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: RYOBEAR/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 sha256:03c47e56669bc88f58a92f078c6599f999cafd53e95681c5bacd1a62d5c2a89b
+size 910131

SnowballTarget/SnowballTarget-749984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6b082b959e98b9bb1e1788da8b999fad9f0e86020e9a65e4704b6f72f00bbf
+size 910131

SnowballTarget/SnowballTarget-749984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aee33e5a2e902956be785a2da66f8f3655c53cecbf77fd6c1eadf5b1bf8f23e0
+size 5426908

SnowballTarget/SnowballTarget-799880.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:325f1d75e891b041cb897c4cb9e33504ae01b4a1ca965fe30fb4904cdd3c9c2b
+size 910131

SnowballTarget/SnowballTarget-799880.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c522a9720715f671e8fbb112468900ed23070868aed7d0b61e5ba6c9b83576f7
+size 5426908

SnowballTarget/SnowballTarget-849968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:970c217f1a6055fdccfbc3bd8ac3739d9369651dead3a22bcbcaf70640daa373
+size 910131

SnowballTarget/SnowballTarget-849968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f990cb642b9751a30cefe65240b80e491fe52efcb265503f7e718a184fbb87ec
+size 5426908

SnowballTarget/SnowballTarget-899928.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03c47e56669bc88f58a92f078c6599f999cafd53e95681c5bacd1a62d5c2a89b
+size 910131

SnowballTarget/SnowballTarget-899928.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727d520c5c45704af0231a88875be85e89bd1b33e8adc04f6b106703d8d5b033
+size 5426908

SnowballTarget/SnowballTarget-901208.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03c47e56669bc88f58a92f078c6599f999cafd53e95681c5bacd1a62d5c2a89b
+size 910131

SnowballTarget/SnowballTarget-901208.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f59ac85387edede848a59a5bbfe1c190ba6c66ca7a9ab90b1bc71e5abc9b3bc
+size 5426908

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f59ac85387edede848a59a5bbfe1c190ba6c66ca7a9ab90b1bc71e5abc9b3bc
+size 5426908

SnowballTarget/events.out.tfevents.1687575824.74b610763a5d.3469.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695aefa0e645644df7b13128d0d6e61aa7fad7c42454f565c701e9b488ababaf
+size 91051

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 4096, "learning_rate": 0.0001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "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": 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": 5, "even_checkpoints": false, "max_steps": 900000, "time_horizon": 128, "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, "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}, "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 +1,77 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 4096
+      learning_rate: 0.0001
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 5
+      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: 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: 5
+    even_checkpoints: false
+    max_steps: 900000
+    time_horizon: 128
+    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
+  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
+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 +1,272 @@
+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'
+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/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:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(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:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(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  0.078 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: 0.693371 ms
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+Setting up 2 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 24171 frames, [16.0 KB-32.0 KB]: 409 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] x 2
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 3
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 44
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 11023 frames, [8.0 MB-16.0 MB]: 13558 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 14.4 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 24581 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.3 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]: 22841 frames, [64.0 KB-128.0 KB]: 1740 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]: 24581 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]: 24581 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]: 24580 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]: 24581 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]: 24581 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": 0.7034497857093811,
+            "min": 0.6976025700569153,
+            "max": 2.88728666305542,
+            "count": 90
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7118.912109375,
+            "min": 6393.955078125,
+            "max": 32109.513671875,
+            "count": 90
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 899928.0,
+            "min": 9952.0,
+            "max": 899928.0,
+            "count": 90
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 899928.0,
+            "min": 9952.0,
+            "max": 899928.0,
+            "count": 90
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.78389835357666,
+            "min": 0.14133355021476746,
+            "max": 13.928528785705566,
+            "count": 90
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1405.9576416015625,
+            "min": 13.709354400634766,
+            "max": 1434.638427734375,
+            "count": 90
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 90
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 13134.0,
+            "count": 90
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 27.0,
+            "min": 2.3181818181818183,
+            "max": 27.727272727272727,
+            "count": 90
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1485.0,
+            "min": 102.0,
+            "max": 1487.0,
+            "count": 90
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 27.0,
+            "min": 2.3181818181818183,
+            "max": 27.727272727272727,
+            "count": 90
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1485.0,
+            "min": 102.0,
+            "max": 1487.0,
+            "count": 90
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06874647402617162,
+            "min": 0.0607511452527861,
+            "max": 0.07715587771057401,
+            "count": 90
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.13749294805234324,
+            "min": 0.1215022905055722,
+            "max": 0.23146763313172203,
+            "count": 90
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.17409881804795826,
+            "min": 0.07601560772780111,
+            "max": 0.3074084019495381,
+            "count": 90
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.34819763609591653,
+            "min": 0.15203121545560222,
+            "max": 0.8535028227111874,
+            "count": 90
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 5.112106000000012e-07,
+            "min": 5.112106000000012e-07,
+            "max": 9.926666739999999e-05,
+            "count": 90
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 1.0224212000000023e-06,
+            "min": 1.0224212000000023e-06,
+            "max": 0.00028826667840000004,
+            "count": 90
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10051111111111113,
+            "min": 0.10051111111111113,
+            "max": 0.1992666666666667,
+            "count": 90
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.20102222222222227,
+            "min": 0.20102222222222227,
+            "max": 0.5882666666666667,
+            "count": 90
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 3.55044444444445e-05,
+            "min": 3.55044444444445e-05,
+            "max": 0.004963406666666668,
+            "count": 90
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 7.1008888888889e-05,
+            "min": 7.1008888888889e-05,
+            "max": 0.014414506666666665,
+            "count": 90
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 90
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 90
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1687575823",
+        "python_version": "3.10.12 (main, Jun  7 2023, 12:45:35) [GCC 9.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1687577671"
+    },
+    "total": 1847.6949618830001,
+    "count": 1,
+    "self": 0.2921174170003269,
+    "children": {
+        "run_training.setup": {
+            "total": 0.03749628599996413,
+            "count": 1,
+            "self": 0.03749628599996413
+        },
+        "TrainerController.start_learning": {
+            "total": 1847.36534818,
+            "count": 1,
+            "self": 2.0489472199999454,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.9043029130000377,
+                    "count": 1,
+                    "self": 3.9043029130000377
+                },
+                "TrainerController.advance": {
+                    "total": 1841.2679873029995,
+                    "count": 81936,
+                    "self": 0.9633118169865611,
+                    "children": {
+                        "env_step": {
+                            "total": 1840.304675486013,
+                            "count": 81936,
+                            "self": 1333.0701943800905,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 506.28038745394485,
+                                    "count": 81936,
+                                    "self": 6.191725687951589,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 500.08866176599327,
+                                            "count": 81936,
+                                            "self": 500.08866176599327
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.9540936519774732,
+                                    "count": 81936,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1844.3780067700304,
+                                            "count": 81936,
+                                            "is_parallel": true,
+                                            "self": 1041.3106220910702,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.001867215000061151,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005656029999272505,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0013016120001339004,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0013016120001339004
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.033797909000099935,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005918820000943015,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00039498099999946135,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00039498099999946135
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03056567700002688,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03056567700002688
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0022453689999792914,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00039210000034017867,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0018532689996391127,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0018532689996391127
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 803.0673846789603,
+                                                    "count": 81935,
+                                                    "is_parallel": true,
+                                                    "self": 38.655531934038436,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 19.771051183008808,
+                                                            "count": 81935,
+                                                            "is_parallel": true,
+                                                            "self": 19.771051183008808
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 619.9736982289395,
+                                                            "count": 81935,
+                                                            "is_parallel": true,
+                                                            "self": 619.9736982289395
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 124.66710333297351,
+                                                            "count": 81935,
+                                                            "is_parallel": true,
+                                                            "self": 21.436351150865562,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 103.23075218210795,
+                                                                    "count": 819350,
+                                                                    "is_parallel": true,
+                                                                    "self": 103.23075218210795
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0009890740002447274,
+                    "count": 1,
+                    "self": 0.0009890740002447274,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 1837.3454557221967,
+                                    "count": 762312,
+                                    "is_parallel": true,
+                                    "self": 14.722534219202544,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 683.0863609769938,
+                                            "count": 762312,
+                                            "is_parallel": true,
+                                            "self": 679.2227238579939,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 3.863637118999918,
+                                                    "count": 18,
+                                                    "is_parallel": true,
+                                                    "self": 3.863637118999918
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 1139.5365605260004,
+                                            "count": 204,
+                                            "is_parallel": true,
+                                            "self": 320.148740854037,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 819.3878196719634,
+                                                    "count": 34680,
+                                                    "is_parallel": true,
+                                                    "self": 819.3878196719634
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1431216700002551,
+                    "count": 1,
+                    "self": 0.0010047240002677427,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.14211694599998737,
+                            "count": 1,
+                            "self": 0.14211694599998737
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 749984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-749984.onnx",
+                "reward": 27.75,
+                "creation_time": 1687577363.6208649,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-749984.pt"
+                ]
+            },
+            {
+                "steps": 799880,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-799880.onnx",
+                "reward": 27.636363636363637,
+                "creation_time": 1687577463.9071743,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-799880.pt"
+                ]
+            },
+            {
+                "steps": 849968,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-849968.onnx",
+                "reward": null,
+                "creation_time": 1687577569.466804,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-849968.pt"
+                ]
+            },
+            {
+                "steps": 899928,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-899928.onnx",
+                "reward": 27.0,
+                "creation_time": 1687577670.4818754,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-899928.pt"
+                ]
+            },
+            {
+                "steps": 901208,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-901208.onnx",
+                "reward": 27.0,
+                "creation_time": 1687577670.7305615,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-901208.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 901208,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 27.0,
+            "creation_time": 1687577670.7305615,
+            "auxillary_file_paths": [
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-901208.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}