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: bubuxiong/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 sha256:49b2c101dd78bcf52f704abdd2f5c903b895cd5d4de20223d104380f1578578d
+size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a52de5e99858c439306d61f8f49d3fad623fe6d206406e02edb5f92f6775a06
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a557bf70c9d6e32dc53d8e7169f294220a9adaae6c82d333cd27a03df50f38
+size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3081679791a12248db320580911fe6a59f259401a1cf447109e99aeb111591c4
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e85cd28ad816856cfe8b6de64ae222bc3f3f44b8209d10e2de71b67551b8ba62
+size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3081679791a12248db320580911fe6a59f259401a1cf447109e99aeb111591c4
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9660b867a8c7dbdf6f0e548b212718bef47433e1546e8b95975ab828e3b9a66
+size 3850075

SnowballTarget/SnowballTarget-249984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a1338c6d1ce6d5a413080c7de881e9c0bda97471efa404123fa4b965eae9b4
+size 650646

SnowballTarget/SnowballTarget-249984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a55956b2b1e6e963dd8c9937e44d808ab16b6a6f23b89c41e3f438a10e3537
+size 3850075

SnowballTarget/SnowballTarget-299944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49b2c101dd78bcf52f704abdd2f5c903b895cd5d4de20223d104380f1578578d
+size 650646

SnowballTarget/SnowballTarget-299944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8f715d7ed6b0276008f5ea8273176f38958ef32e77af11d760ce21a61987cb
+size 3850075

SnowballTarget/SnowballTarget-300520.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49b2c101dd78bcf52f704abdd2f5c903b895cd5d4de20223d104380f1578578d
+size 650646

SnowballTarget/SnowballTarget-300520.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34744bce39f9fc69df2d9b82abd21f10563368d119049bad9c316f2b3e1642f8
+size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84ebc0d9db7a39062817c92e914a5d4374c39da3516500e1baf2218912a2d952
+size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da45fa88124514e4909bcf7a6bb4044bcbbb267e1ba10906610fb76ed087e660
+size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441b33c216fdfeb81301770a61f610d712bf521f6da3048bf3d9284f6d9e0428
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c83283910d1133fff16e898a5e586b0cd8ac903f8076e94e732c8d9bbed6d86
+size 3850000

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0183ec1d3fe1492ca35aca1a355c235a481444caf4bba3c3c84ccd33e1295230
+size 3849250

SnowballTarget/events.out.tfevents.1701177061.c6ed09e9f4ff.4105.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee18ceadc255a681a1d1bc95adb974f1f4468ba07a940f6574d45a60a535552
+size 24168

SnowballTarget/events.out.tfevents.1701177864.c6ed09e9f4ff.7485.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b5ee6ea98519fc8f5ba7683b5312b00bd575441845d14b06ccd9c530c7d765
+size 9366

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0004, "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": 300000, "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0004
+      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: 300000
+    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: SnowballTarget1
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,259 @@
+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  0.087 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: 0.713808 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]: 2694 frames, [16.0 KB-32.0 KB]: 45 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 33
+    [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]: 2740 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.2 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 2740 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.4 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]: 2500 frames, [64.0 KB-128.0 KB]: 240 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.4 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 2740 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]: 2740 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]: 2739 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]: 2740 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]: 2740 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": 0.8186061978340149,
+            "min": 0.8186061978340149,
+            "max": 1.0559101104736328,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 8410.3603515625,
+            "min": 8268.572265625,
+            "max": 10790.345703125,
+            "count": 10
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 299944.0,
+            "min": 209936.0,
+            "max": 299944.0,
+            "count": 10
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 299944.0,
+            "min": 209936.0,
+            "max": 299944.0,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.922038078308105,
+            "min": 11.952845573425293,
+            "max": 12.922038078308105,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2636.095703125,
+            "min": 2294.9462890625,
+            "max": 2636.095703125,
+            "count": 10
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 10
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 10
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06289340531380445,
+            "min": 0.06289340531380445,
+            "max": 0.07298895062550026,
+            "count": 10
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.31446702656902226,
+            "min": 0.2564468645221353,
+            "max": 0.3649447531275013,
+            "count": 10
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.18273486009999815,
+            "min": 0.17269556761226232,
+            "max": 0.2061975409587224,
+            "count": 10
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.9136743004999908,
+            "min": 0.6907822704490493,
+            "max": 1.030987704793612,
+            "count": 10
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 7.168098208000002e-06,
+            "min": 7.168098208000002e-06,
+            "max": 0.00012596806850800004,
+            "count": 10
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.584049104000001e-05,
+            "min": 3.584049104000001e-05,
+            "max": 0.00056384035904,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10179200000000002,
+            "min": 0.10179200000000002,
+            "max": 0.131492,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5089600000000001,
+            "min": 0.420368,
+            "max": 0.64096,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 9.942080000000004e-05,
+            "min": 9.942080000000004e-05,
+            "max": 0.0015814508000000001,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0004971040000000002,
+            "min": 0.0004971040000000002,
+            "max": 0.007083904000000002,
+            "count": 10
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.254545454545454,
+            "min": 23.59090909090909,
+            "max": 25.65909090909091,
+            "count": 10
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1389.0,
+            "min": 1038.0,
+            "max": 1394.0,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.254545454545454,
+            "min": 23.59090909090909,
+            "max": 25.65909090909091,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1389.0,
+            "min": 1038.0,
+            "max": 1394.0,
+            "count": 10
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 10
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 10
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1701177864",
+        "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=SnowballTarget1 --no-graphics --resume",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1701178121"
+    },
+    "total": 257.64591268899994,
+    "count": 1,
+    "self": 0.6856021840001176,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05936170099994342,
+            "count": 1,
+            "self": 0.05936170099994342
+        },
+        "TrainerController.start_learning": {
+            "total": 256.9009488039999,
+            "count": 1,
+            "self": 0.3805073840026125,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.9045668460000797,
+                    "count": 1,
+                    "self": 2.9045668460000797
+                },
+                "TrainerController.advance": {
+                    "total": 253.47316530099715,
+                    "count": 9133,
+                    "self": 0.14800347099526334,
+                    "children": {
+                        "env_step": {
+                            "total": 253.3251618300019,
+                            "count": 9133,
+                            "self": 171.39293613799282,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 81.77459825699498,
+                                    "count": 9133,
+                                    "self": 0.7997666729916091,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 80.97483158400337,
+                                            "count": 9133,
+                                            "self": 80.97483158400337
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.15762743501409204,
+                                    "count": 9133,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 256.1380643099999,
+                                            "count": 9133,
+                                            "is_parallel": true,
+                                            "self": 126.38200379400519,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0020239119999132527,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006067859994800529,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0014171260004331998,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0014171260004331998
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.04059344400002374,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006465980000029958,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003702849999172031,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003702849999172031
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03738552599998002,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03738552599998002
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.00219103500012352,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00041975999988608237,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0017712750002374378,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0017712750002374378
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 129.7560605159947,
+                                                    "count": 9132,
+                                                    "is_parallel": true,
+                                                    "self": 5.707123729009709,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 2.9608065359964257,
+                                                            "count": 9132,
+                                                            "is_parallel": true,
+                                                            "self": 2.9608065359964257
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 102.44725635898658,
+                                                            "count": 9132,
+                                                            "is_parallel": true,
+                                                            "self": 102.44725635898658
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 18.64087389200199,
+                                                            "count": 9132,
+                                                            "is_parallel": true,
+                                                            "self": 3.5414231690879205,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 15.09945072291407,
+                                                                    "count": 91320,
+                                                                    "is_parallel": true,
+                                                                    "self": 15.09945072291407
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0004969950000486278,
+                    "count": 1,
+                    "self": 0.0004969950000486278,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 251.32488757299438,
+                                    "count": 260643,
+                                    "is_parallel": true,
+                                    "self": 5.929078582990769,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 143.6799359830029,
+                                            "count": 260643,
+                                            "is_parallel": true,
+                                            "self": 143.3605227300029,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.31941325299999335,
+                                                    "count": 2,
+                                                    "is_parallel": true,
+                                                    "self": 0.31941325299999335
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 101.71587300700071,
+                                            "count": 45,
+                                            "is_parallel": true,
+                                            "self": 32.16048138999463,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 69.55539161700608,
+                                                    "count": 2292,
+                                                    "is_parallel": true,
+                                                    "self": 69.55539161700608
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.14221227799998815,
+                    "count": 1,
+                    "self": 0.0016194329998597823,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.14059284500012836,
+                            "count": 1,
+                            "self": 0.14059284500012836
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,92 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 11.545454545454545,
+                "creation_time": 1701177194.6987677,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 18.0,
+                "creation_time": 1701177320.773931,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 21.727272727272727,
+                "creation_time": 1701177448.851989,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 23.272727272727273,
+                "creation_time": 1701177576.2133915,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 23.272727272727273,
+                "creation_time": 1701177576.3772128,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
+            },
+            {
+                "steps": 249984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
+                "reward": 24.181818181818183,
+                "creation_time": 1701177995.8195035,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
+                ]
+            },
+            {
+                "steps": 299944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.onnx",
+                "reward": 24.90909090909091,
+                "creation_time": 1701178120.9616673,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.pt"
+                ]
+            },
+            {
+                "steps": 300520,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-300520.onnx",
+                "reward": 24.90909090909091,
+                "creation_time": 1701178121.2111726,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-300520.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 300520,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 24.90909090909091,
+            "creation_time": 1701178121.2111726,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-300520.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.1.1+cu121"
+    }
+}