60
+oid sha256:54dda9ae2311ea21e2f9af9e7e3e9a90f3950b0135f65860d0de1e296969163f
 size 21520334

SoccerTwos/SoccerTwos-13499993.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030d6dbe9ef15c133fcc9dd357633e15e1d7c7bc069bae62f9341cb49b657e2e
+size 21520334

SoccerTwos/SoccerTwos-13499993.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1afb30d62e9e790e0439b0f2af67614020007baf4f3354086ace0afadf78c947
+size 232310391

SoccerTwos/SoccerTwos-13999896.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f29a9c99445aa3af77840feaea0aafd70f4ead4562736d00c45fac3867add8
+size 21520334

SoccerTwos/SoccerTwos-13999896.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1cbc11a8b4ef6536bca8dfee1764299b7d4a2b5ac65211a657762d5f0defedd
+size 232310391

SoccerTwos/SoccerTwos-14499990.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef2e66f98ae7e9fa27c40acf9f1f20e60286c2ea6e8c9024388d15541ffdeff
+size 21520334

SoccerTwos/SoccerTwos-14499990.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6fb89e9748c0a79a887cd369116804eaf583f7853349b0684772000bde5d81
+size 232310391

SoccerTwos/SoccerTwos-14999767.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54dda9ae2311ea21e2f9af9e7e3e9a90f3950b0135f65860d0de1e296969163f
+size 21520334

SoccerTwos/SoccerTwos-14999767.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0acdc3fa7685553f240d9f2e7982eefdcd4c82645c139822cab0142d1995fe
+size 232310391

SoccerTwos/SoccerTwos-15000056.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54dda9ae2311ea21e2f9af9e7e3e9a90f3950b0135f65860d0de1e296969163f
+size 21520334

SoccerTwos/SoccerTwos-15000056.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:213c41696b915f4aa21a5eafab9cf57c7a4d51ef928b9ea620561bf0fc27aced
+size 232310391

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6f24fdaa2f79db2ad82e7e5e3b1faa4a120bf0d2ad14d4e424b5cf3f24385bb
+oid sha256:8deccbae5c5f0848e2618dd090eacbf2d3d60a238a00f669243d8dca87a778cf
 size 232308969

SoccerTwos/events.out.tfevents.1761039534.ada-B550-AORUS-ELITE.320808.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cec71eab6310b735efbd947a721b4d99b339a108eada0352e4bbf1430a0cfe5d
+size 5098109

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 4096, "buffer_size": 40960, "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": 1280, "num_layers": 4, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 10000000, "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/linux/SoccerTwos/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 4096, "buffer_size": 40960, "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": 1280, "num_layers": 4, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 15000000, "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/linux/SoccerTwos/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 10000000
+    max_steps: 15000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -11,7 +11,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.066 seconds
+- Completed reload, in  0.063 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -36,7 +36,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 1.175173 ms
+UnloadTime: 1.845811 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
@@ -45,7 +45,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 94130 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 94203 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
@@ -88,7 +88,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 5]
       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_Background Job.Worker 14]
       Initial Block Size 32.0 KB
@@ -163,7 +163,7 @@ 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
@@ -231,19 +231,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 4
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 94131 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 94204 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 4.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 94131 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 94204 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.5 MB
@@ -275,13 +275,13 @@ 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]: 94130 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 94203 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]: 94131 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 94204 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -293,13 +293,13 @@ 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]: 94131 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 94204 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]: 94130 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 94203 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
@@ -311,13 +311,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 94131 frames
+      Peak usage frame count: [0-1.0 KB]: 94204 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]: 94130 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 94203 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

@@ -2,75 +2,75 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 2.0398004055023193,
-            "min": 1.9644250869750977,
-            "max": 2.3080594539642334,
+            "value": 2.0193281173706055,
+            "min": 1.9643131494522095,
+            "max": 2.0792429447174072,
             "count": 500
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 40339.09375,
-            "min": 35269.69921875,
-            "max": 51725.21875,
+            "value": 36832.546875,
+            "min": 33020.5546875,
+            "max": 50278.8203125,
             "count": 500
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 70.55555555555556,
-            "min": 48.504950495049506,
-            "max": 88.70175438596492,
+            "value": 87.18181818181819,
+            "min": 56.833333333333336,
+            "max": 113.6590909090909,
             "count": 500
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 20320.0,
-            "min": 18460.0,
-            "max": 20968.0,
+            "value": 19180.0,
+            "min": 18308.0,
+            "max": 21300.0,
             "count": 500
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1430.6054365615053,
-            "min": 1395.4322560619753,
-            "max": 1479.3025989460373,
+            "value": 1410.7601003344073,
+            "min": 1379.8705983144878,
+            "max": 1465.220959065712,
             "count": 500
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 206007.18286485676,
-            "min": 162083.54493889448,
-            "max": 288266.36033069075,
+            "value": 155183.6110367848,
+            "min": 123247.55267462911,
+            "max": 248221.81810924233,
             "count": 500
         },
         "SoccerTwos.Step.mean": {
-            "value": 9999844.0,
-            "min": 5009936.0,
-            "max": 9999844.0,
+            "value": 14999767.0,
+            "min": 10009854.0,
+            "max": 14999767.0,
             "count": 500
         },
         "SoccerTwos.Step.sum": {
-            "value": 9999844.0,
-            "min": 5009936.0,
-            "max": 9999844.0,
+            "value": 14999767.0,
+            "min": 10009854.0,
+            "max": 14999767.0,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.02794094942510128,
-            "min": -0.13166673481464386,
-            "max": 0.09667656570672989,
+            "value": -0.013330723159015179,
+            "min": -0.15980811417102814,
+            "max": 0.0799807533621788,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -4.023496627807617,
-            "min": -22.646678924560547,
-            "max": 15.97828197479248,
+            "value": -1.4797102212905884,
+            "min": -19.49658966064453,
+            "max": 9.91761302947998,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.03377959504723549,
-            "min": -0.13075293600559235,
-            "max": 0.09306292980909348,
+            "value": -0.018607420846819878,
+            "min": -0.159414604306221,
+            "max": 0.08092209696769714,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -4.864261627197266,
-            "min": -22.489505767822266,
-            "max": 15.767440795898438,
+            "value": -2.0654237270355225,
+            "min": -19.77153205871582,
+            "max": 10.034339904785156,
             "count": 500
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
@@ -86,27 +86,27 @@
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.19032777928643757,
-            "min": -0.45712957793558145,
-            "max": 0.3221280566222376,
+            "value": -0.006893694937766135,
+            "min": -0.4453192295936438,
+            "max": 0.37280999720096586,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -27.40720021724701,
-            "min": -67.62159985303879,
-            "max": 55.031199872493744,
+            "value": -0.765200138092041,
+            "min": -63.493199944496155,
+            "max": 44.737199664115906,
             "count": 500
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.19032777928643757,
-            "min": -0.45712957793558145,
-            "max": 0.3221280566222376,
+            "value": -0.006893694937766135,
+            "min": -0.4453192295936438,
+            "max": 0.37280999720096586,
             "count": 500
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -27.40720021724701,
-            "min": -67.62159985303879,
-            "max": 55.031199872493744,
+            "value": -0.765200138092041,
+            "min": -63.493199944496155,
+            "max": 44.737199664115906,
             "count": 500
         },
         "SoccerTwos.IsTraining.mean": {
@@ -122,39 +122,39 @@
             "count": 500
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.020835822743053237,
-            "min": 0.011444932171919693,
-            "max": 0.021884263044921682,
+            "value": 0.0260514505886628,
+            "min": 0.017916234560713444,
+            "max": 0.02759317404900988,
             "count": 121
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.020835822743053237,
-            "min": 0.011444932171919693,
-            "max": 0.021884263044921682,
+            "value": 0.0260514505886628,
+            "min": 0.017916234560713444,
+            "max": 0.02759317404900988,
             "count": 121
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.09043513039747873,
-            "min": 0.09043513039747873,
-            "max": 0.11270512193441391,
+            "value": 0.08049535776178042,
+            "min": 0.07586482713619867,
+            "max": 0.09767879719535509,
             "count": 121
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.09043513039747873,
-            "min": 0.09043513039747873,
-            "max": 0.11270512193441391,
+            "value": 0.08049535776178042,
+            "min": 0.07586482713619867,
+            "max": 0.09767879719535509,
             "count": 121
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.0924225573738416,
-            "min": 0.0924225573738416,
-            "max": 0.11528976236780485,
+            "value": 0.08245965912938118,
+            "min": 0.07864355693260829,
+            "max": 0.09992946684360504,
             "count": 121
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.0924225573738416,
-            "min": 0.0924225573738416,
-            "max": 0.11528976236780485,
+            "value": 0.08245965912938118,
+            "min": 0.07864355693260829,
+            "max": 0.09992946684360504,
             "count": 121
         },
         "SoccerTwos.Policy.LearningRate.mean": {
@@ -196,7 +196,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1761030263",
+        "start_time_seconds": "1761039533",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
         "command_line_arguments": "/home/ada/work/ai/venv3.10/bin/mlagents-learn ./config/poca/SoccerTwosGo.yaml --resume --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics",
         "mlagents_version": "1.2.0.dev0",
@@ -204,59 +204,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.9.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1761039070"
+        "end_time_seconds": "1761048180"
     },
-    "total": 8806.912067136,
+    "total": 8646.804316897003,
     "count": 1,
-    "self": 0.3700354260217864,
+    "self": 0.5711837930139154,
     "children": {
         "run_training.setup": {
-            "total": 0.02791739098029211,
+            "total": 0.04321815399453044,
             "count": 1,
-            "self": 0.02791739098029211
+            "self": 0.04321815399453044
         },
         "TrainerController.start_learning": {
-            "total": 8806.514114318998,
+            "total": 8646.189914949995,
             "count": 1,
-            "self": 7.435185670939973,
+            "self": 7.507484404166462,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.84465062894742,
+                    "total": 2.494118211994646,
                     "count": 26,
-                    "self": 2.84465062894742
+                    "self": 2.494118211994646
                 },
                 "TrainerController.advance": {
-                    "total": 8790.612266586104,
-                    "count": 343638,
-                    "self": 6.351156423712382,
+                    "total": 8630.252385538857,
+                    "count": 339454,
+                    "self": 6.080225770798279,
                     "children": {
                         "env_step": {
-                            "total": 6720.901084811252,
-                            "count": 343638,
-                            "self": 5002.9086125326285,
+                            "total": 6664.653628120519,
+                            "count": 339454,
+                            "self": 4947.748722012417,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 1712.9968780488416,
-                                    "count": 343638,
-                                    "self": 40.101664002315374,
+                                    "total": 1711.8997630827362,
+                                    "count": 339454,
+                                    "self": 42.065065260307165,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 1672.8952140465262,
-                                            "count": 627544,
-                                            "self": 1672.8952140465262
+                                            "total": 1669.834697822429,
+                                            "count": 628038,
+                                            "self": 1669.834697822429
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 4.995594229782,
-                                    "count": 343638,
+                                    "total": 5.005143025366124,
+                                    "count": 339454,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 8783.89048864122,
-                                            "count": 343638,
+                                            "total": 8624.998652902985,
+                                            "count": 339454,
                                             "is_parallel": true,
-                                            "self": 4590.35340325741,
+                                            "self": 4486.705685442663,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.003542367019690573,
+                                                            "total": 0.0034261269902344793,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0007718350389041007,
+                                                            "self": 0.0007970519363880157,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0027705319807864726,
+                                                                    "total": 0.0026290750538464636,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0027705319807864726
+                                                                    "self": 0.0026290750538464636
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.024601226003142074,
+                                                            "total": 0.023506944009568542,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005739079788327217,
+                                                            "self": 0.0011191890225745738,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0011554610100574791,
+                                                                    "total": 0.0003908869985025376,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0011554610100574791
+                                                                    "self": 0.0003908869985025376
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.021280603017657995,
+                                                                    "total": 0.01935509900795296,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.021280603017657995
+                                                                    "self": 0.01935509900795296
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0015912539965938777,
+                                                                    "total": 0.0026417689805384725,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002887440496124327,
+                                                                    "self": 0.0004645489971153438,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001302509946981445,
+                                                                            "total": 0.0021772199834231287,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001302509946981445
+                                                                            "self": 0.0021772199834231287
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.05390251087374054,
+                                                    "total": 0.05029912613099441,
                                                     "count": 50,
                                                     "is_parallel": true,
-                                                    "self": 0.008939814695622772,
+                                                    "self": 0.00849195200135,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.04496269617811777,
+                                                            "total": 0.04180717412964441,
                                                             "count": 200,
                                                             "is_parallel": true,
-                                                            "self": 0.04496269617811777
+                                                            "self": 0.04180717412964441
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 4193.483182872937,
-                                                    "count": 343637,
+                                                    "total": 4138.242668334191,
+                                                    "count": 339453,
                                                     "is_parallel": true,
-                                                    "self": 237.2786227556353,
+                                                    "self": 235.49196220262093,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 165.74657718246453,
-                                                            "count": 343637,
+                                                            "total": 162.76754256189452,
+                                                            "count": 339453,
                                                             "is_parallel": true,
-                                                            "self": 165.74657718246453
+                                                            "self": 162.76754256189452
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 3161.2942640984547,
-                                                            "count": 343637,
+                                                            "total": 3117.3282692046196,
+                                                            "count": 339453,
                                                             "is_parallel": true,
-                                                            "self": 3161.2942640984547
+                                                            "self": 3117.3282692046196
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 629.163718836382,
-                                                            "count": 687274,
+                                                            "total": 622.654894365056,
+                                                            "count": 678906,
                                                             "is_parallel": true,
-                                                            "self": 106.77949554094812,
+                                                            "self": 104.93273744470207,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 522.3842232954339,
-                                                                    "count": 2749096,
+                                                                    "total": 517.7221569203539,
+                                                                    "count": 2715624,
                                                                     "is_parallel": true,
-                                                                    "self": 522.3842232954339
+                                                                    "self": 517.7221569203539
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 2063.3600253511395,
-                            "count": 343638,
-                            "self": 60.09984627761878,
+                            "total": 1959.51853164754,
+                            "count": 339454,
+                            "self": 60.41723086338607,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 923.2924243326415,
-                                    "count": 343638,
-                                    "self": 878.8967296876363,
+                                    "total": 824.4058585642197,
+                                    "count": 339454,
+                                    "self": 786.0357252132089,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 44.39569464500528,
+                                            "total": 38.370133351010736,
                                             "count": 10,
-                                            "self": 44.39569464500528
+                                            "self": 38.370133351010736
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1079.9677547408792,
+                                    "total": 1074.6954422199342,
                                     "count": 121,
-                                    "self": 543.4696179345483,
+                                    "self": 539.9536242478644,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 536.4981368063309,
+                                            "total": 534.7418179720698,
                                             "count": 3630,
-                                            "self": 536.4981368063309
+                                            "self": 534.7418179720698
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 5.309993866831064e-07,
+                    "total": 5.809997674077749e-07,
                     "count": 1,
-                    "self": 5.309993866831064e-07
+                    "self": 5.809997674077749e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 5.622010902006878,
+                    "total": 5.935926213976927,
                     "count": 1,
-                    "self": 0.12181861800490879,
+                    "self": 0.17000244598602876,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 5.500192284001969,
+                            "total": 5.765923767990898,
                             "count": 1,
-                            "self": 5.500192284001969
+                            "self": 5.765923767990898
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 8499928,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8499928.onnx",
+                "steps": 13499993,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13499993.onnx",
                 "reward": 0.0,
-                "creation_time": 1761036429.2893617,
+                "creation_time": 1761045583.9210482,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8499928.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13499993.pt"
                 ]
             },
             {
-                "steps": 8999842,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8999842.onnx",
+                "steps": 13999896,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13999896.onnx",
                 "reward": 0.0,
-                "creation_time": 1761037307.3044715,
+                "creation_time": 1761046445.653239,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8999842.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13999896.pt"
                 ]
             },
             {
-                "steps": 9499972,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9499972.onnx",
+                "steps": 14499990,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14499990.onnx",
                 "reward": 0.0,
-                "creation_time": 1761038188.2236493,
+                "creation_time": 1761047312.8546755,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9499972.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14499990.pt"
                 ]
             },
             {
-                "steps": 9999844,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9999844.onnx",
+                "steps": 14999767,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14999767.onnx",
                 "reward": 0.0,
-                "creation_time": 1761039064.1502738,
+                "creation_time": 1761048173.7460728,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9999844.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14999767.pt"
                 ]
             },
             {
-                "steps": 10000402,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-10000402.onnx",
+                "steps": 15000056,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-15000056.onnx",
                 "reward": 0.0,
-                "creation_time": 1761039069.6936312,
+                "creation_time": 1761048179.5381525,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-10000402.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-15000056.pt"
                 ]
             }
         ],
-        "elo": 1429.5746920677718,
+        "elo": 1411.057248883631,
         "final_checkpoint": {
-            "steps": 10000402,
+            "steps": 15000056,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1761039069.6936312,
+            "creation_time": 1761048179.5381525,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-10000402.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-15000056.pt"
             ]
         }
     },