First model push

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: jimjiang203/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 sha256:818399e1ace336c8c2d05d98421e20ca9dc857cf49857d6937e467ada049cedd
+size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818399e1ace336c8c2d05d98421e20ca9dc857cf49857d6937e467ada049cedd
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d9457a6c92e0d53db2fb7e8244ddae243c500e738ea01090888dc18e1b8a81
+size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818399e1ace336c8c2d05d98421e20ca9dc857cf49857d6937e467ada049cedd
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ac2ac8a23940a44b31c56686311c9dda85221d144d6a8b139ac12c8a59aada
+size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818399e1ace336c8c2d05d98421e20ca9dc857cf49857d6937e467ada049cedd
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db29fd23cee78eca689b34ffdb7058eb8b617b6ffcfd28a247b7815eed8444d0
+size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818399e1ace336c8c2d05d98421e20ca9dc857cf49857d6937e467ada049cedd
+size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b5a871aabb03f5ba33dceede9365915cfb9c5dc42e7f712b58723f3003a68cc
+size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818399e1ace336c8c2d05d98421e20ca9dc857cf49857d6937e467ada049cedd
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0531db2da108059b072d788662d61d7c0fca151023aa041dc0597dbcc84825d7
+size 3850000

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233695e50f3c728b70f344b8590c0d12fed9939db1939538e3b1041d99d2c04b
+size 3849250

SnowballTarget/events.out.tfevents.1719579618.2bae086f6f0d.15059.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a59c1394fb001813085c9270aa54b97625141d605e42faee4da0edb2198345
+size 20457

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.05, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.05
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 10
+    even_checkpoints: false
+    max_steps: 200000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SnowballTarget2
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,259 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    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  0.129 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: 0.875093 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.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [2.0 KB-4.0 KB]: 4857 frames, [4.0 KB-8.0 KB]: 31 frames, [8.0 KB-16.0 KB]: 481 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
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 198 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]
+      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]
+      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_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 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 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 44
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 21.2 MB
+      Peak Large allocation bytes 16.0 MB
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 5461 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.7 MB
+      Peak Large allocation bytes 0 B
+[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]: 5453 frames, [64.0 KB-128.0 KB]: 8 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 65.6 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5461 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]: 5461 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]: 5460 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]: 5461 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]: 5461 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 +1,377 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": -3.576278402306343e-07,
+            "min": -3.576278402306343e-07,
+            "max": 0.6270020604133606,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": -0.0034185645636171103,
+            "min": -0.0036860702093690634,
+            "max": 6428.02490234375,
+            "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": 0.0031717538367956877,
+            "min": -0.03686489909887314,
+            "max": 0.0049997917376458645,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 0.6184920072555542,
+            "min": -7.151790618896484,
+            "max": 1.0199575424194336,
+            "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": 0.0653819996400225,
+            "min": 0.06419295240178982,
+            "max": 0.14083556993379415,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.26152799856009,
+            "min": 0.2567718096071593,
+            "max": 0.5633422797351766,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 1.4869749532845518e-05,
+            "min": 1.3001024359148097e-05,
+            "max": 322.4647458659975,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 5.947899813138207e-05,
+            "min": 5.745186459138245e-05,
+            "max": 1289.85898346399,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 0.001347000097306001,
+            "min": 0.001347000097306001,
+            "max": 0.04864700000270601,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 0.005388000389224004,
+            "min": 0.005388000389224004,
+            "max": 0.23086000003828003,
+            "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": 0.0,
+            "min": 0.0,
+            "max": 0.8181818181818182,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 36.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.8181818181818182,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 36.0,
+            "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": "1719579617",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.3.0+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1719580047"
+    },
+    "total": 429.6964784659999,
+    "count": 1,
+    "self": 0.4249309470001208,
+    "children": {
+        "run_training.setup": {
+            "total": 0.07610302499961108,
+            "count": 1,
+            "self": 0.07610302499961108
+        },
+        "TrainerController.start_learning": {
+            "total": 429.1954444940002,
+            "count": 1,
+            "self": 0.5483462620036335,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.92004316800012,
+                    "count": 1,
+                    "self": 2.92004316800012
+                },
+                "TrainerController.advance": {
+                    "total": 425.63874754399603,
+                    "count": 18202,
+                    "self": 0.2667180619937426,
+                    "children": {
+                        "env_step": {
+                            "total": 425.3720294820023,
+                            "count": 18202,
+                            "self": 270.04188939302503,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 155.0543094580171,
+                                    "count": 18202,
+                                    "self": 1.4406679380090281,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 153.61364152000806,
+                                            "count": 18202,
+                                            "self": 153.61364152000806
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.27583063096017213,
+                                    "count": 18202,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 427.9282036689665,
+                                            "count": 18202,
+                                            "is_parallel": true,
+                                            "self": 227.30470915795604,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002898317000017414,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007315580010072154,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0021667589990101987,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0021667589990101987
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.041576238999823545,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006295649995990971,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003987660002167104,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003987660002167104
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.038644737000140594,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.038644737000140594
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0019031709998671431,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000372070000594249,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0015311009992728941,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0015311009992728941
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 200.62349451101045,
+                                                    "count": 18201,
+                                                    "is_parallel": true,
+                                                    "self": 10.094619112072905,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.343198521982686,
+                                                            "count": 18201,
+                                                            "is_parallel": true,
+                                                            "self": 5.343198521982686
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 151.213497765998,
+                                                            "count": 18201,
+                                                            "is_parallel": true,
+                                                            "self": 151.213497765998
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 33.97217911095686,
+                                                            "count": 18201,
+                                                            "is_parallel": true,
+                                                            "self": 6.504058340904976,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 27.468120770051883,
+                                                                    "count": 182010,
+                                                                    "is_parallel": true,
+                                                                    "self": 27.468120770051883
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00011823400018329266,
+                    "count": 1,
+                    "self": 0.00011823400018329266,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 420.43164133383425,
+                                    "count": 628604,
+                                    "is_parallel": true,
+                                    "self": 13.144507115160195,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 232.33192482367394,
+                                            "count": 628604,
+                                            "is_parallel": true,
+                                            "self": 231.5352226676746,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.7967021559993555,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.7967021559993555
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 174.9552093950001,
+                                            "count": 90,
+                                            "is_parallel": true,
+                                            "self": 53.98603316800927,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 120.96917622699084,
+                                                    "count": 4587,
+                                                    "is_parallel": true,
+                                                    "self": 120.96917622699084
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.08818928600021536,
+                    "count": 1,
+                    "self": 0.0009118399998442328,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.08727744600037113,
+                            "count": 1,
+                            "self": 0.08727744600037113
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 49936,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 0.0,
+                "creation_time": 1719579729.0303314,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 0.0,
+                "creation_time": 1719579835.6797252,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 0.0,
+                "creation_time": 1719579941.1235309,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 0.0,
+                "creation_time": 1719580046.578286,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 0.0,
+                "creation_time": 1719580046.6906297,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 200112,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 0.0,
+            "creation_time": 1719580046.6906297,
+            "auxillary_file_paths": [
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.3.0+cu121"
+    }
+}