Unit 5 SnowballTarget

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SnowballTarget
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SnowballTarget
+---
+
+  # **ppo** Agent playing **SnowballTarget**
+  This is a trained model of a **ppo** agent playing **SnowballTarget**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+
+  ## 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 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 your model_id: Chiz/ppo-SnowballTarget
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SnowballTarget.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2114f68b2e9a0f0b0be80528cc1f05302c4467f565ef6d51aa2d9b7e8bb90cad
+size 650645

SnowballTarget/SnowballTarget-1000696.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2114f68b2e9a0f0b0be80528cc1f05302c4467f565ef6d51aa2d9b7e8bb90cad
+size 650645

SnowballTarget/SnowballTarget-1000696.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54af6df37212729907fb26baf42bdd15218071b16df7a389944661e2b12a3ecb
+size 3848855

SnowballTarget/SnowballTarget-399968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a236479b193dc7a1cec795115f3dc086349418c744a206b7756303280e2c58c0
+size 650645

SnowballTarget/SnowballTarget-399968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a76b7cb669316dabba9bb25bdbca72cbe82a6414e1a325b436fb2bcdc8293e8
+size 3848718

SnowballTarget/SnowballTarget-599976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62bf182942bdf6ff957913523429bb2f8aef1817c31c548690a0f797b04c9058
+size 650645

SnowballTarget/SnowballTarget-599976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b43cb24fecd8f6b14852485b78ae38b3a27399df22ae3a0e69c52e7aeac02f
+size 3848718

SnowballTarget/SnowballTarget-799984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f348d6d353a84ef99bf9297f3ed071a4dec9fa4b03d091babec1343335440a4e
+size 650645

SnowballTarget/SnowballTarget-799984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c0f7885f9f12b41b630e99c935687593d899411dd5140c85da12e6aef7bd59
+size 3848718

SnowballTarget/SnowballTarget-999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2114f68b2e9a0f0b0be80528cc1f05302c4467f565ef6d51aa2d9b7e8bb90cad
+size 650645

SnowballTarget/SnowballTarget-999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f556966bac7d4e8588211e374f636758c60ea98cfdef7a8e9fbd3fb89cb0ec00
+size 3848718

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1d668662885ad15c8b4bf4153bee67d307984442f770e64fe5425107744f53
+size 3847851

SnowballTarget/events.out.tfevents.1771964269.99d11e677bcf.1923.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdbe8ffbf218eecc23b92a9da3cf28c8fb35826622d9c0359f063ecdbf920f27
+size 33448

SnowballTarget/events.out.tfevents.1771964824.99d11e677bcf.2014.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208a600c7c5442001b5c38e7ea214eda05024a5611bb9444ca145576c5c66e58
+size 1170

SnowballTarget/events.out.tfevents.1771965162.99d11e677bcf.2086.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:452b3863a6b3ae61938069214e09981fac87283cae9edf2a86e4b07e442ae3cc
+size 1170

SnowballTarget/events.out.tfevents.1771965496.99d11e677bcf.2184.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3cbf355222e5c04a094dba36257de158939942ba6051126f539a045bba12579
+size 66666

config.json

@@ -0,0 +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": 200000, "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": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "/kaggle/working/training-envs-executables/SnowballTarget/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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+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: 200000
+    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: 5
+    even_checkpoints: false
+    max_steps: 1000000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: /kaggle/working/training-envs-executables/SnowballTarget/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: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,269 @@
+Mono path[0] = '/kaggle/working/training-envs-executables/SnowballTarget/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/kaggle/working/training-envs-executables/SnowballTarget/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /kaggle/working/training-envs-executables/SnowballTarget/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+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  0.092 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)
+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?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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: 0.735038 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 2 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 21474 frames, [16.0 KB-32.0 KB]: 363 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
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 210 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 228.9 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      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 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      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 10]
+      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 14]
+      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 6]
+      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 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 2
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      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 1]
+      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 2]
+      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 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 3
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      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 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [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 11]
+      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 0]
+      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 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  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]: 10116 frames, [8.0 MB-16.0 MB]: 11722 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 12.2 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 21838 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.5 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 21327 frames, [64.0 KB-128.0 KB]: 511 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      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]: 21838 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 39.6 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 21838 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]: 21837 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
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 21838 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]: 21838 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.7 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,362 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.6763535141944885,
+            "min": 0.5772567987442017,
+            "max": 0.8170011043548584,
+            "count": 81
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 6904.216796875,
+            "min": 573.7645263671875,
+            "max": 8339.947265625,
+            "count": 81
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 81
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 81
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 999992.0,
+            "min": 209936.0,
+            "max": 999992.0,
+            "count": 80
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 999992.0,
+            "min": 209936.0,
+            "max": 999992.0,
+            "count": 80
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 14.001880645751953,
+            "min": 12.165338516235352,
+            "max": 14.145326614379883,
+            "count": 80
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2730.36669921875,
+            "min": 2360.07568359375,
+            "max": 2894.1689453125,
+            "count": 80
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06619183858128963,
+            "min": 0.06069366172442268,
+            "max": 0.07497782197827417,
+            "count": 80
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.2647673543251585,
+            "min": 0.2537285487541892,
+            "max": 0.3705939667027754,
+            "count": 80
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.1689330839058932,
+            "min": 0.1388872119725919,
+            "max": 0.24017250216474717,
+            "count": 80
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.6757323356235728,
+            "min": 0.5555488478903676,
+            "max": 1.1725973995292889,
+            "count": 80
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 1.4412995196000008e-06,
+            "min": 1.4412995196000008e-06,
+            "max": 0.0002383812205396,
+            "count": 80
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 5.765198078400003e-06,
+            "min": 5.765198078400003e-06,
+            "max": 0.001177056107648,
+            "count": 80
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10048040000000001,
+            "min": 0.10048040000000001,
+            "max": 0.17946040000000002,
+            "count": 80
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.40192160000000005,
+            "min": 0.40192160000000005,
+            "max": 0.8923520000000001,
+            "count": 80
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 3.397196000000001e-05,
+            "min": 3.397196000000001e-05,
+            "max": 0.00397507396,
+            "count": 80
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00013588784000000004,
+            "min": 0.00013588784000000004,
+            "max": 0.019628364800000003,
+            "count": 80
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 80
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 80
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 27.613636363636363,
+            "min": 24.636363636363637,
+            "max": 27.945454545454545,
+            "count": 80
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1215.0,
+            "min": 1094.0,
+            "max": 1537.0,
+            "count": 80
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 27.613636363636363,
+            "min": 24.636363636363637,
+            "max": 27.945454545454545,
+            "count": 80
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1215.0,
+            "min": 1094.0,
+            "max": 1537.0,
+            "count": 80
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1771965495",
+        "python_version": "3.10.12 (main, Jan 26 2026, 14:55:28) [GCC 11.4.0]",
+        "command_line_arguments": "/kaggle/working/mlagents-env/bin/mlagents-learn /kaggle/working/ml-agents/config/ppo/SnowballTarget.yaml --env=/kaggle/working/training-envs-executables/SnowballTarget/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --resume",
+        "mlagents_version": "1.1.0",
+        "mlagents_envs_version": "1.1.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.0.1+cpu",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1771966945"
+    },
+    "total": 1450.027796929,
+    "count": 1,
+    "self": 0.3221737439998833,
+    "children": {
+        "run_training.setup": {
+            "total": 0.01651180499993643,
+            "count": 1,
+            "self": 0.01651180499993643
+        },
+        "TrainerController.start_learning": {
+            "total": 1449.6891113800002,
+            "count": 1,
+            "self": 1.357187974061162,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 0.6131898730000103,
+                    "count": 1,
+                    "self": 0.6131898730000103
+                },
+                "TrainerController.advance": {
+                    "total": 1447.6450636579384,
+                    "count": 72792,
+                    "self": 1.3677062019378354,
+                    "children": {
+                        "env_step": {
+                            "total": 1015.8329502420947,
+                            "count": 72792,
+                            "self": 872.3113249719509,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 142.66619366815667,
+                                    "count": 72792,
+                                    "self": 4.486886113172659,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 138.179307554984,
+                                            "count": 72792,
+                                            "self": 138.179307554984
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.8554316019872203,
+                                    "count": 72792,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1446.8322269669934,
+                                            "count": 72792,
+                                            "is_parallel": true,
+                                            "self": 678.0437214750955,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0024183679997804575,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007359899982475326,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0016823780015329248,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0016823780015329248
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.02699791000031837,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00035739400027523516,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00042642500011425,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00042642500011425
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.02483729600044171,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.02483729600044171
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0013767949994871742,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00029327300126169575,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0010835219982254785,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0010835219982254785
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 768.7885054918979,
+                                                    "count": 72791,
+                                                    "is_parallel": true,
+                                                    "self": 36.33827272714916,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 20.0706446958784,
+                                                            "count": 72791,
+                                                            "is_parallel": true,
+                                                            "self": 20.0706446958784
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 592.0298332259263,
+                                                            "count": 72791,
+                                                            "is_parallel": true,
+                                                            "self": 592.0298332259263
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 120.3497548429441,
+                                                            "count": 72791,
+                                                            "is_parallel": true,
+                                                            "self": 21.73427093882492,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 98.61548390411917,
+                                                                    "count": 727910,
+                                                                    "is_parallel": true,
+                                                                    "self": 98.61548390411917
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 430.44440721390583,
+                            "count": 72792,
+                            "self": 1.6056490339133234,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 82.97671695698682,
+                                    "count": 72792,
+                                    "self": 82.55159718098639,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.42511977600042883,
+                                            "count": 5,
+                                            "self": 0.42511977600042883
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 345.8620412230057,
+                                    "count": 363,
+                                    "self": 146.92715134594528,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 198.9348898770604,
+                                            "count": 18510,
+                                            "self": 198.9348898770604
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.0020003173849545e-06,
+                    "count": 1,
+                    "self": 1.0020003173849545e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.07366887300031522,
+                    "count": 1,
+                    "self": 0.0007980939999470138,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.0728707790003682,
+                            "count": 1,
+                            "self": 0.0728707790003682
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0",
+        "torch_version": "2.0.1+cpu"
+    },
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 399968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
+                "reward": 26.0,
+                "creation_time": 1771965859.882426,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
+                ]
+            },
+            {
+                "steps": 599976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.onnx",
+                "reward": 27.181818181818183,
+                "creation_time": 1771966220.182076,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.pt"
+                ]
+            },
+            {
+                "steps": 799984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.onnx",
+                "reward": 27.181818181818183,
+                "creation_time": 1771966582.6429114,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.pt"
+                ]
+            },
+            {
+                "steps": 999992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.onnx",
+                "reward": 28.636363636363637,
+                "creation_time": 1771966945.0186331,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.pt"
+                ]
+            },
+            {
+                "steps": 1000696,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000696.onnx",
+                "reward": 28.636363636363637,
+                "creation_time": 1771966945.149162,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000696.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000696,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 28.636363636363637,
+            "creation_time": 1771966945.149162,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000696.pt"
+            ]
+        }
+    }
+}