First Push

SnowballTarget.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc225048d8dfa7dcb8319518f1c8d6efce8a4f9958f50dbfff03db2d0dce18d3
+size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fdfe1be8254bfbc241840fd8db985f71b3b4fc0aa3fa47a90adf2ee90708364
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e96c969dd39b39be80a570df70e1274ddf7f2ec08054e310c79b681ca4a67b
+size 3850564

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc225048d8dfa7dcb8319518f1c8d6efce8a4f9958f50dbfff03db2d0dce18d3
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:892b7472212b25b344bfb27341953b80edbf2fd3c2f57e69cd34937901b85984
+size 3850564

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc225048d8dfa7dcb8319518f1c8d6efce8a4f9958f50dbfff03db2d0dce18d3
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8caad15cf979472fe6bb55a04b31c0e258df53b38d83df2d31e947917b9fd7ea
+size 3850564

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2136e4a49b7021b8556ac564c3266e5e603d526cc0cef60a6aa688d45256d55
+size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42a32425b9dc0528ba4b790d454d0bdaf89d00a7bb684b83c10057503c05c16b
+oid sha256:a881eb674d3a62a7fc0f33453f503a9ff3dc2ea70998c3627cbfeffe9d51e255
 size 3850487

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9bb8a521a20812bda066cfe1841625d572a928058ab8213ccbb46f376a66cc
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16942f506a358c25d70933bb77b78421cbe51dfd665e90095fc589da9005cc7
+size 3850487

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3e91d6ec5922041d591d56b6b32a5b1b650c9a9ea5f50208351fad9b21a194
+oid sha256:2d687120a016d05f33bb9db199ae3fcb570983f2da05fb7f7280b15f48b39a00
 size 3849717

SnowballTarget/events.out.tfevents.1765596681.6633669359a9.3098.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14dfe62209b9b48744803c508be4c1d905a8a2cd280251ec6ddefa35d36b18fa
+size 28094

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": "./training-envs-executables/linux/SnowballTarget/SnowballTarget.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, "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}
+{"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: ./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
   env_args: null
   base_port: 5005
   num_envs: 1

run_logs/Player-0.log

@@ -1,12 +1,12 @@
-Mono path[0] = '/content/ml-agents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
-Mono config path = '/content/ml-agents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+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/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
@@ -34,7 +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  0.209 seconds
+- Completed reload, in  0.084 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)
@@ -45,7 +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: 1.670405 ms
+UnloadTime: 0.653834 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.
@@ -53,7 +53,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 1355 frames, [16.0 KB-32.0 KB]: 22 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
@@ -61,7 +61,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 218 B
+      Peak Allocated Bytes 198 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
@@ -169,19 +169,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 45
+  Peak main deferred allocation count 44
     [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]: 1378 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 6.2 MB
+      Peak Allocated memory 7.1 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1378 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
@@ -213,13 +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]: 797 frames, [64.0 KB-128.0 KB]: 581 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4981 frames, [64.0 KB-128.0 KB]: 477 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 67.7 KB
+      Peak Allocated memory 66.8 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1378 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
@@ -231,13 +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]: 1378 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]: 1377 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
@@ -249,13 +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]: 1378 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]: 1378 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

@@ -2,213 +2,213 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 2.0024518966674805,
-            "min": 2.0024518966674805,
-            "max": 2.840315580368042,
-            "count": 5
+            "value": 0.862381637096405,
+            "min": 0.8137264847755432,
+            "max": 2.8540990352630615,
+            "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 20441.029296875,
-            "min": 20441.029296875,
-            "max": 28993.94140625,
-            "count": 5
+            "value": 8196.0751953125,
+            "min": 7805.2646484375,
+            "max": 29134.642578125,
+            "count": 20
         },
         "SnowballTarget.Step.mean": {
-            "value": 49936.0,
+            "value": 199984.0,
             "min": 9952.0,
-            "max": 49936.0,
-            "count": 5
+            "max": 199984.0,
+            "count": 20
         },
         "SnowballTarget.Step.sum": {
-            "value": 49936.0,
+            "value": 199984.0,
             "min": 9952.0,
-            "max": 49936.0,
-            "count": 5
+            "max": 199984.0,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 5.122859001159668,
-            "min": 0.4962412118911743,
-            "max": 5.122859001159668,
-            "count": 5
+            "value": 13.044581413269043,
+            "min": 0.3387218713760376,
+            "max": 13.055965423583984,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 993.8346557617188,
-            "min": 96.27079772949219,
-            "max": 993.8346557617188,
-            "count": 5
+            "value": 2543.693359375,
+            "min": 65.71204376220703,
+            "max": 2670.221435546875,
+            "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06665322676545818,
-            "min": 0.06562543280009528,
-            "max": 0.06875504208899871,
-            "count": 5
+            "value": 0.06754262566349045,
+            "min": 0.06235437081201121,
+            "max": 0.07732099537636661,
+            "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2666129070618327,
-            "min": 0.2644840449222601,
-            "max": 0.34377521044499354,
-            "count": 5
+            "value": 0.2701705026539618,
+            "min": 0.25226799421487195,
+            "max": 0.37251804858861565,
+            "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.2711929982053298,
-            "min": 0.1577339629099394,
-            "max": 0.2969021650359911,
-            "count": 5
+            "value": 0.19701581755105185,
+            "min": 0.11408315048845229,
+            "max": 0.29254157104912926,
+            "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 1.0847719928213193,
-            "min": 0.6309358516397576,
-            "max": 1.231872004621169,
-            "count": 5
+            "value": 0.7880632702042074,
+            "min": 0.45633260195380915,
+            "max": 1.4627078552456463,
+            "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 0.000232482022506,
-            "min": 0.000232482022506,
+            "value": 8.082097306000005e-06,
+            "min": 8.082097306000005e-06,
             "max": 0.000291882002706,
-            "count": 5
+            "count": 20
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 0.000929928090024,
-            "min": 0.000929928090024,
+            "value": 3.232838922400002e-05,
+            "min": 3.232838922400002e-05,
             "max": 0.00138516003828,
-            "count": 5
+            "count": 20
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.17749400000000004,
-            "min": 0.17749400000000004,
+            "value": 0.10269400000000001,
+            "min": 0.10269400000000001,
             "max": 0.19729400000000002,
-            "count": 5
+            "count": 20
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.7099760000000002,
-            "min": 0.7099760000000002,
+            "value": 0.41077600000000003,
+            "min": 0.41077600000000003,
             "max": 0.96172,
-            "count": 5
+            "count": 20
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0038769506000000003,
-            "min": 0.0038769506000000003,
+            "value": 0.0001444306000000001,
+            "min": 0.0001444306000000001,
             "max": 0.0048649706,
-            "count": 5
+            "count": 20
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.015507802400000001,
-            "min": 0.015507802400000001,
+            "value": 0.0005777224000000004,
+            "min": 0.0005777224000000004,
             "max": 0.023089828,
-            "count": 5
+            "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 5
+            "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
             "value": 8756.0,
             "min": 8756.0,
             "max": 10945.0,
-            "count": 5
+            "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 13.818181818181818,
-            "min": 4.113636363636363,
-            "max": 13.818181818181818,
-            "count": 5
+            "value": 25.636363636363637,
+            "min": 3.1136363636363638,
+            "max": 25.727272727272727,
+            "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 608.0,
-            "min": 181.0,
-            "max": 617.0,
-            "count": 5
+            "value": 1128.0,
+            "min": 137.0,
+            "max": 1415.0,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 13.818181818181818,
-            "min": 4.113636363636363,
-            "max": 13.818181818181818,
-            "count": 5
+            "value": 25.636363636363637,
+            "min": 3.1136363636363638,
+            "max": 25.727272727272727,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 608.0,
-            "min": 181.0,
-            "max": 617.0,
-            "count": 5
+            "value": 1128.0,
+            "min": 137.0,
+            "max": 1415.0,
+            "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 5
+            "count": 20
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 5
+            "count": 20
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1765313448",
+        "start_time_seconds": "1765596680",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics",
-        "mlagents_version": "1.1.0",
-        "mlagents_envs_version": "1.1.0",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./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": "2.9.1+cu128",
+        "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1765313562"
+        "end_time_seconds": "1765597122"
     },
-    "total": 113.98827209899991,
+    "total": 442.5386485309999,
     "count": 1,
-    "self": 0.47679799399998046,
+    "self": 0.43190271099979327,
     "children": {
         "run_training.setup": {
-            "total": 0.026548259000037433,
+            "total": 0.02664396900001975,
             "count": 1,
-            "self": 0.026548259000037433
+            "self": 0.02664396900001975
         },
         "TrainerController.start_learning": {
-            "total": 113.4849258459999,
+            "total": 442.0801018510001,
             "count": 1,
-            "self": 0.09543491099520907,
+            "self": 0.367131559992913,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.675724683999988,
+                    "total": 3.37301025499994,
                     "count": 1,
-                    "self": 3.675724683999988
+                    "self": 3.37301025499994
                 },
                 "TrainerController.advance": {
-                    "total": 109.68492115600475,
-                    "count": 4592,
-                    "self": 0.10683829900744968,
+                    "total": 438.26335806200734,
+                    "count": 18192,
+                    "self": 0.38037230798613564,
                     "children": {
                         "env_step": {
-                            "total": 79.99079243999336,
-                            "count": 4592,
-                            "self": 61.99460743797658,
+                            "total": 319.08165941401955,
+                            "count": 18192,
+                            "self": 250.46327713000846,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 17.94217196701129,
-                                    "count": 4592,
-                                    "self": 0.3296976550079762,
+                                    "total": 68.40137414000378,
+                                    "count": 18192,
+                                    "self": 1.287372039025854,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 17.612474312003314,
-                                            "count": 4592,
-                                            "self": 17.612474312003314
+                                            "total": 67.11400210097793,
+                                            "count": 18192,
+                                            "self": 67.11400210097793
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.05401303500548238,
-                                    "count": 4592,
+                                    "total": 0.21700814400730906,
+                                    "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 113.12851751201242,
-                                            "count": 4592,
+                                            "total": 440.4496590500029,
+                                            "count": 18192,
                                             "is_parallel": true,
-                                            "self": 58.567631793013334,
+                                            "self": 220.48415711400605,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0031165850000434148,
+                                                            "total": 0.0029147269999612035,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0016253419998975005,
+                                                            "self": 0.0015168979997497445,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014912430001459143,
+                                                                    "total": 0.001397829000211459,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014912430001459143
+                                                                    "self": 0.001397829000211459
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03607795800007807,
+                                                            "total": 0.03797151200001281,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006105020001996309,
+                                                            "self": 0.0008414720001610476,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003805490000559075,
+                                                                    "total": 0.0003986909999866839,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003805490000559075
+                                                                    "self": 0.0003986909999866839
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03320832999997947,
+                                                                    "total": 0.034690561999923375,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03320832999997947
+                                                                    "self": 0.034690561999923375
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018785769998430624,
+                                                                    "total": 0.0020407869999417017,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004025949999686418,
+                                                                    "self": 0.0003879629997527445,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014759819998744206,
+                                                                            "total": 0.0016528240001889571,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014759819998744206
+                                                                            "self": 0.0016528240001889571
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 54.56088571899909,
-                                                    "count": 4591,
+                                                    "total": 219.96550193599683,
+                                                    "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 2.567736763985522,
+                                                    "self": 10.41468327898167,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 1.4252797330047997,
-                                                            "count": 4591,
+                                                            "total": 5.683180562006555,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 1.4252797330047997
+                                                            "self": 5.683180562006555
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 41.30663292300619,
-                                                            "count": 4591,
+                                                            "total": 167.38735474800706,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 41.30663292300619
+                                                            "self": 167.38735474800706
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 9.261236299002576,
-                                                            "count": 4591,
+                                                            "total": 36.480283347001546,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 1.7437830719804879,
+                                                            "self": 6.602916233994961,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 7.517453227022088,
-                                                                    "count": 45910,
+                                                                    "total": 29.877367113006585,
+                                                                    "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 7.517453227022088
+                                                                    "self": 29.877367113006585
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 29.587290417003942,
-                            "count": 4592,
-                            "self": 0.114874456009602,
+                            "total": 118.80132634000165,
+                            "count": 18192,
+                            "self": 0.4594071530146948,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 6.7556094799945186,
-                                    "count": 4592,
-                                    "self": 6.7246087719945535,
+                                    "total": 26.237937183987697,
+                                    "count": 18192,
+                                    "self": 25.71182364798767,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.031000707999965016,
-                                            "count": 1,
-                                            "self": 0.031000707999965016
+                                            "total": 0.5261135360000253,
+                                            "count": 4,
+                                            "self": 0.5261135360000253
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 22.71680648099982,
-                                    "count": 22,
-                                    "self": 9.15645044999792,
+                                    "total": 92.10398200299926,
+                                    "count": 90,
+                                    "self": 38.16283905199896,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 13.560356031001902,
-                                            "count": 1119,
-                                            "self": 13.560356031001902
+                                            "total": 53.9411429510003,
+                                            "count": 4587,
+                                            "self": 53.9411429510003
                                         }
                                     }
                                 }
@@ -339,15 +339,20 @@
                         }
                     }
                 },
+                "trainer_threads": {
+                    "total": 1.160000010713702e-06,
+                    "count": 1,
+                    "self": 1.160000010713702e-06
+                },
                 "TrainerController._save_models": {
-                    "total": 0.02884509499995147,
+                    "total": 0.07660081399990304,
                     "count": 1,
-                    "self": 2.0384999970701756e-05,
+                    "self": 0.0007509699998990982,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.02882470999998077,
+                            "total": 0.07584984400000394,
                             "count": 1,
-                            "self": 0.02882470999998077
+                            "self": 0.07584984400000394
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,7 +1,65 @@
 {
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 15.909090909090908,
+                "creation_time": 1765596792.7048,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 24.818181818181817,
+                "creation_time": 1765596903.5343623,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 24.727272727272727,
+                "creation_time": 1765597013.7271621,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 26.272727272727273,
+                "creation_time": 1765597122.032703,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 26.272727272727273,
+                "creation_time": 1765597122.1202946,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 200112,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 26.272727272727273,
+            "creation_time": 1765597122.1202946,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+            ]
+        }
+    },
     "metadata": {
         "stats_format_version": "0.3.0",
-        "mlagents_version": "1.1.0",
-        "torch_version": "2.9.1+cu128"
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cu128"
     }
 }