First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7789c0578940e6761a33f9c2ae32b8772d825eceb2fa7e0f2a45ec6e161e47fa
+oid sha256:1467ca6eee8b0d9354920191311004adb988ef6db1a3dfe2c2ed2d6a240febed
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4b636c9f4f543b1fb1aa40f21a18395f35cf6c7dbb9dbc46f0745215947d7a9
+oid sha256:be03bef452c38a3e5eaee84aad5f852ff7adb7b7db9aafa7b75256f5e0a48388
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75007ae9f442525aae4bad1f107d1e331a5c1de9ad748b3987c30e3a674360dd
+oid sha256:80c9847ec4511cd37edf69a4460c07f2d8656e4dfd048fd65c1bf6d84745e2e6
 size 3849902

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446a642d78b990be49009573f22155a5b3c66f993e717933e19e5ee19109dd81
+oid sha256:1467ca6eee8b0d9354920191311004adb988ef6db1a3dfe2c2ed2d6a240febed
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5060f97da5cb2e41d551e65d4a9ec0d562bd4c482ead8b1cf8a4bf7edb7af148
+oid sha256:8a5918ddb8fb5bfaeab21866901b3f852449137f40bb90e550dba3853e44e909
 size 3849902

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446a642d78b990be49009573f22155a5b3c66f993e717933e19e5ee19109dd81
+oid sha256:1467ca6eee8b0d9354920191311004adb988ef6db1a3dfe2c2ed2d6a240febed
 size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9b57d18c2991d313d121815204133f48732fb091a33b1a9fc0c436f7ec16b78
+oid sha256:a54b0e52e6f3b3645c7f5c2008c7b8c86d4a4ad6abc324f2df9b828c1f8eb0bc
 size 3849902

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f31425e30a69b0b4d2e32c10ec39328db74aa4c844ab14e48590df61b6ff9ab8
+oid sha256:aab5974c73721d7ae52587d4e234b8d1cabeb65108b8dac7fb5ca7adbfb41dd9
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:427c342473214b0c9fd03aa3234cdef873872ff59a7b71494875850c4caaf140
+oid sha256:8654e0fac2e6cfaea9adf40aceac3b2c4344b1d8461ca81ddb6db5177dc00d23
 size 3849827

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd038bc98525bde97e5ac3790dad66f8d497c5a97580dc909db231d81aad2db4
+oid sha256:ccf0818a9d839fc28f8669ea68810683762931de2a2ac64d89477c68537e26a5
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fe89bb4cc4237925fd66351e709a3cf04479956f284ea7b60c3415706835190
+oid sha256:a0d10a67f208de9948f90ec1ba391fc3dae7d1c3c40e736ca02b10d35f07e14e
 size 3849827

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c1d07603fad469d1ad636554986bf05d208c0f539ff032e680b2e9d55886c74
+oid sha256:04e449f09d2cbdaae7d585ebd1146a21277abed8cca173dc3b4268038f6b9aed
 size 3849077

SnowballTarget/events.out.tfevents.1774515909.93bd6bb4963f.25494.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed85a8df580fe114a0887cd454c508b3fac2264b05c9a034e7e4a523a3d90d7
+size 23941

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "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": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget", "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "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": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -45,7 +45,7 @@ behaviors:
     self_play: null
     behavioral_cloning: null
 env_settings:
-  env_path: /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
   env_args: null
   base_port: 5005
   num_envs: 1
@@ -70,7 +70,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -2,6 +2,9 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
 Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
+Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_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  0.086 seconds
+- Completed reload, in  0.217 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)
@@ -42,7 +45,7 @@ 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: 0.635293 ms
+UnloadTime: 0.881739 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -50,7 +53,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 71 frames, [16.0 KB-32.0 KB]: 1 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -166,22 +169,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 23
+  Peak main deferred allocation count 40
     [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]: 73 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.6 MB
+      Peak Allocated memory 6.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 73 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.3 MB
+      Peak Allocated memory 17.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -210,13 +213,13 @@ 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]: 59 frames, [64.0 KB-128.0 KB]: 14 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5100 frames, [64.0 KB-128.0 KB]: 358 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.0 KB
+      Peak Allocated memory 66.4 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 73 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -228,13 +231,13 @@ 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]: 73 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5458 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]: 72 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -246,13 +249,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 73 frames
+      Peak usage frame count: [0-1.0 KB]: 5458 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]: 73 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -1,68 +1,214 @@
 {
     "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.8421187996864319,
+            "min": 0.8294015526771545,
+            "max": 2.862067699432373,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 8003.4970703125,
+            "min": 8003.4970703125,
+            "max": 29215.986328125,
+            "count": 20
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.93126392364502,
+            "min": 0.578868567943573,
+            "max": 12.945226669311523,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2521.596435546875,
+            "min": 112.30050659179688,
+            "max": 2640.826171875,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06596056137955292,
+            "min": 0.06252342511816453,
+            "max": 0.07189556669681241,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.26384224551821167,
+            "min": 0.2500937004726581,
+            "max": 0.35947783348406204,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.2147451358682969,
+            "min": 0.14058841464073196,
+            "max": 0.2829120778569988,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.8589805434731876,
+            "min": 0.5623536585629278,
+            "max": 1.3469010889530182,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.082097306000005e-06,
+            "min": 8.082097306000005e-06,
+            "max": 0.000291882002706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.232838922400002e-05,
+            "min": 3.232838922400002e-05,
+            "max": 0.00138516003828,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10269400000000001,
+            "min": 0.10269400000000001,
+            "max": 0.19729400000000002,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.41077600000000003,
+            "min": 0.41077600000000003,
+            "max": 0.96172,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0001444306000000001,
+            "min": 0.0001444306000000001,
+            "max": 0.0048649706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005777224000000004,
+            "min": 0.0005777224000000004,
+            "max": 0.023089828,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 24.84090909090909,
+            "min": 4.136363636363637,
+            "max": 25.618181818181817,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1093.0,
+            "min": 182.0,
+            "max": 1409.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 24.84090909090909,
+            "min": 4.136363636363637,
+            "max": 25.618181818181817,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1093.0,
+            "min": 182.0,
+            "max": 1409.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1774450640",
-        "python_version": "3.10.12 (main, Mar  3 2026, 11:56:32) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
+        "start_time_seconds": "1774515907",
+        "python_version": "3.10.12 (main, Mar 26 2026, 08:57:09) [GCC 11.4.0]",
+        "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1774450650"
+        "end_time_seconds": "1774516598"
     },
-    "total": 9.944801772000119,
+    "total": 691.0420400199996,
     "count": 1,
-    "self": 0.2512809649997507,
+    "self": 0.5393680859997403,
     "children": {
         "run_training.setup": {
-            "total": 0.020826790000228357,
+            "total": 0.04395901799989588,
             "count": 1,
-            "self": 0.020826790000228357
+            "self": 0.04395901799989588
         },
         "TrainerController.start_learning": {
-            "total": 9.67269401700014,
+            "total": 690.458712916,
             "count": 1,
-            "self": 0.007303334000880568,
+            "self": 0.695101081975281,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.2259614049999072,
+                    "total": 3.9992803519999143,
                     "count": 1,
-                    "self": 2.2259614049999072
+                    "self": 3.9992803519999143
                 },
                 "TrainerController.advance": {
-                    "total": 7.258743764999508,
-                    "count": 241,
-                    "self": 0.0070282040028359916,
+                    "total": 685.6588675920248,
+                    "count": 18192,
+                    "self": 0.7597590580558062,
                     "children": {
                         "env_step": {
-                            "total": 5.826802035001037,
-                            "count": 241,
-                            "self": 4.526333886993598,
+                            "total": 499.50885010496995,
+                            "count": 18192,
+                            "self": 386.74676743300006,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 1.296535138004856,
-                                    "count": 241,
-                                    "self": 0.020648447005441994,
+                                    "total": 112.33429610399344,
+                                    "count": 18192,
+                                    "self": 2.2981345710272763,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 1.275886690999414,
-                                            "count": 241,
-                                            "self": 1.275886690999414
+                                            "total": 110.03616153296616,
+                                            "count": 18192,
+                                            "self": 110.03616153296616
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.0039330100025836146,
-                                    "count": 240,
+                                    "total": 0.42778656797645453,
+                                    "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 9.469316171006085,
-                                            "count": 240,
+                                            "total": 687.1033201259816,
+                                            "count": 18192,
                                             "is_parallel": true,
-                                            "self": 5.5749521690063375,
+                                            "self": 355.29735936896077,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -71,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002102367000134109,
+                                                            "total": 0.00567378000005192,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005958860001555877,
+                                                            "self": 0.0038776699993832153,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0015064809999785211,
+                                                                    "total": 0.0017961100006687047,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0015064809999785211
+                                                                    "self": 0.0017961100006687047
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.039717526000004,
+                                                            "total": 0.046606675000020914,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006249230000321404,
+                                                            "self": 0.0008353890002581466,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00039238399995156215,
+                                                                    "total": 0.0007151039999371278,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00039238399995156215
+                                                                    "self": 0.0007151039999371278
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.036524124999687047,
+                                                                    "total": 0.04219078799997078,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.036524124999687047
+                                                                    "self": 0.04219078799997078
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0021760940003332507,
+                                                                    "total": 0.0028653939998548594,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00045167400003265357,
+                                                                    "self": 0.0005732739991799463,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0017244200003005972,
+                                                                            "total": 0.002292120000674913,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0017244200003005972
+                                                                            "self": 0.002292120000674913
                                                                         }
                                                                     }
                                                                 }
@@ -121,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 3.8943640019997474,
-                                                    "count": 239,
+                                                    "total": 331.8059607570208,
+                                                    "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 0.14868378399523863,
+                                                    "self": 15.749062510966269,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.07919952900101634,
-                                                            "count": 239,
+                                                            "total": 9.289236497021193,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.07919952900101634
+                                                            "self": 9.289236497021193
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2.9883966150009655,
-                                                            "count": 239,
+                                                            "total": 247.05889551302835,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 2.9883966150009655
+                                                            "self": 247.05889551302835
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 0.6780840740025269,
-                                                            "count": 239,
+                                                            "total": 59.708766236004976,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.11788593300070715,
+                                                            "self": 11.343388004057033,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.5601981410018197,
-                                                                    "count": 2390,
+                                                                    "total": 48.36537823194794,
+                                                                    "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 0.5601981410018197
+                                                                    "self": 48.36537823194794
                                                                 }
                                                             }
                                                         }
@@ -161,24 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1.4249135259956347,
-                            "count": 240,
-                            "self": 0.007994139994025318,
+                            "total": 185.390258428999,
+                            "count": 18192,
+                            "self": 0.8655924619638427,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 0.3330998380015444,
-                                    "count": 240,
-                                    "self": 0.3330998380015444
+                                    "total": 42.93650429603531,
+                                    "count": 18192,
+                                    "self": 42.41495265703452,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.5215516390007906,
+                                            "count": 4,
+                                            "self": 0.5215516390007906
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 1.083819548000065,
-                                    "count": 1,
-                                    "self": 0.3629525940009444,
+                                    "total": 141.58816167099985,
+                                    "count": 90,
+                                    "self": 65.6881444659748,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 0.7208669539991206,
-                                            "count": 48,
-                                            "self": 0.7208669539991206
+                                            "total": 75.90001720502505,
+                                            "count": 4587,
+                                            "self": 75.90001720502505
                                         }
                                     }
                                 }
@@ -187,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.47299988384475e-06,
+                    "total": 1.1669999366858974e-06,
                     "count": 1,
-                    "self": 1.47299988384475e-06
+                    "self": 1.1669999366858974e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.18068403999996008,
+                    "total": 0.10546272300007331,
                     "count": 1,
-                    "self": 0.0017293259998041322,
+                    "self": 0.0008940550001170777,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.17895471400015595,
+                            "total": 0.10456866799995623,
                             "count": 1,
-                            "self": 0.17895471400015595
+                            "self": 0.10456866799995623
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,58 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 2200,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2200.onnx",
-                "reward": 3.090909090909091,
-                "creation_time": 1774450650.635877,
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 13.454545454545455,
+                "creation_time": 1774516083.484805,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-2200.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 22.90909090909091,
+                "creation_time": 1774516257.5857074,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 23.90909090909091,
+                "creation_time": 1774516431.0897186,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 26.09090909090909,
+                "creation_time": 1774516598.0796702,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 26.09090909090909,
+                "creation_time": 1774516598.2026603,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2200,
+            "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 3.090909090909091,
-            "creation_time": 1774450650.635877,
+            "reward": 26.09090909090909,
+            "creation_time": 1774516598.2026603,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-2200.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },