Upload folder using huggingface_hub

README.md

@@ -29,7 +29,7 @@ tags:
   You can watch your agent **playing directly in your browser**
 
   1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
-  2. Step 1: Find your model_id: seynath/ppo-SnowballTarget
+  2. Step 1: Find your model_id: Matyji/ML-Agents-SnowballTarget
   3. Step 2: Select your *.nn /*.onnx file
   4. Click on Watch the agent play 👀
   

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e5ad8580fa59719a9b9e372fdeb5adff90d02de6b2623b39858f8ca67988289
-size 649740
+oid sha256:26d54f49cc7602b7f879407fcee87e7669118c539e199ce30b181e3616424c9b
+size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155cc66f55e2f69d62633d4211c9167c9074f172c9a0f4774ba0412a8b5ca12a
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bef98da3db937036ab627e1354eb73551baa9e09b1aca0edd3f85d46eaef37e
+size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d54f49cc7602b7f879407fcee87e7669118c539e199ce30b181e3616424c9b
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8cb31c9754b9de1cadbf37a975a4565ba966847071aa8ebe633c360f386e3f2
+size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d54f49cc7602b7f879407fcee87e7669118c539e199ce30b181e3616424c9b
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74d43d1c0e7dca6f533f4973dd073d61ebee18fd1d4fd2a46aa71714c93a9a78
+size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8c6466c295053594b866bf83f164a7fa6aeff22ba21e8d02d533d01a3256f33
+size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d3cb669851d3a2a067063969ac26beb12a1e6bf5a731ff6bdd642317636a96
+size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3591dd7f0f7ec4916739dbf502000e4eecf541ade229c9265286adc1defec377
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ef6c9eb6c60fd294d05d5135c39ee153ee80f8fa802b1c40ae739d28f7b04b
+size 3850000

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48aef1c329f31a2f0b1b8caf2051b626aacdffb161ab70a278310fb574223978
-size 1286389
+oid sha256:69bc48a30b65be613911fb9dd730abb58d7b6370f243d6f476864cae755cfaa8
+size 3849250

SnowballTarget/events.out.tfevents.1742739568.502cf0fb22bc.4885.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ced5296872d97b2ce0ea83c303abae841afeba77563c13f1f35c484ba2ee319
+size 28144

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": 50, "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": 200, "time_horizon": 64, "summary_freq": 100, "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}
+{"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

@@ -14,7 +14,7 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 50
+    checkpoint_interval: 50000
     network_settings:
       normalize: false
       hidden_units: 256
@@ -38,9 +38,9 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 200
+    max_steps: 200000
     time_horizon: 64
-    summary_freq: 100
+    summary_freq: 10000
     threaded: false
     self_play: null
     behavioral_cloning: null

run_logs/Player-0.log

@@ -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  0.279 seconds
+- Completed reload, in  0.090 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)
@@ -45,17 +45,15 @@ 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: 0.810874 ms
+UnloadTime: 0.747679 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.
-abort_threads: Failed aborting id: 0x7d20f3a4b640, 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]: 19 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
@@ -171,22 +169,22 @@ 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 45
     [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]: 20 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 4.9 MB
+      Peak Allocated memory 7.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 20 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 17.6 MB
+      Peak Allocated memory 17.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -200,7 +198,7 @@ Memory Statistics:
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
   Initial Block Size 2.0 MB
-  Used Block Count 1
+  Used Block Count 2
   Overflow Count (too large) 0
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -215,13 +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]: 17 frames, [64.0 KB-128.0 KB]: 3 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 3287 frames, [64.0 KB-128.0 KB]: 2171 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 KB
+      Peak Allocated memory 67.3 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 20 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
@@ -233,13 +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]: 20 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]: 19 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
@@ -251,13 +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]: 20 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]: 20 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

@@ -2,117 +2,213 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 2.8903346061706543,
-            "min": 2.8903346061706543,
-            "max": 2.8903346061706543,
-            "count": 1
+            "value": 0.7811824679374695,
+            "min": 0.7709082961082458,
+            "max": 2.8721606731414795,
+            "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 2034.7955322265625,
-            "min": 2034.7955322265625,
-            "max": 2034.7955322265625,
-            "count": 1
+            "value": 7424.3583984375,
+            "min": 7424.3583984375,
+            "max": 29319.015625,
+            "count": 20
         },
         "SnowballTarget.Step.mean": {
-            "value": 640.0,
-            "min": 64.0,
-            "max": 640.0,
-            "count": 7
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
         },
         "SnowballTarget.Step.sum": {
-            "value": 640.0,
-            "min": 64.0,
-            "max": 640.0,
-            "count": 7
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.11623887717723846,
-            "min": 0.10424119234085083,
-            "max": 0.1218389943242073,
-            "count": 7
+            "value": 11.972668647766113,
+            "min": 0.2813635468482971,
+            "max": 11.972668647766113,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 0.11623887717723846,
-            "min": 0.10606031864881516,
-            "max": 0.2436779886484146,
-            "count": 7
+            "value": 2334.67041015625,
+            "min": 54.58452606201172,
+            "max": 2420.564208984375,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06295659255988093,
+            "min": 0.060444064867196556,
+            "max": 0.07650350043025123,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.2518263702395237,
+            "min": 0.24177625946878623,
+            "max": 0.35741002059384136,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.17162585035696917,
+            "min": 0.1081036708646399,
+            "max": 0.26972815262920713,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.6865034014278767,
+            "min": 0.4324146834585596,
+            "max": 1.2929292040712692,
+            "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": 23.727272727272727,
+            "min": 3.159090909090909,
+            "max": 23.727272727272727,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1044.0,
+            "min": 139.0,
+            "max": 1279.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 23.727272727272727,
+            "min": 3.159090909090909,
+            "max": 23.727272727272727,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1044.0,
+            "min": 139.0,
+            "max": 1279.0,
+            "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
-            "value": 0.0,
-            "min": 0.0,
+            "value": 1.0,
+            "min": 1.0,
             "max": 1.0,
-            "count": 7
+            "count": 20
         },
         "SnowballTarget.IsTraining.sum": {
-            "value": 0.0,
-            "min": 0.0,
+            "value": 1.0,
+            "min": 1.0,
             "max": 1.0,
-            "count": 7
+            "count": 20
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1766043657",
+        "start_time_seconds": "1742739567",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/root/miniconda/envs/mlagents/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=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",
+        "pytorch_version": "2.6.0+cu124",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1766043664"
+        "end_time_seconds": "1742740012"
     },
-    "total": 6.552861748999931,
+    "total": 444.4390376399999,
     "count": 1,
-    "self": 0.48545274499974767,
+    "self": 0.4359825959998034,
     "children": {
         "run_training.setup": {
-            "total": 0.029647306000015305,
+            "total": 0.023827851000078226,
             "count": 1,
-            "self": 0.029647306000015305
+            "self": 0.023827851000078226
         },
         "TrainerController.start_learning": {
-            "total": 6.037761698000168,
+            "total": 443.97922719300004,
             "count": 1,
-            "self": 0.0017854399995940184,
+            "self": 0.34946201698062396,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.64345822700011,
+                    "total": 3.0383297299999867,
                     "count": 1,
-                    "self": 3.64345822700011
+                    "self": 3.0383297299999867
                 },
                 "TrainerController.advance": {
-                    "total": 2.329971007000495,
-                    "count": 64,
-                    "self": 0.0017017419997955585,
+                    "total": 440.4473043080193,
+                    "count": 18192,
+                    "self": 0.3798192670158187,
                     "children": {
                         "env_step": {
-                            "total": 1.4308008210011849,
-                            "count": 64,
-                            "self": 0.9917202310018638,
+                            "total": 312.15114762900225,
+                            "count": 18192,
+                            "self": 238.14719357498393,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 0.438181040999325,
-                                    "count": 64,
-                                    "self": 0.006287398998438221,
+                                    "total": 73.79232831502759,
+                                    "count": 18192,
+                                    "self": 1.3050039680194914,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 0.43189364200088676,
-                                            "count": 64,
-                                            "self": 0.43189364200088676
+                                            "total": 72.4873243470081,
+                                            "count": 18192,
+                                            "self": 72.4873243470081
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.0008995489999961137,
-                                    "count": 64,
+                                    "total": 0.21162573899073323,
+                                    "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 5.102421936999917,
-                                            "count": 64,
+                                            "total": 442.2089642609967,
+                                            "count": 18192,
                                             "is_parallel": true,
-                                            "self": 4.272434992999479,
+                                            "self": 232.86567158598405,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -121,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.014340551000032065,
+                                                            "total": 0.00622745999999097,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.004239720000441594,
+                                                            "self": 0.00450486099975933,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.010100830999590471,
+                                                                    "total": 0.0017225990002316394,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.010100830999590471
+                                                                    "self": 0.0017225990002316394
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03908259700006056,
+                                                            "total": 0.03707721099999617,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006355920002079074,
+                                                            "self": 0.0006158880000839417,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00040146699984688894,
+                                                                    "total": 0.0004958510000960814,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00040146699984688894
+                                                                    "self": 0.0004958510000960814
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0339447310000196,
+                                                                    "total": 0.03397013499989043,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0339447310000196
+                                                                    "self": 0.03397013499989043
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.004100806999986162,
+                                                                    "total": 0.001995336999925712,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003637770003024343,
+                                                                    "self": 0.00037948799990772386,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0037370299996837275,
+                                                                            "total": 0.0016158490000179881,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0037370299996837275
+                                                                            "self": 0.0016158490000179881
                                                                         }
                                                                     }
                                                                 }
@@ -171,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 0.8299869440004386,
-                                                    "count": 63,
+                                                    "total": 209.34329267501266,
+                                                    "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 0.03678823800260034,
+                                                    "self": 9.995811815985007,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.02060778299892263,
-                                                            "count": 63,
+                                                            "total": 5.566330642999219,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.02060778299892263
+                                                            "self": 5.566330642999219
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 0.6452412069995717,
-                                                            "count": 63,
+                                                            "total": 160.63367244102074,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.6452412069995717
+                                                            "self": 160.63367244102074
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 0.12734971599934397,
-                                                            "count": 63,
+                                                            "total": 33.1474777750077,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.022938641002156146,
+                                                            "self": 6.0218651190027686,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.10441107499718782,
-                                                                    "count": 630,
+                                                                    "total": 27.125612656004932,
+                                                                    "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 0.10441107499718782
+                                                                    "self": 27.125612656004932
                                                                 }
                                                             }
                                                         }
@@ -211,19 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 0.8974684439995144,
-                            "count": 64,
-                            "self": 0.001835421001260329,
+                            "total": 127.91633741200121,
+                            "count": 18192,
+                            "self": 0.44787858800191316,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 0.8956330229982541,
-                                    "count": 64,
-                                    "self": 0.17742453399841907,
+                                    "total": 27.95624848699913,
+                                    "count": 18192,
+                                    "self": 27.32192759799932,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.718208488999835,
-                                            "count": 10,
-                                            "self": 0.718208488999835
+                                            "total": 0.6343208889998095,
+                                            "count": 4,
+                                            "self": 0.6343208889998095
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 99.51221033700017,
+                                    "count": 90,
+                                    "self": 41.13690210599998,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 58.37530823100019,
+                                            "count": 4587,
+                                            "self": 58.37530823100019
                                         }
                                     }
                                 }
@@ -232,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.679999948275508e-07,
+                    "total": 1.368000084767118e-06,
                     "count": 1,
-                    "self": 9.679999948275508e-07
+                    "self": 1.368000084767118e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.06254605599997376,
+                    "total": 0.14412977000006322,
                     "count": 1,
-                    "self": 0.0007164069997998013,
+                    "self": 0.0010588190000362374,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.06182964900017396,
+                            "total": 0.14307095100002698,
                             "count": 1,
-                            "self": 0.06182964900017396
+                            "self": 0.14307095100002698
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,109 +2,64 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 128,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-128.onnx",
-                "reward": null,
-                "creation_time": 1766043663.1486273,
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 14.272727272727273,
+                "creation_time": 1742739681.556784,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-128.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
-                "steps": 192,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-192.onnx",
-                "reward": null,
-                "creation_time": 1766043663.221023,
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 21.09090909090909,
+                "creation_time": 1742739790.4955256,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-192.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
             },
             {
-                "steps": 256,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-256.onnx",
-                "reward": null,
-                "creation_time": 1766043663.2919605,
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 23.727272727272727,
+                "creation_time": 1742739900.630838,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-256.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
-                "steps": 320,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-320.onnx",
-                "reward": null,
-                "creation_time": 1766043663.360498,
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 23.636363636363637,
+                "creation_time": 1742740011.649374,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-320.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
-                "steps": 384,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-384.onnx",
-                "reward": null,
-                "creation_time": 1766043663.4418378,
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 23.636363636363637,
+                "creation_time": 1742740011.8161774,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-384.pt"
-                ]
-            },
-            {
-                "steps": 448,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-448.onnx",
-                "reward": null,
-                "creation_time": 1766043663.5098684,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-448.pt"
-                ]
-            },
-            {
-                "steps": 512,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-512.onnx",
-                "reward": null,
-                "creation_time": 1766043663.5825038,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-512.pt"
-                ]
-            },
-            {
-                "steps": 576,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-576.onnx",
-                "reward": null,
-                "creation_time": 1766043663.6539183,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-576.pt"
-                ]
-            },
-            {
-                "steps": 640,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-640.onnx",
-                "reward": null,
-                "creation_time": 1766043663.7216976,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-640.pt"
-                ]
-            },
-            {
-                "steps": 704,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-704.onnx",
-                "reward": null,
-                "creation_time": 1766043663.792489,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-704.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 704,
+            "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1766043663.792489,
+            "reward": 23.636363636363637,
+            "creation_time": 1742740011.8161774,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-704.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },
     "metadata": {
         "stats_format_version": "0.3.0",
         "mlagents_version": "1.2.0.dev0",
-        "torch_version": "2.8.0+cu128"
+        "torch_version": "2.6.0+cu124"
     }
 }