First agent

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: EduardoCGarridoMerchan/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 sha256:4b0d3ecceb0954a19a5a1a56fb447bd8baff6c961ee37d613ef6adb4a44ce2ab
+size 645119

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1f29cc8b2d0a63e195154b6573f82df565ab7e5c775175289460b2e7c6f5e4
+size 645119

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad2ca4ede647f3bb85a80cb27fefbecc4e9792527e7f648430e0c6204b9768a
+size 3845312

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a3aee0e367a3630ca962c3d576a0a39d4775d3131ee0f91e5476995fd99638e
+size 645119

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ffdfad13bbbf4dfda47ca2f299fe186c759d13417ee3accaf9704a005bfb901
+size 3845312

SnowballTarget/SnowballTarget-249944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fed795d46295957b5ba252ba727e2ad13530f6e57abffc2c022cbfc719d3027
+size 645119

SnowballTarget/SnowballTarget-249944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b570aa180fe78b11b03992965a6cd9f9bf939bcdbb31f205299bc5e6ac293c53
+size 3845312

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18aa28ecb4effc3786289c02f7cf6770d5b1351b6b5bfa44f909070e3aaea91e
+size 645119

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2424a854f42bf633587312f83164a18bfd4b7ce30ae8856c7117c8bd50f762
+size 3845312

SnowballTarget/SnowballTarget-349992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c02b41efcf558cf9cc3e42fde89c681dd149891db4b7468bf10737b3695e87
+size 645119

SnowballTarget/SnowballTarget-349992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6730b28912cf1cec7f920a4a55298b63d1600d2bd7d5ecb357e0d88148dfc7b5
+size 3845312

SnowballTarget/SnowballTarget-399992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:281aa5551859d8d2564c454c7b7b8f7181f4d16ac2648e5d2faa07af992bdd29
+size 645119

SnowballTarget/SnowballTarget-399992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d327c5228b81f1231af745f8a1e92d81c707c4a787ae497c4d1d70e1dda821
+size 3845312

SnowballTarget/SnowballTarget-449952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a62401f72f57461dddb3208dba21a79d36d9cda3fdec85222d1a3fd3a4ac72
+size 645119

SnowballTarget/SnowballTarget-449952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd3723c8294374de59aaf261c9abd093ae25a5732566bb8e242e499db2cc415
+size 3845312

SnowballTarget/SnowballTarget-499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0d3ecceb0954a19a5a1a56fb447bd8baff6c961ee37d613ef6adb4a44ce2ab
+size 645119

SnowballTarget/SnowballTarget-499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3369121792b21b542014315718f29229592927e1449791f89bf070e6ac55c714
+size 3845312

SnowballTarget/SnowballTarget-500104.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0d3ecceb0954a19a5a1a56fb447bd8baff6c961ee37d613ef6adb4a44ce2ab
+size 645119

SnowballTarget/SnowballTarget-500104.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8785139b2fbabe7dcba3efee565b1a6f01deba207d109946247b54da3f8e14
+size 3845312

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6b725d65fbb5b7e0f2a35acb5c987222b96db6b9c20af552df27d921406b61a
+size 645119

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924684e45aaa33e9ee23663b1088f26be67de4a0916e20ed2b16bbe27523b751
+size 3845312

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8785139b2fbabe7dcba3efee565b1a6f01deba207d109946247b54da3f8e14
+size 3845312

SnowballTarget/events.out.tfevents.1674039374.efb5849a5f26.6069.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88851eee3cdbb7e79f44cda2d953ed09dd70827a68c49938e76ba86c02102ff3
+size 14703

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 64, "buffer_size": 2048, "learning_rate": 0.0001, "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": 500000, "time_horizon": 64, "summary_freq": 50000, "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: 64
+      buffer_size: 2048
+      learning_rate: 0.0001
+      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: 500000
+    time_horizon: 64
+    summary_freq: 50000
+    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  0.077 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: 0.745031 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]: 13416 frames, [16.0 KB-32.0 KB]: 227 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 44
+    [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]: 11413 frames, [8.0 MB-16.0 MB]: 2231 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 9.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 13644 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]: 12331 frames, [64.0 KB-128.0 KB]: 1313 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]: 13644 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]: 13644 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]: 13643 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]: 13644 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]: 13644 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": 0.7169133424758911,
+            "min": 0.7169133424758911,
+            "max": 2.5835161209106445,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 35810.5390625,
+            "min": 35810.5390625,
+            "max": 130526.984375,
+            "count": 10
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 499976.0,
+            "min": 49936.0,
+            "max": 499976.0,
+            "count": 10
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 499976.0,
+            "min": 49936.0,
+            "max": 499976.0,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.537559509277344,
+            "min": 2.3262007236480713,
+            "max": 13.537559509277344,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 13578.171875,
+            "min": 2307.591064453125,
+            "max": 13578.171875,
+            "count": 10
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 10
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 50347.0,
+            "min": 48158.0,
+            "max": 50347.0,
+            "count": 10
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.09952346138659715,
+            "min": 0.09466299025930625,
+            "max": 0.10087861357168838,
+            "count": 10
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 2.2890396118917344,
+            "min": 2.1755999400326496,
+            "max": 2.320208112148833,
+            "count": 10
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.18897049657790865,
+            "min": 0.18560784062067362,
+            "max": 0.255028156342917,
+            "count": 10
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 4.346321421291899,
+            "min": 4.1164782167795835,
+            "max": 5.865647595887091,
+            "count": 10
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 4.977695022400002e-06,
+            "min": 4.977695022400002e-06,
+            "max": 9.495760504239999e-05,
+            "count": 10
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 0.00011448698551520003,
+            "min": 0.00011448698551520003,
+            "max": 0.0020890673109328,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10497759999999998,
+            "min": 0.10497759999999998,
+            "max": 0.19495760000000004,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 2.4144847999999994,
+            "min": 2.4144847999999994,
+            "max": 4.289067200000001,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.00025838224000000005,
+            "min": 0.00025838224000000005,
+            "max": 0.0047483842399999995,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.005942791520000001,
+            "min": 0.005942791520000001,
+            "max": 0.10446445328,
+            "count": 10
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.49407114624506,
+            "min": 7.433884297520661,
+            "max": 26.49407114624506,
+            "count": 10
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 6703.0,
+            "min": 1799.0,
+            "max": 6703.0,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.49407114624506,
+            "min": 7.433884297520661,
+            "max": 26.49407114624506,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 6703.0,
+            "min": 1799.0,
+            "max": 6703.0,
+            "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": "1674039368",
+        "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": "1674040491"
+    },
+    "total": 1122.6467492589998,
+    "count": 1,
+    "self": 0.3830281609996291,
+    "children": {
+        "run_training.setup": {
+            "total": 0.11190371199995752,
+            "count": 1,
+            "self": 0.11190371199995752
+        },
+        "TrainerController.start_learning": {
+            "total": 1122.1518173860002,
+            "count": 1,
+            "self": 1.3495537490184688,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 9.088162218999969,
+                    "count": 1,
+                    "self": 9.088162218999969
+                },
+                "TrainerController.advance": {
+                    "total": 1111.5961136439812,
+                    "count": 45477,
+                    "self": 0.7089983889948144,
+                    "children": {
+                        "env_step": {
+                            "total": 1110.8871152549864,
+                            "count": 45477,
+                            "self": 782.5423483469895,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 327.68075491198056,
+                                    "count": 45477,
+                                    "self": 3.3905774380211824,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 324.2901774739594,
+                                            "count": 45477,
+                                            "self": 72.44579044294528,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 251.8443870310141,
+                                                    "count": 45477,
+                                                    "self": 251.8443870310141
+                                                }
+                                            }
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.6640119960163702,
+                                    "count": 45477,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1119.2070092759475,
+                                            "count": 45477,
+                                            "is_parallel": true,
+                                            "self": 575.9232987029563,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.005660044000023845,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.003462286000058157,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.002197757999965688,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002197757999965688
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.042526369999905,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006222729998626164,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00027388500006964023,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00027388500006964023
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03969701200003328,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03969701200003328
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0019331999999394611,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004443279997303762,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001488872000209085,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001488872000209085
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 543.2837105729911,
+                                                    "count": 45476,
+                                                    "is_parallel": true,
+                                                    "self": 20.542142130923366,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 11.932183702015209,
+                                                            "count": 45476,
+                                                            "is_parallel": true,
+                                                            "self": 11.932183702015209
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 438.3587254880065,
+                                                            "count": 45476,
+                                                            "is_parallel": true,
+                                                            "self": 438.3587254880065
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 72.45065925204608,
+                                                            "count": 45476,
+                                                            "is_parallel": true,
+                                                            "self": 15.787640815154873,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 56.66301843689121,
+                                                                    "count": 454760,
+                                                                    "is_parallel": true,
+                                                                    "self": 56.66301843689121
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 3.444400044827489e-05,
+                    "count": 1,
+                    "self": 3.444400044827489e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 1104.0753907361634,
+                                    "count": 874880,
+                                    "is_parallel": true,
+                                    "self": 22.69800708795856,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 582.5718808692036,
+                                            "count": 874880,
+                                            "is_parallel": true,
+                                            "self": 580.5311300472033,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 2.040750822000291,
+                                                    "count": 10,
+                                                    "is_parallel": true,
+                                                    "self": 2.040750822000291
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 498.80550277900124,
+                                            "count": 227,
+                                            "is_parallel": true,
+                                            "self": 102.70710151600565,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 396.0984012629956,
+                                                    "count": 23151,
+                                                    "is_parallel": true,
+                                                    "self": 396.0984012629956
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.11795333000009123,
+                    "count": 1,
+                    "self": 0.0010511870000300405,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.11690214300006119,
+                            "count": 1,
+                            "self": 0.11690214300006119
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 18.272727272727273,
+                "creation_time": 1674039596.460914,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 22.272727272727273,
+                "creation_time": 1674039708.0522,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.272727272727273,
+                "creation_time": 1674039819.3134322,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 249944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
+                "reward": 26.0,
+                "creation_time": 1674039932.375243,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 26.0,
+                "creation_time": 1674040047.2077258,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 349992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
+                "reward": 26.09090909090909,
+                "creation_time": 1674040158.590551,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
+                ]
+            },
+            {
+                "steps": 399992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
+                "reward": 25.0,
+                "creation_time": 1674040270.7453825,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
+                ]
+            },
+            {
+                "steps": 449952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
+                "reward": 26.90909090909091,
+                "creation_time": 1674040381.7889433,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
+                ]
+            },
+            {
+                "steps": 499976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
+                "reward": 26.363636363636363,
+                "creation_time": 1674040490.9901326,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
+                ]
+            },
+            {
+                "steps": 500104,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.onnx",
+                "reward": 26.363636363636363,
+                "creation_time": 1674040491.1353183,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 500104,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 26.363636363636363,
+            "creation_time": 1674040491.1353183,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.29.0.dev0",
+        "torch_version": "1.8.1+cu102"
+    }
+}