CPU trained

README.md

@@ -14,16 +14,22 @@ tags:
   ## Usage (with ML-Agents)
   The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
 
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
   ### Resume the training
   ```bash
   mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
   ```
 
-  ### Watch Agent play
-  You can watch the agent **playing directly in browser**
+  ### Watch your Agent play
+  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 the model_id: elliemci/ppo-Snowball-Target
-  3. Step 2: Select *.nn /*.onnx file
+  2. Step 1: Find your model_id: elliemci/ppo-Snowball-Target
+  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:cfb2da1aeb5f47a7bd3901b753d46f36802405e31688c5c9fa653b4c9425db7e
-size 649740
+oid sha256:937b3ba4dbd003d1f63e19fee42ce918fd8686f3d8fef2b15c94ed619ba595ba
+size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc24daae263b21ec5063fb54d7d029ef194f8d943f57ded7e72438f62a8d1765
+oid sha256:7e9d203eed71d916d59b329b724452e57809e549f7c4889b7b3c71e60d7c0844
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:476c6cd3d6e71dfdef4ce860944077e17e4972d9afcbe2a92b557d1d6f6226c8
+oid sha256:15a2dd3c08c785579f15e584a37980328fa0378acc72d74d4d4140bbff3bf8de
 size 3849604

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a18275a641c2c73e841e20d58968923684d8e1f47c8293fe984f21a0ddcc8fb4
+oid sha256:937b3ba4dbd003d1f63e19fee42ce918fd8686f3d8fef2b15c94ed619ba595ba
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70b40ca485a3b6a8741253c65359ae2fdf10d5676e92bd93a6a92512e4560d82
+oid sha256:70f78af91c97a47a2a284456248103336c9fe7932a62031f97b90cb127c6bd2d
 size 3849604

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a18275a641c2c73e841e20d58968923684d8e1f47c8293fe984f21a0ddcc8fb4
+oid sha256:937b3ba4dbd003d1f63e19fee42ce918fd8686f3d8fef2b15c94ed619ba595ba
 size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec7018ea462fe4c5c2d3bb838e4df64c925308aa31e1bf4e4cab799dc59d14c6
+oid sha256:2d66be04b6e90cd261339ba6e9e10916bb3d4487a4191eaa78ac2d688d1ae3da
 size 3849604

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14a63806fd83979dbaae2512042edc66e383411d8bb03fa14d9fb4c84318a3c4
+oid sha256:bbe5622eaae2a22f5ee7d13fdd72a4c038e45d899b65b082939d9a2773935678
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1622bd2d94fdb7ce5472c93b76337f689703c3308d9ec0397c2a6c4e7017f061
+oid sha256:572b1aed8620f56c95b3c0a48205657f9274aeb2650c2e45c5e04ff997c8e4af
 size 3849527

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:983b9c0f5d99987fbfd28cdfbbb84238a56f9250285bff2bbb1014cac132be40
+oid sha256:001bb034aec6e6fbe56ac775e75778b4496243d13c039278f5da9326d0af92e3
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c67c8a0e34437392e4cbc50f40d630365dbca719029b0e700debe3bfe8e8484c
+oid sha256:173896f3dc4cab7aedb06750b1c6ffefde7b22f42a18d0a62c17d0167b83b1c0
 size 3849527

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d3522100021019af087b783d058592a2df0ace90d175940e52fb36489438dd
-size 1286389
+oid sha256:3232f8f0c485c96cafe742213b1a0db75b0992816adc135710741294fd63f548
+size 3848757

SnowballTarget/events.out.tfevents.1759617282.222bc6b1bac0.13994.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a2cee8d3df7189542e335dc45f8cb8a5f73e92560acfe89f3edfb5b1d505d8
+size 28461

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0005, "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": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "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": true, "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": "cpu"}, "debug": false}

configuration.yaml

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
-      learning_rate: 0.0005
+      learning_rate: 0.0003
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 500000
+    max_steps: 200000
     time_horizon: 64
     summary_freq: 10000
     threaded: true
@@ -75,5 +75,5 @@ checkpoint_settings:
   inference: false
   results_dir: results
 torch_settings:
-  device: null
+  device: cpu
 debug: false

run_logs/Player-0.log

@@ -1,9 +1,12 @@
-Mono path[0] = '/content/drive/MyDrive/ColabNotebooks/DeepRL/UnityMLAgents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
-Mono config path = '/content/drive/MyDrive/ColabNotebooks/DeepRL/UnityMLAgents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Mono path[0] = '/content/drive/MyDrive/ColabNotebooks/DeepRL/unity_ml_agents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/drive/MyDrive/ColabNotebooks/DeepRL/unity_ml_agents/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/drive/MyDrive/ColabNotebooks/DeepRL/UnityMLAgents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+[Subsystems] Discovering subsystems at path /content/drive/MyDrive/ColabNotebooks/DeepRL/unity_ml_agents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
@@ -31,7 +34,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  1.620 seconds
+- Completed reload, in  6.577 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +45,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 1.009586 ms
+UnloadTime: 1.350994 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -50,7 +53,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 78 frames, [16.0 KB-32.0 KB]: 1 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5371 frames, [16.0 KB-32.0 KB]: 91 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
@@ -58,7 +61,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 298 B
+      Peak Allocated Bytes 302 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
@@ -166,22 +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 40
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 80 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5463 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.3 MB
+      Peak Allocated memory 6.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 80 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.6 MB
+      Peak Allocated memory 17.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -210,13 +213,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 73 frames, [64.0 KB-128.0 KB]: 7 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5122 frames, [64.0 KB-128.0 KB]: 341 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 KB
+      Peak Allocated memory 66.4 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 80 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -228,13 +231,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 80 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5463 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]: 79 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -246,13 +249,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 80 frames
+      Peak usage frame count: [0-1.0 KB]: 5463 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]: 80 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5463 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": 0.8864038586616516,
+            "min": 0.8864038586616516,
+            "max": 2.871638536453247,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 8482.884765625,
+            "min": 8482.884765625,
+            "max": 29440.0390625,
+            "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": 13.26480770111084,
+            "min": 0.42416539788246155,
+            "max": 13.26480770111084,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2586.637451171875,
+            "min": 82.2880859375,
+            "max": 2689.9091796875,
+            "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.Losses.PolicyLoss.mean": {
+            "value": 0.07335391956211441,
+            "min": 0.06281399575504931,
+            "max": 0.07335391956211441,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.29341567824845766,
+            "min": 0.2582186224620576,
+            "max": 0.35503686174257276,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.18263008303063755,
+            "min": 0.10906449994688634,
+            "max": 0.2709916849784991,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7305203321225502,
+            "min": 0.43625799978754537,
+            "max": 1.3486190797651516,
+            "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.CumulativeReward.mean": {
+            "value": 26.113636363636363,
+            "min": 3.1818181818181817,
+            "max": 26.113636363636363,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1149.0,
+            "min": 140.0,
+            "max": 1432.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.113636363636363,
+            "min": 3.1818181818181817,
+            "max": 26.113636363636363,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1149.0,
+            "min": 140.0,
+            "max": 1432.0,
+            "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": "1759538802",
+        "start_time_seconds": "1759617257",
         "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]",
-        "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",
+        "command_line_arguments": "/content/drive/MyDrive/ColabNotebooks/DeepRL/unity_ml_agents/ml-agents/ml-agents/mlagents/trainers/learn.py config/ppo/SnowballTarget.yaml --env=training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --torch-device cpu",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1759538902"
+        "end_time_seconds": "1759617977"
     },
-    "total": 100.7819420199994,
+    "total": 720.7424643029999,
     "count": 1,
-    "self": 0.38623908899899106,
+    "self": 3.04285879400004,
     "children": {
         "run_training.setup": {
-            "total": 0.036189582000588416,
+            "total": 0.5054450689999612,
             "count": 1,
-            "self": 0.036189582000588416
+            "self": 0.5054450689999612
         },
         "TrainerController.start_learning": {
-            "total": 100.35951334899983,
+            "total": 717.1941604399999,
             "count": 1,
-            "self": 0.009456181973291677,
+            "self": 0.8967849949854099,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.9558861869991233,
+                    "total": 27.97904822999999,
                     "count": 1,
-                    "self": 3.9558861869991233
+                    "self": 27.97904822999999
                 },
                 "TrainerController.advance": {
-                    "total": 96.1951234860262,
-                    "count": 264,
-                    "self": 0.004127066018554615,
+                    "total": 688.1857627680142,
+                    "count": 18207,
+                    "self": 0.45647151800312713,
                     "children": {
                         "env_step": {
-                            "total": 96.19099642000765,
-                            "count": 264,
-                            "self": 94.18451913301215,
+                            "total": 687.7292912500111,
+                            "count": 18207,
+                            "self": 551.11223637699,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 2.002232754985016,
-                                    "count": 264,
-                                    "self": 0.022674629974062555,
+                                    "total": 136.16034631501043,
+                                    "count": 18207,
+                                    "self": 2.495420341008412,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 1.9795581250109535,
-                                            "count": 264,
-                                            "self": 1.9795581250109535
+                                            "total": 133.66492597400202,
+                                            "count": 18207,
+                                            "self": 133.66492597400202
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.004244532010488911,
-                                    "count": 264,
+                                    "total": 0.45670855801063226,
+                                    "count": 18207,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 11.116804798002704,
-                                            "count": 264,
+                                            "total": 713.8301045720245,
+                                            "count": 18207,
                                             "is_parallel": true,
-                                            "self": 6.73045409100996,
+                                            "self": 323.0260147560148,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -71,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002119500999469892,
+                                                            "total": 0.00796136100007061,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007359600022027735,
+                                                            "self": 0.005653170000641694,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013835409972671187,
+                                                                    "total": 0.0023081909994289163,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013835409972671187
+                                                                    "self": 0.0023081909994289163
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04008158799842931,
+                                                            "total": 0.04777077600010671,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007188429990492295,
+                                                            "self": 0.0007130789999791887,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00040681100108486135,
+                                                                    "total": 0.0004538260000117589,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00040681100108486135
+                                                                    "self": 0.0004538260000117589
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03693036699951335,
+                                                                    "total": 0.04415833500024746,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03693036699951335
+                                                                    "self": 0.04415833500024746
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002025566998781869,
+                                                                    "total": 0.002445535999868298,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000411769997299416,
+                                                                    "self": 0.000475898999866331,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0016137970014824532,
+                                                                            "total": 0.001969637000001967,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0016137970014824532
+                                                                            "self": 0.001969637000001967
                                                                         }
                                                                     }
                                                                 }
@@ -121,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 4.386350706992744,
-                                                    "count": 263,
+                                                    "total": 390.80408981600976,
+                                                    "count": 18206,
                                                     "is_parallel": true,
-                                                    "self": 0.16981740100527531,
+                                                    "self": 16.378712090016506,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.09151577699412883,
-                                                            "count": 263,
+                                                            "total": 8.630475927984207,
+                                                            "count": 18206,
                                                             "is_parallel": true,
-                                                            "self": 0.09151577699412883
+                                                            "self": 8.630475927984207
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 3.381234082982701,
-                                                            "count": 263,
+                                                            "total": 304.2668674440056,
+                                                            "count": 18206,
                                                             "is_parallel": true,
-                                                            "self": 3.381234082982701
+                                                            "self": 304.2668674440056
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 0.7437834460106387,
-                                                            "count": 263,
+                                                            "total": 61.528034354003466,
+                                                            "count": 18206,
                                                             "is_parallel": true,
-                                                            "self": 0.1480902439889178,
+                                                            "self": 11.493632857002012,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.5956932020217209,
-                                                                    "count": 2630,
+                                                                    "total": 50.034401497001454,
+                                                                    "count": 182060,
                                                                     "is_parallel": true,
-                                                                    "self": 0.5956932020217209
+                                                                    "self": 50.034401497001454
                                                                 }
                                                             }
                                                         }
@@ -163,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.0016189200014196103,
+                    "total": 0.00013421300036497996,
                     "count": 1,
-                    "self": 0.0016189200014196103,
+                    "self": 0.00013421300036497996,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -174,28 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 5.538244231085628,
-                                    "count": 11257,
+                                    "total": 682.5432780908368,
+                                    "count": 582195,
                                     "is_parallel": true,
-                                    "self": 0.21920331808905757,
+                                    "self": 15.422843784749148,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 4.897417552996558,
-                                            "count": 11257,
+                                            "total": 370.06148500908785,
+                                            "count": 582195,
                                             "is_parallel": true,
-                                            "self": 4.897417552996558
+                                            "self": 368.71366196308827,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 1.3478230459995757,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 1.3478230459995757
+                                                }
+                                            }
                                         },
                                         "_update_policy": {
-                                            "total": 0.4216233600000123,
-                                            "count": 1,
+                                            "total": 297.0589492969998,
+                                            "count": 90,
                                             "is_parallel": true,
-                                            "self": 0.4062999290017615,
+                                            "self": 63.11306371699675,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 0.015323430998250842,
-                                                    "count": 1,
+                                                    "total": 233.94588558000305,
+                                                    "count": 4587,
                                                     "is_parallel": true,
-                                                    "self": 0.015323430998250842
+                                                    "self": 233.94588558000305
                                                 }
                                             }
                                         }
@@ -206,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.19742857399978675,
+                    "total": 0.13243023399991216,
                     "count": 1,
-                    "self": 0.010422376999486005,
+                    "self": 0.013348662999760563,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.18700619700030074,
+                            "total": 0.1190815710001516,
                             "count": 1,
-                            "self": 0.18700619700030074
+                            "self": 0.1190815710001516
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,58 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 2112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2112.onnx",
-                "reward": null,
-                "creation_time": 1759538902.4298677,
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 14.090909090909092,
+                "creation_time": 1759617455.0387928,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-2112.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 22.90909090909091,
+                "creation_time": 1759617633.4812636,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 25.363636363636363,
+                "creation_time": 1759617804.8444421,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.09090909090909,
+                "creation_time": 1759617974.6280048,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 25.09090909090909,
+                "creation_time": 1759617974.7832618,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2112,
+            "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1759538902.4298677,
+            "reward": 25.09090909090909,
+            "creation_time": 1759617974.7832618,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-2112.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },