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: celocho/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 sha256:2962aeb61dcbb43b04f9b57f9e9967ddd025e0745a1d9a070a0f87a7da99064b
+size 2867524

SnowballTarget/SnowballTarget-0.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d73e4a3aa18d40a9c6ac1fdd07aef224986e8df361acdf666ada315bdb13e6
+size 2863606

SnowballTarget/SnowballTarget-0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d1036ce0414aa580bee7741f2c146ad7f37bd22f46b1dfb26d1c90ca47bf10a
+size 5712476

SnowballTarget/SnowballTarget-128.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d73e4a3aa18d40a9c6ac1fdd07aef224986e8df361acdf666ada315bdb13e6
+size 2863606

SnowballTarget/SnowballTarget-128.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2db62ec3cdbdd13a2c90245af9ef370d9c0f1091d05832e6797d2bc8089854
+size 5712538

SnowballTarget/SnowballTarget-256.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d73e4a3aa18d40a9c6ac1fdd07aef224986e8df361acdf666ada315bdb13e6
+size 2863606

SnowballTarget/SnowballTarget-256.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d67912f720c7e90b1dff20bff7e9a1e27d9f85e0a05cfcd93b675886fc88143
+size 5712538

SnowballTarget/SnowballTarget-28064.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2962aeb61dcbb43b04f9b57f9e9967ddd025e0745a1d9a070a0f87a7da99064b
+size 2867524

SnowballTarget/SnowballTarget-28064.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a3afee3706fe134c1c6c6cb4c9768962710640bad627c47c5b1ce39133e6fe
+size 17129392

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8c717da0c4a0c0829f60719e7e2b2727cff574fbcb4c08b06cf5b1b98da074
+size 17128482

SnowballTarget/events.out.tfevents.1734343267.2cb94e2c865b.2834.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6cced9c727e20d66469aabad4f4d6cc8a4446ddcb6938a673d7e8c4ce661346
+size 1115

SnowballTarget/events.out.tfevents.1734343308.2cb94e2c865b.3067.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c48bd1012c8944d681ccb630e2d66ccb32d683b8855ced04b8e56264299616
+size 1115

SnowballTarget/events.out.tfevents.1734343416.2cb94e2c865b.3582.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:302e141d5fba9aba28050474c20a7d3fc3bd10f9fd5fe4ad8f766fd924a8aca4
+size 1115

SnowballTarget/events.out.tfevents.1734343529.2cb94e2c865b.4106.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f4c4ff8c2124dc62748cc802d9f8be0b96c50e67ee8a3abbeed3a1c26f36768
+size 1115

SnowballTarget/events.out.tfevents.1734343614.2cb94e2c865b.4524.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c21e741eecafaa9e200aba9eeb3392b1408eec769081a9811b0eed2d9a30176
+size 1115

SnowballTarget/events.out.tfevents.1734345115.2cb94e2c865b.10950.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d4e0a93f9c9b9147c199e9c4e847298ba97fc612d3b8d005e49a7832e5c9ddb
+size 1115

SnowballTarget/events.out.tfevents.1734345185.2cb94e2c865b.11297.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e109e31196c5941d104f140136e6141524a438e9cf235de1b8ef868b2fcfa0c0
+size 1115

SnowballTarget/events.out.tfevents.1734345440.2cb94e2c865b.12442.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01d119238669e4b1153bd5df7ee16f2b0370254a84877588d4f79ca26f157e5
+size 12591

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 4096, "learning_rate": 0.0001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 4, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "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": 300000, "time_horizon": 128, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": true, "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: 512
+      buffer_size: 4096
+      learning_rate: 0.0001
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 4
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 3
+      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: 300000
+    time_horizon: 128
+    summary_freq: 10000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SnowballTarget1
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: true
+  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/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'
+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  0.089 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: 0.801858 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]: 766 frames, [16.0 KB-32.0 KB]: 12 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]: 779 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.4 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 779 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.9 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]: 727 frames, [64.0 KB-128.0 KB]: 52 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.0 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 779 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]: 779 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]: 778 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]: 779 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]: 779 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 +1,355 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 2.8568007946014404,
+            "min": 2.8568007946014404,
+            "max": 2.8892247676849365,
+            "count": 2
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 27402.43359375,
+            "min": 27402.43359375,
+            "max": 29493.20703125,
+            "count": 2
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 19984.0,
+            "min": 9952.0,
+            "max": 19984.0,
+            "count": 2
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 19984.0,
+            "min": 9952.0,
+            "max": 19984.0,
+            "count": 2
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.515291154384613,
+            "min": 0.13076090812683105,
+            "max": 0.515291154384613,
+            "count": 2
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 52.55970001220703,
+            "min": 12.422286033630371,
+            "max": 52.55970001220703,
+            "count": 2
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 2
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 2
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 3.4444444444444446,
+            "min": 3.227272727272727,
+            "max": 3.4444444444444446,
+            "count": 2
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 186.0,
+            "min": 142.0,
+            "max": 186.0,
+            "count": 2
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 3.4444444444444446,
+            "min": 3.227272727272727,
+            "max": 3.4444444444444446,
+            "count": 2
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 186.0,
+            "min": 142.0,
+            "max": 186.0,
+            "count": 2
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.032652815368692245,
+            "min": 0.032652815368692245,
+            "max": 0.032889401037664356,
+            "count": 2
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.06530563073738449,
+            "min": 0.06530563073738449,
+            "max": 0.06577880207532871,
+            "count": 2
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.125598820974119,
+            "min": 0.12147390993777663,
+            "max": 0.125598820974119,
+            "count": 2
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.251197641948238,
+            "min": 0.24294781987555325,
+            "max": 0.251197641948238,
+            "count": 2
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 9.4781338552e-05,
+            "min": 9.4781338552e-05,
+            "max": 9.7714668952e-05,
+            "count": 2
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 0.000189562677104,
+            "min": 0.000189562677104,
+            "max": 0.000195429337904,
+            "count": 2
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.19478133333333333,
+            "min": 0.19478133333333333,
+            "max": 0.19771466666666668,
+            "count": 2
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.38956266666666667,
+            "min": 0.38956266666666667,
+            "max": 0.39542933333333335,
+            "count": 2
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0047395885333333335,
+            "min": 0.0047395885333333335,
+            "max": 0.004885961866666667,
+            "count": 2
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.009479177066666667,
+            "min": 0.009479177066666667,
+            "max": 0.009771923733333333,
+            "count": 2
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 2
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 2
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1734345440",
+        "python_version": "3.10.12 (main, Nov  6 2024, 20:22:13) [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=SnowballTarget1 --no-graphics --resume --force",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1734345503"
+    },
+    "total": 63.05687432700006,
+    "count": 1,
+    "self": 0.165197862000241,
+    "children": {
+        "run_training.setup": {
+            "total": 0.053642877000129374,
+            "count": 1,
+            "self": 0.053642877000129374
+        },
+        "TrainerController.start_learning": {
+            "total": 62.83803358799969,
+            "count": 1,
+            "self": 0.05968189500572407,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.8741869640002733,
+                    "count": 1,
+                    "self": 1.8741869640002733
+                },
+                "TrainerController.advance": {
+                    "total": 60.5440248019936,
+                    "count": 2595,
+                    "self": 0.06128617002195824,
+                    "children": {
+                        "env_step": {
+                            "total": 45.24623885799565,
+                            "count": 2595,
+                            "self": 34.371922099990115,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 10.840280149015143,
+                                    "count": 2595,
+                                    "self": 0.1930087980153985,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 10.647271350999745,
+                                            "count": 2595,
+                                            "self": 10.647271350999745
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.03403660899039096,
+                                    "count": 2594,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 62.328322223013856,
+                                            "count": 2594,
+                                            "is_parallel": true,
+                                            "self": 32.35301709001624,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002056752000044071,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006673490001958271,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0013894029998482438,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0013894029998482438
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03538853600002767,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.000591672999689763,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003957849999096652,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003957849999096652
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03254683000022851,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03254683000022851
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001854248000199732,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003865670005325228,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001467680999667209,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001467680999667209
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 29.97530513299762,
+                                                    "count": 2593,
+                                                    "is_parallel": true,
+                                                    "self": 1.426354452978103,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 0.7860832880146518,
+                                                            "count": 2593,
+                                                            "is_parallel": true,
+                                                            "self": 0.7860832880146518
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 23.094042740007808,
+                                                            "count": 2593,
+                                                            "is_parallel": true,
+                                                            "self": 23.094042740007808
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 4.668824651997056,
+                                                            "count": 2593,
+                                                            "is_parallel": true,
+                                                            "self": 0.8578550389456723,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 3.810969613051384,
+                                                                    "count": 25930,
+                                                                    "is_parallel": true,
+                                                                    "self": 3.810969613051384
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 15.236499773975993,
+                            "count": 2594,
+                            "self": 0.0796725699660783,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 3.0663161460101946,
+                                    "count": 2594,
+                                    "self": 3.0663161460101946
+                                },
+                                "_update_policy": {
+                                    "total": 12.09051105799972,
+                                    "count": 6,
+                                    "self": 7.561024990001442,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 4.529486067998278,
+                                            "count": 192,
+                                            "self": 4.529486067998278
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.666000116529176e-06,
+                    "count": 1,
+                    "self": 1.666000116529176e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.3601382609999746,
+                    "count": 1,
+                    "self": 0.007063416999699257,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.35307484400027533,
+                            "count": 1,
+                            "self": 0.35307484400027533
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,56 @@
+{
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1+cu121"
+    },
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 0,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-0.onnx",
+                "reward": null,
+                "creation_time": 1734343310.5982862,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-0.pt"
+                ]
+            },
+            {
+                "steps": 128,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-128.onnx",
+                "reward": null,
+                "creation_time": 1734345031.015344,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-128.pt"
+                ]
+            },
+            {
+                "steps": 256,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-256.onnx",
+                "reward": null,
+                "creation_time": 1734345190.6994612,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-256.pt"
+                ]
+            },
+            {
+                "steps": 28064,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-28064.onnx",
+                "reward": null,
+                "creation_time": 1734345502.9955914,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-28064.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 28064,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": null,
+            "creation_time": 1734345502.9955914,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-28064.pt"
+            ]
+        }
+    }
+}