First training of SnowballTarget

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-SnowballTarget
+      library_name: ml-agents
+---
+    
+  # **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://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  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. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
+  2. Step 1: Write your model_id: javiervela/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:b82ea0d31f4aae63566dd1b755e76b6759c7fc57b66bcfc22552c7a046eab8f8
+size 645119

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da46aeabd06c825fbc2b3e8e3d3108f0b96e4e2542bf783169fb5851bc120dcc
+size 645119

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d65b7e5a2bcfdc4a75600109ee423d09ee79a7bbd1fb3cad0e62b771216f619
+size 3845312

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82ea0d31f4aae63566dd1b755e76b6759c7fc57b66bcfc22552c7a046eab8f8
+size 645119

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea8d441189879d036c914db1acf24a85cf56f089727c64639171da779c25e18e
+size 3845312

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82ea0d31f4aae63566dd1b755e76b6759c7fc57b66bcfc22552c7a046eab8f8
+size 645119

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:021772ee5390a1480799315c0dc32ea9e4c75e33dc87ae0863961e452eeba8c4
+size 3845312

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce27beef9b835a735515e7c75613a745da974b935810c411bd397283de12c307
+size 645119

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8150a3fd9ee0c6c6d896fe2f1daf6fd1832c6f309a73d57e1271baa15fb281
+size 3845312

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e337d37c820578705d11f80cbc97e33f2137a3166cd4ce452810e0b26ac63d5
+size 645119

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a95227f261ccbc56dfd1b86435f26dc34a238bc36259441c817a13a99c0a417
+size 3845312

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:021772ee5390a1480799315c0dc32ea9e4c75e33dc87ae0863961e452eeba8c4
+size 3845312

SnowballTarget/events.out.tfevents.1674759263.0b319fd7ab95.1942.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988d4f90d2c35560f7f0236c4aae703b193dd181add9d4d2a0ef8f9950e71d8e
+size 23747

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 50000, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": "SnowballTarget1", "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 +1,75 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    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
+    checkpoint_interval: 50000
+    max_steps: 200000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  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: SnowballTarget1
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,262 @@
+Mono path[0] = '/content/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  0.080 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: 0.607160 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]: 5375 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 198 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 228.9 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 45
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5467 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5467 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.8 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4231 frames, [64.0 KB-128.0 KB]: 1236 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]: 5467 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 0.9 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5467 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]: 5466 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 0.9 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 5467 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]: 5467 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 +1,384 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.8047587275505066,
+            "min": 0.8047587275505066,
+            "max": 2.844916343688965,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7781.2119140625,
+            "min": 7781.2119140625,
+            "max": 29134.7890625,
+            "count": 20
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 11.816329002380371,
+            "min": 0.3686668276786804,
+            "max": 11.816329002380371,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2304.18408203125,
+            "min": 71.5213623046875,
+            "max": 2398.43115234375,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06831586426044084,
+            "min": 0.06234255140265234,
+            "max": 0.0762028780719037,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.27326345704176336,
+            "min": 0.2572842669883268,
+            "max": 0.38101439035951856,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.1758270290698491,
+            "min": 0.11047851242577,
+            "max": 0.27533148258340123,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7033081162793964,
+            "min": 0.44191404970308,
+            "max": 1.3175450665693658,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.082097306000005e-06,
+            "min": 8.082097306000005e-06,
+            "max": 0.000291882002706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.232838922400002e-05,
+            "min": 3.232838922400002e-05,
+            "max": 0.00138516003828,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10269400000000001,
+            "min": 0.10269400000000001,
+            "max": 0.19729400000000002,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.41077600000000003,
+            "min": 0.41077600000000003,
+            "max": 0.96172,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0001444306000000001,
+            "min": 0.0001444306000000001,
+            "max": 0.0048649706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005777224000000004,
+            "min": 0.0005777224000000004,
+            "max": 0.023089828,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 23.545454545454547,
+            "min": 3.090909090909091,
+            "max": 23.545454545454547,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1036.0,
+            "min": 136.0,
+            "max": 1281.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 23.545454545454547,
+            "min": 3.090909090909091,
+            "max": 23.545454545454547,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1036.0,
+            "min": 136.0,
+            "max": 1281.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1674759257",
+        "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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=SnowballTarget1 --no-graphics",
+        "mlagents_version": "0.29.0.dev0",
+        "mlagents_envs_version": "0.29.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.8.1+cu102",
+        "numpy_version": "1.21.6",
+        "end_time_seconds": "1674759704"
+    },
+    "total": 446.73370976100006,
+    "count": 1,
+    "self": 0.7160155540000801,
+    "children": {
+        "run_training.setup": {
+            "total": 0.10207663099998854,
+            "count": 1,
+            "self": 0.10207663099998854
+        },
+        "TrainerController.start_learning": {
+            "total": 445.915617576,
+            "count": 1,
+            "self": 0.580501232991196,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 9.416779936000012,
+                    "count": 1,
+                    "self": 9.416779936000012
+                },
+                "TrainerController.advance": {
+                    "total": 435.7197957920088,
+                    "count": 18223,
+                    "self": 0.30650851600984197,
+                    "children": {
+                        "env_step": {
+                            "total": 435.413287275999,
+                            "count": 18223,
+                            "self": 285.16918579699336,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 149.9474767600039,
+                                    "count": 18223,
+                                    "self": 1.522381588008102,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 148.4250951719958,
+                                            "count": 18223,
+                                            "self": 35.602587510996045,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 112.82250766099975,
+                                                    "count": 18223,
+                                                    "self": 112.82250766099975
+                                                }
+                                            }
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.29662471900172704,
+                                    "count": 18223,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 444.4526538550004,
+                                            "count": 18223,
+                                            "is_parallel": true,
+                                            "self": 212.01011736099832,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0057125299999825074,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0032123979997891183,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.002500132000193389,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002500132000193389
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03982694400002629,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006353960000069492,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00039621700000225246,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00039621700000225246
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03692699599997695,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03692699599997695
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0018683350000401333,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004510130000880963,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001417321999952037,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001417321999952037
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 232.44253649400207,
+                                                    "count": 18222,
+                                                    "is_parallel": true,
+                                                    "self": 8.584995219995221,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.175450551002882,
+                                                            "count": 18222,
+                                                            "is_parallel": true,
+                                                            "self": 5.175450551002882
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 187.33626103000677,
+                                                            "count": 18222,
+                                                            "is_parallel": true,
+                                                            "self": 187.33626103000677
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 31.3458296929972,
+                                                            "count": 18222,
+                                                            "is_parallel": true,
+                                                            "self": 7.066802653000934,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 24.279027039996265,
+                                                                    "count": 182220,
+                                                                    "is_parallel": true,
+                                                                    "self": 24.279027039996265
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 4.1517999989082455e-05,
+                    "count": 1,
+                    "self": 4.1517999989082455e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 432.7090723020058,
+                                    "count": 365757,
+                                    "is_parallel": true,
+                                    "self": 9.333889902044007,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 250.0770053869611,
+                                            "count": 365757,
+                                            "is_parallel": true,
+                                            "self": 248.97290215096132,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 1.104103235999787,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 1.104103235999787
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 173.29817701300067,
+                                            "count": 90,
+                                            "is_parallel": true,
+                                            "self": 42.3191218649996,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 130.97905514800107,
+                                                    "count": 4587,
+                                                    "is_parallel": true,
+                                                    "self": 130.97905514800107
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.19849909699996715,
+                    "count": 1,
+                    "self": 0.0010917869999502727,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.19740731000001688,
+                            "count": 1,
+                            "self": 0.19740731000001688
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 13.636363636363637,
+                "creation_time": 1674759377.1623898,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 21.545454545454547,
+                "creation_time": 1674759486.9389548,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 22.181818181818183,
+                "creation_time": 1674759595.6720226,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 23.181818181818183,
+                "creation_time": 1674759703.1571863,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 23.181818181818183,
+                "creation_time": 1674759703.3900428,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 200112,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 23.181818181818183,
+            "creation_time": 1674759703.3900428,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.29.0.dev0",
+        "torch_version": "1.8.1+cu102"
+    }
+}