First 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: rajveer43/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:c51ddc198a6faff537940d77a7a596c74ca66292e5798913c6d2f24481394df0
+size 2874755

SnowballTarget/SnowballTarget-224912.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d6cc64edf0185925a28bbd4895a4d248bf76726b7740b274962823c959c5ec
+size 2874755

SnowballTarget/SnowballTarget-224912.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938d87822c9b2f4e3b1a6b0734130c406ae2f47cda2b0cdb9b43a1988d260dbf
+size 17151526

SnowballTarget/SnowballTarget-249880.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1955a194f1d33006c4745a388c51df9726de9d1fee2957533bb2ff02c9e1945d
+size 2874755

SnowballTarget/SnowballTarget-249880.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9dcac90a59f2248215f7a6da6d16b06c3a67010b5a5fd83b38218b250ee3194
+size 17151526

SnowballTarget/SnowballTarget-274928.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e897b9b23ba455fed54c16fb8706f40bf78dbe02a203f8298ae4368f72476a72
+size 2874755

SnowballTarget/SnowballTarget-274928.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535fe35df27479a6f8d120ead77672c027e7e6c4d456bf983b9c6282f55f5623
+size 17151526

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b292b0b332212e8bb72c78f4c6c9656eccb16fda30704dfe7c99dd12368968f0
+size 2874755

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85dc1ddf6d4e6c8b4654d13c44d989efc86fe32e7c05c93a7608e10c68e2c77f
+size 17151526

SnowballTarget/SnowballTarget-301256.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c51ddc198a6faff537940d77a7a596c74ca66292e5798913c6d2f24481394df0
+size 2874755

SnowballTarget/SnowballTarget-301256.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95dbf798c8826103f9290903828914c706f8f0710b340d7374823142f3643c9
+size 17151526

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d9116e3b3900e425961cb380a19e9ab515513325fba0940bf83179890dea0e9
+size 17150195

SnowballTarget/events.out.tfevents.1726660984.9f11752eafda.18037.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:144b2361675bb2c36c1ca76bc1197db68d0223ef6272acae6340a9adc887793a
+size 63406

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 4096, "learning_rate": 0.0001, "beta": 0.01, "epsilon": 0.1, "lambd": 0.95, "num_epoch": 5, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 25000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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": 300000, "time_horizon": 128, "summary_freq": 5000, "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: 256
+      buffer_size: 4096
+      learning_rate: 0.0001
+      beta: 0.01
+      epsilon: 0.1
+      lambd: 0.95
+      num_epoch: 5
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 25000
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        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: 300000
+    time_horizon: 128
+    summary_freq: 5000
+    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 +1,262 @@
+Mono path[0] = '/content/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/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/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  0.095 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: 0.697778 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: [8.0 KB-16.0 KB]: 8087 frames, [16.0 KB-32.0 KB]: 137 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 178 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 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]: 8225 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 7.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 8225 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.8 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]: 7732 frames, [64.0 KB-128.0 KB]: 493 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.8 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 8225 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]: 8225 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]: 8224 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]: 8225 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]: 8225 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": 1.4903042316436768,
+            "min": 1.473644495010376,
+            "max": 2.88923978805542,
+            "count": 60
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7147.4990234375,
+            "min": 6569.8173828125,
+            "max": 19259.671875,
+            "count": 60
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 299968.0,
+            "min": 4912.0,
+            "max": 299968.0,
+            "count": 60
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 299968.0,
+            "min": 4912.0,
+            "max": 299968.0,
+            "count": 60
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 24.058250427246094,
+            "min": -0.018803970888257027,
+            "max": 24.058250427246094,
+            "count": 60
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1178.854248046875,
+            "min": -0.9025905728340149,
+            "max": 1217.2606201171875,
+            "count": 60
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 60
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 6567.0,
+            "min": 2189.0,
+            "max": 6567.0,
+            "count": 60
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.363636363636363,
+            "min": 2.9545454545454546,
+            "max": 26.363636363636363,
+            "count": 60
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 580.0,
+            "min": 65.0,
+            "max": 749.0,
+            "count": 60
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.363636363636363,
+            "min": 2.9545454545454546,
+            "max": 26.363636363636363,
+            "count": 60
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 580.0,
+            "min": 65.0,
+            "max": 749.0,
+            "count": 60
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.0499648793535444,
+            "min": 0.037421126091623375,
+            "max": 0.061435123433372665,
+            "count": 60
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.0499648793535444,
+            "min": 0.037421126091623375,
+            "max": 0.10900242760647363,
+            "count": 60
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.24116564182674183,
+            "min": 0.0974211367614129,
+            "max": 0.3482391301323386,
+            "count": 60
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.24116564182674183,
+            "min": 0.0974211367614129,
+            "max": 0.6832874596118927,
+            "count": 60
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 2.667664000000039e-07,
+            "min": 2.667664000000039e-07,
+            "max": 9.853333480000002e-05,
+            "count": 60
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 2.667664000000039e-07,
+            "min": 2.667664000000039e-07,
+            "max": 0.00017506669160000004,
+            "count": 60
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.09999999999999998,
+            "min": 0.09999999999999998,
+            "max": 0.09999999999999998,
+            "count": 60
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.09999999999999998,
+            "min": 0.09999999999999998,
+            "max": 0.19999999999999996,
+            "count": 60
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 3.6640000000000395e-05,
+            "min": 3.6640000000000395e-05,
+            "max": 0.009853479999999998,
+            "count": 60
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 3.6640000000000395e-05,
+            "min": 3.6640000000000395e-05,
+            "max": 0.017509160000000003,
+            "count": 60
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 60
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 60
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1726660983",
+        "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "2.4.0+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1726661726"
+    },
+    "total": 742.5457266829999,
+    "count": 1,
+    "self": 0.4337463519996163,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05375741100033338,
+            "count": 1,
+            "self": 0.05375741100033338
+        },
+        "TrainerController.start_learning": {
+            "total": 742.0582229199999,
+            "count": 1,
+            "self": 0.9639921740408681,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.87935927000035,
+                    "count": 1,
+                    "self": 2.87935927000035
+                },
+                "TrainerController.advance": {
+                    "total": 738.0103127039583,
+                    "count": 27414,
+                    "self": 0.4029001189956034,
+                    "children": {
+                        "env_step": {
+                            "total": 737.6074125849627,
+                            "count": 27414,
+                            "self": 399.4398875051984,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 337.7503058068478,
+                                    "count": 27414,
+                                    "self": 2.139963248897402,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 335.6103425579504,
+                                            "count": 27414,
+                                            "self": 335.6103425579504
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.4172192729165545,
+                                    "count": 27414,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 740.0496240319417,
+                                            "count": 27414,
+                                            "is_parallel": true,
+                                            "self": 416.7165244518492,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002100170999256079,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006135749981694971,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.001486596001086582,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.001486596001086582
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.06091328100046667,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005985839998174924,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00039034100063872756,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00039034100063872756
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.0582315120000203,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0582315120000203
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0016928439999901457,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003080729984503705,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0013847710015397752,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0013847710015397752
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 323.3330995800925,
+                                                    "count": 27413,
+                                                    "is_parallel": true,
+                                                    "self": 14.863294503912584,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 7.755492722012605,
+                                                            "count": 27413,
+                                                            "is_parallel": true,
+                                                            "self": 7.755492722012605
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 251.88660386410993,
+                                                            "count": 27413,
+                                                            "is_parallel": true,
+                                                            "self": 251.88660386410993
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 48.827708490057375,
+                                                            "count": 27413,
+                                                            "is_parallel": true,
+                                                            "self": 9.056327009237975,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 39.7713814808194,
+                                                                    "count": 274130,
+                                                                    "is_parallel": true,
+                                                                    "self": 39.7713814808194
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0008779700001468882,
+                    "count": 1,
+                    "self": 0.0008779700001468882,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 731.5485044326742,
+                                    "count": 857191,
+                                    "is_parallel": true,
+                                    "self": 17.148951226859936,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 338.38722694181615,
+                                            "count": 857191,
+                                            "is_parallel": true,
+                                            "self": 333.41943709581574,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 4.967789846000414,
+                                                    "count": 12,
+                                                    "is_parallel": true,
+                                                    "self": 4.967789846000414
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 376.01232626399815,
+                                            "count": 68,
+                                            "is_parallel": true,
+                                            "self": 146.37344319796193,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 229.63888306603621,
+                                                    "count": 5780,
+                                                    "is_parallel": true,
+                                                    "self": 229.63888306603621
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.20368080200023542,
+                    "count": 1,
+                    "self": 0.0023105770005713566,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.20137022499966406,
+                            "count": 1,
+                            "self": 0.20137022499966406
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 224912,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-224912.onnx",
+                "reward": null,
+                "creation_time": 1726661540.7312195,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-224912.pt"
+                ]
+            },
+            {
+                "steps": 249880,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-249880.onnx",
+                "reward": 23.636363636363637,
+                "creation_time": 1726661598.843612,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-249880.pt"
+                ]
+            },
+            {
+                "steps": 274928,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-274928.onnx",
+                "reward": 24.8,
+                "creation_time": 1726661659.872479,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-274928.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": null,
+                "creation_time": 1726661725.6013088,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 301256,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-301256.onnx",
+                "reward": 25.77777777777778,
+                "creation_time": 1726661725.9627678,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-301256.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 301256,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 25.77777777777778,
+            "creation_time": 1726661725.9627678,
+            "auxillary_file_paths": [
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-301256.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.4.0+cu121"
+    }
+}