Second test run

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5508dfd368f171b8590444abc0d2a8c500f0c49354cc1189efb2ae8dadf527e
-size 649740
+oid sha256:1f580a5992f56c1e8de42cd01cda6bcb0fda08511f39b0aa98f9153980596191
+size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52b8f6bd49d6a7d809e831de44636a9750e97e23bbe7931599b796930c9b843a
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db4864998d8456a03f0bbf9c3838f8c357372e65ae23b13f72e39bfd0dc0f38b
+size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f580a5992f56c1e8de42cd01cda6bcb0fda08511f39b0aa98f9153980596191
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86b15567138d6ebad2d7445d1608d91a72bcfcf3c60bd58426ab20428c4df9e
+size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f580a5992f56c1e8de42cd01cda6bcb0fda08511f39b0aa98f9153980596191
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a021846882f117370220164beb78c8a9d3f6021268ae60f0cd75e6a06d9a76
+size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316a51cde7757cdfbccddcdfdbf7b3b289b88672e4b7dd5b148866c4d654ead2
+size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fdff584e500b20ee55939b34c92ef75db3f451f462e1f76becc1e31037da87f
+size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44528a38867a871672d29ad5246efc8fe0ef8b84ff47f9bac15e16390c7268fd
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268a24c57704d07c28fa9a263016c3d2832f8d6a4d308c8eac1c483d1a07f993
+size 3850000

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8309781577c8a1a20d2cfd4e418d380cff73eb78272da7f583df436b4f432847
-size 1285986
+oid sha256:69201188f6ca42051ca58ab0b6ba47eab55b18a017b9382e7162fd99efba8319
+size 3849250

SnowballTarget/events.out.tfevents.1737245877.1a82401c6dd0.84.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e9dd0ffe1989214a2b069bcce99560fcf845f4a34a8d5e008316c8eeedc368
+size 23572

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": true, "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}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 2048, "learning_rate": 0.001, "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": "SnowballTarget2", "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

@@ -3,9 +3,9 @@ behaviors:
   SnowballTarget:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 128
+      batch_size: 256
       buffer_size: 2048
-      learning_rate: 0.0003
+      learning_rate: 0.001
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
@@ -41,7 +41,7 @@ behaviors:
     max_steps: 200000
     time_horizon: 64
     summary_freq: 10000
-    threaded: true
+    threaded: false
     self_play: null
     behavioral_cloning: null
 env_settings:
@@ -66,7 +66,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTarget2
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,12 @@
-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'
+Mono path[0] = '/kaggle/working/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/kaggle/working/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
+[Subsystems] Discovering subsystems at path /kaggle/working/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  0.096 seconds
+- Completed reload, in  0.093 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,15 +45,19 @@ 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: 0.689949 ms
+UnloadTime: 0.684856 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.
+Setting up 2 worker threads for Enlighten.
+abort_threads: Failed aborting id: 0x7a7bc18fd640, mono_thread_manage will ignore it
+
+abort_threads: Failed aborting id: 0x7a7bc1afe640, mono_thread_manage will ignore it
+
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 38 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 +65,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 198 B
+      Peak Allocated Bytes 212 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
@@ -103,7 +107,7 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_EnlightenWorker]
+    [ALLOC_TEMP_EnlightenWorker] x 2
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
@@ -128,7 +132,7 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 3
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
@@ -143,12 +147,22 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 11]
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 3]
+    [ALLOC_TEMP_Background Job.Worker 11]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -169,22 +183,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 28
+  Peak main deferred allocation count 37
     [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]: 39 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 4.8 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]: 39 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 17.8 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
@@ -213,13 +227,13 @@ 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]: 36 frames, [64.0 KB-128.0 KB]: 3 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4821 frames, [64.0 KB-128.0 KB]: 637 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 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]: 39 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 +245,13 @@ 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]: 39 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]: 38 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 +263,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 39 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]: 39 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": 0.7578401565551758,
+            "min": 0.7578401565551758,
+            "max": 2.8495936393737793,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7202.5126953125,
+            "min": 7202.5126953125,
+            "max": 29088.65234375,
+            "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": 13.306885719299316,
+            "min": 0.5077546238899231,
+            "max": 13.497345924377441,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2594.8427734375,
+            "min": 98.50440216064453,
+            "max": 2752.75,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.043117407193979794,
+            "min": 0.041890770931180064,
+            "max": 0.05512676508321117,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.17246962877591918,
+            "min": 0.16756308372472026,
+            "max": 0.2595114825120011,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.1955135907046497,
+            "min": 0.1359500007238239,
+            "max": 0.3003390124067664,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7820543628185987,
+            "min": 0.5438000028952956,
+            "max": 1.3857900959750016,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 2.694009730600002e-05,
+            "min": 2.694009730600002e-05,
+            "max": 0.000972940002706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 0.00010776038922400007,
+            "min": 0.00010776038922400007,
+            "max": 0.004617200038280001,
+            "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": 0.9617200000000001,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.00014443060000000012,
+            "min": 0.00014443060000000012,
+            "max": 0.0048649706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005777224000000005,
+            "min": 0.0005777224000000005,
+            "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": 26.045454545454547,
+            "min": 3.8181818181818183,
+            "max": 27.15909090909091,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1146.0,
+            "min": 168.0,
+            "max": 1442.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.045454545454547,
+            "min": 3.8181818181818183,
+            "max": 27.15909090909091,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1146.0,
+            "min": 168.0,
+            "max": 1442.0,
+            "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": "1737243332",
+        "start_time_seconds": "1737245876",
         "python_version": "3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
-        "pytorch_version": "2.5.1+cu124",
+        "pytorch_version": "2.5.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1737244344"
+        "end_time_seconds": "1737246234"
     },
-    "total": 1012.1962585640001,
+    "total": 358.2258431539999,
     "count": 1,
-    "self": 0.01987448900013078,
+    "self": 0.3292246050000358,
     "children": {
         "run_training.setup": {
-            "total": 0.019866056999944703,
+            "total": 0.08340822799982561,
             "count": 1,
-            "self": 0.019866056999944703
+            "self": 0.08340822799982561
         },
         "TrainerController.start_learning": {
-            "total": 1012.156518018,
+            "total": 357.81321032100004,
             "count": 1,
-            "self": 0.0036341910008559353,
+            "self": 0.3241159759841139,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.4223916670000563,
+                    "total": 4.709884568999769,
                     "count": 1,
-                    "self": 2.4223916670000563
+                    "self": 4.709884568999769
                 },
                 "TrainerController.advance": {
-                    "total": 1009.3643103539991,
-                    "count": 128,
-                    "self": 0.0017041929970673664,
+                    "total": 352.6907825740159,
+                    "count": 18192,
+                    "self": 0.34657970504622426,
                     "children": {
                         "env_step": {
-                            "total": 1009.3626061610021,
-                            "count": 128,
-                            "self": 1008.3232561970012,
+                            "total": 265.89916335997304,
+                            "count": 18192,
+                            "self": 200.5090012449673,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 1.0375915400004487,
-                                    "count": 128,
-                                    "self": 0.009806885002035415,
+                                    "total": 65.18958782399386,
+                                    "count": 18192,
+                                    "self": 1.1350779470126326,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 1.0277846549984133,
-                                            "count": 128,
-                                            "self": 1.0277846549984133
+                                            "total": 64.05450987698123,
+                                            "count": 18192,
+                                            "self": 64.05450987698123
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.0017584240003998275,
-                                    "count": 128,
+                                    "total": 0.20057429101188973,
+                                    "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 5.255466324000963,
-                                            "count": 128,
+                                            "total": 357.07193339096693,
+                                            "count": 18192,
                                             "is_parallel": true,
-                                            "self": 3.7409391040016544,
+                                            "self": 180.6356780869387,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -71,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005145967999851564,
+                                                            "total": 0.002237651000086771,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003284711000333118,
+                                                            "self": 0.0006449709999287734,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0018612569995184458,
+                                                                    "total": 0.0015926800001579977,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0018612569995184458
+                                                                    "self": 0.0015926800001579977
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03652428400005192,
+                                                            "total": 0.027012511000066297,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005666550002842996,
+                                                            "self": 0.00041847700003927457,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004108439998162794,
+                                                                    "total": 0.000266099000327813,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004108439998162794
+                                                                    "self": 0.000266099000327813
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.033536563999859936,
+                                                                    "total": 0.025165166999613575,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.033536563999859936
+                                                                    "self": 0.025165166999613575
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0020102210000914056,
+                                                                    "total": 0.0011627680000856344,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003749050003989396,
+                                                                    "self": 0.00024115799942592275,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001635315999692466,
+                                                                            "total": 0.0009216100006597117,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001635315999692466
+                                                                            "self": 0.0009216100006597117
                                                                         }
                                                                     }
                                                                 }
@@ -121,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1.5145272199993087,
-                                                    "count": 127,
+                                                    "total": 176.43625530402824,
+                                                    "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 0.06787295300136975,
+                                                    "self": 7.640120969095278,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.0390016719986761,
-                                                            "count": 127,
+                                                            "total": 4.085226885965767,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.0390016719986761
+                                                            "self": 4.085226885965767
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1.1906287290009914,
-                                                            "count": 127,
+                                                            "total": 139.61412439696232,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 1.1906287290009914
+                                                            "self": 139.61412439696232
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 0.2170238659982715,
-                                                            "count": 127,
+                                                            "total": 25.096783052004866,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.04009542199810312,
+                                                            "self": 4.764068768921788,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.17692844400016838,
-                                                                    "count": 1270,
+                                                                    "total": 20.332714283083078,
+                                                                    "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 0.17692844400016838
+                                                                    "self": 20.332714283083078
                                                                 }
                                                             }
                                                         }
@@ -159,18 +305,54 @@
                                     }
                                 }
                             }
+                        },
+                        "trainer_advance": {
+                            "total": 86.44503950899662,
+                            "count": 18192,
+                            "self": 0.3822299280068364,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 25.07527838098804,
+                                    "count": 18192,
+                                    "self": 24.657987443987622,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.4172909370004163,
+                                            "count": 4,
+                                            "self": 0.4172909370004163
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 60.98753120000174,
+                                    "count": 90,
+                                    "self": 34.6922201549969,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 26.295311045004837,
+                                            "count": 2160,
+                                            "self": 26.295311045004837
+                                        }
+                                    }
+                                }
+                            }
                         }
                     }
                 },
+                "trainer_threads": {
+                    "total": 8.609999895270448e-07,
+                    "count": 1,
+                    "self": 8.609999895270448e-07
+                },
                 "TrainerController._save_models": {
-                    "total": 0.36618180599998595,
+                    "total": 0.0884263410002859,
                     "count": 1,
-                    "self": 0.0012529530004030676,
+                    "self": 0.0009129190002568066,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.3649288529995829,
+                            "total": 0.0875134220000291,
                             "count": 1,
-                            "self": 0.3649288529995829
+                            "self": 0.0875134220000291
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,28 +2,64 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 64,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-64.onnx",
-                "reward": null,
-                "creation_time": 1737244344.6745977,
+                "steps": 49936,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 15.818181818181818,
+                "creation_time": 1737245970.142414,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-64.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 22.636363636363637,
+                "creation_time": 1737246058.1037786,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 25.90909090909091,
+                "creation_time": 1737246147.1103303,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 26.545454545454547,
+                "creation_time": 1737246234.3439865,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 26.545454545454547,
+                "creation_time": 1737246234.4432325,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 64,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1737244344.6745977,
+            "steps": 200112,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 26.545454545454547,
+            "creation_time": 1737246234.4432325,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-64.pt"
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },
     "metadata": {
         "stats_format_version": "0.3.0",
         "mlagents_version": "1.2.0.dev0",
-        "torch_version": "2.5.1+cu124"
+        "torch_version": "2.5.1+cu121"
     }
 }