First Push

README.md

@@ -0,0 +1,29 @@
+---
+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://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: Find your model_id: ghassenhannachi/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:c04983404a2e6c8116d01d7b5110c1cf24499680c5cc79b0871f11ce3a8c3cbe
+size 646532

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02763edf6ab0677995d42c01f4510455b04bbf9a971e6b4b3557eb106763935
+size 646532

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a874bb6c81e015446f1f03e608e9fcafb7b9f3439a1f50e29dae12bf4afc180
+size 3843968

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de25264aab18a0b91aa09b8fd804c29f7c2c8b1961afa949f19b538d240443f4
+size 646532

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a21f6d1fd500a4d1177c260d442679f7c11259bbd6c2a75e8f03390e39eb8a2
+size 3843968

SnowballTarget/SnowballTarget-249944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76446cc7f5893e93466785b92e7191b3b2ab56de7cb0e5d52ef18b43f7df1c8f
+size 646532

SnowballTarget/SnowballTarget-249944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431cd965069355d72ab9c231244a96f62f9af26bd171a982b6d8cb8355a537e1
+size 3843968

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c30c71eedf0c2c22f29789b1d7e86fdbf5e4fed9646b08142561c16d9700c5fb
+size 646532

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3c3bc56753fcf044dbab5d1a8b7b48ed66efc8db0cee27b9a8276430f6f7e98
+size 3843968

SnowballTarget/SnowballTarget-349992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e8429158e9c4a149b1df365cc0cba292f76d2b2e9c46d642e7a9c17e651a8a
+size 646532

SnowballTarget/SnowballTarget-349992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a89067873f70bf67cd30bf98015d84a3b7694ba80b157c3664123c9eab8e19af
+size 3843968

SnowballTarget/SnowballTarget-399992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7cc2523fefc7b80e6fdf3f62899ed7de50a5017a41685ee073730a7288abc6
+size 646532

SnowballTarget/SnowballTarget-399992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7986aeda25505b007a0766795d21c30e95f22dbbac070d3b5034592519973ea0
+size 3843968

SnowballTarget/SnowballTarget-449952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:997714b1766df5eaea508349192728a1932b4b6d50c16fedcb8976bada62e5b2
+size 646532

SnowballTarget/SnowballTarget-449952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c80fe179af57c8d4008b0166845817670ca8964b053d5e81c95d504910c475
+size 3843968

SnowballTarget/SnowballTarget-499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04983404a2e6c8116d01d7b5110c1cf24499680c5cc79b0871f11ce3a8c3cbe
+size 646532

SnowballTarget/SnowballTarget-499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6fa97172856cac69c5d45ab186184478fcb4897f27b35cb842d1adb8577a8e9
+size 3843968

SnowballTarget/SnowballTarget-500104.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04983404a2e6c8116d01d7b5110c1cf24499680c5cc79b0871f11ce3a8c3cbe
+size 646532

SnowballTarget/SnowballTarget-500104.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a2877e0ddc080f6a1f7f6f84b98870ee02bec3375ade3213f6ee44dc70ccfc
+size 3843968

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e87ac41f088ddd192883d57b2bb116c8b19692c3b65622538a42119a5013804
+size 646532

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b5e04e49fb9abfbc208482571052a92be24ea55e8a838885d83a43c7d29c15
+size 3843968

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a2877e0ddc080f6a1f7f6f84b98870ee02bec3375ade3213f6ee44dc70ccfc
+size 3843968

SnowballTarget/events.out.tfevents.1680006954.4c4ee985d3b6.6364.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2bc0ec94a3279dd14c654e5696180ec7ab61fdf0fb63b37b566276b5a77ef0
+size 48059

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, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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 +1,77 @@
+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
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 10
+    even_checkpoints: false
+    max_steps: 500000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  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  0.079 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: 0.710440 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]: 13412 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 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 11054 frames, [8.0 MB-16.0 MB]: 2586 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]: 13640 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.9 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 12145 frames, [64.0 KB-128.0 KB]: 1495 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 68.2 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13640 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]: 13640 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]: 13639 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]: 13640 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]: 13640 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 +1,362 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.6862497329711914,
+            "min": 0.6552515029907227,
+            "max": 2.8428843021392822,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 6582.50732421875,
+            "min": 6347.6259765625,
+            "max": 29020.1640625,
+            "count": 50
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 499976.0,
+            "min": 9952.0,
+            "max": 499976.0,
+            "count": 50
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 499976.0,
+            "min": 9952.0,
+            "max": 499976.0,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.695756912231445,
+            "min": 0.3072643578052521,
+            "max": 13.759556770324707,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2807.630126953125,
+            "min": 59.60928726196289,
+            "max": 2807.630126953125,
+            "count": 50
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06382315461158607,
+            "min": 0.06118524266796656,
+            "max": 0.07484577231276918,
+            "count": 50
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.3191157730579303,
+            "min": 0.24474097067186623,
+            "max": 0.3728141247506488,
+            "count": 50
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.16815492767913667,
+            "min": 0.13116641822453662,
+            "max": 0.28046553023889953,
+            "count": 50
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.8407746383956833,
+            "min": 0.5246656728981465,
+            "max": 1.4023276511944975,
+            "count": 50
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 3.0528989824000028e-06,
+            "min": 3.0528989824000028e-06,
+            "max": 0.00029675280108239997,
+            "count": 50
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 1.5264494912000015e-05,
+            "min": 1.5264494912000015e-05,
+            "max": 0.001454064015312,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10101760000000001,
+            "min": 0.10101760000000001,
+            "max": 0.19891759999999997,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5050880000000001,
+            "min": 0.41199040000000003,
+            "max": 0.984688,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 6.0778240000000044e-05,
+            "min": 6.0778240000000044e-05,
+            "max": 0.00494598824,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0003038912000000002,
+            "min": 0.0003038912000000002,
+            "max": 0.0242359312,
+            "count": 50
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 50
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 50
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.581818181818182,
+            "min": 3.4318181818181817,
+            "max": 27.163636363636364,
+            "count": 50
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1462.0,
+            "min": 151.0,
+            "max": 1494.0,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.581818181818182,
+            "min": 3.4318181818181817,
+            "max": 27.163636363636364,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1462.0,
+            "min": 151.0,
+            "max": 1494.0,
+            "count": 50
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1680006949",
+        "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \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": "0.31.0.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": "1680007940"
+    },
+    "total": 991.0241347240001,
+    "count": 1,
+    "self": 0.4331869140003164,
+    "children": {
+        "run_training.setup": {
+            "total": 0.10909364299982371,
+            "count": 1,
+            "self": 0.10909364299982371
+        },
+        "TrainerController.start_learning": {
+            "total": 990.4818541669999,
+            "count": 1,
+            "self": 0.838118010996368,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 8.431820031999905,
+                    "count": 1,
+                    "self": 8.431820031999905
+                },
+                "TrainerController.advance": {
+                    "total": 981.0865343620037,
+                    "count": 45464,
+                    "self": 0.8882832679885269,
+                    "children": {
+                        "env_step": {
+                            "total": 693.3801975859685,
+                            "count": 45464,
+                            "self": 567.0031829649961,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 125.84557056697508,
+                                    "count": 45464,
+                                    "self": 6.93332973902443,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 118.91224082795065,
+                                            "count": 45464,
+                                            "self": 118.91224082795065
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.5314440539973475,
+                                    "count": 45464,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 987.4322079959543,
+                                            "count": 45464,
+                                            "is_parallel": true,
+                                            "self": 486.7480606049503,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0062808270001823985,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.004719443999874784,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0015613830003076146,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0015613830003076146
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03437766299998657,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006794840003294667,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00037672499979635177,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00037672499979635177
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.031576019999874916,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.031576019999874916
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0017454339999858348,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00035070000035375415,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0013947339996320807,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0013947339996320807
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 500.684147391004,
+                                                    "count": 45463,
+                                                    "is_parallel": true,
+                                                    "self": 23.50415237105085,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 12.620105701034618,
+                                                            "count": 45463,
+                                                            "is_parallel": true,
+                                                            "self": 12.620105701034618
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 390.96815782094427,
+                                                            "count": 45463,
+                                                            "is_parallel": true,
+                                                            "self": 390.96815782094427
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 73.59173149797425,
+                                                            "count": 45463,
+                                                            "is_parallel": true,
+                                                            "self": 13.862445530092373,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 59.72928596788188,
+                                                                    "count": 454630,
+                                                                    "is_parallel": true,
+                                                                    "self": 59.72928596788188
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 286.81805350804666,
+                            "count": 45464,
+                            "self": 1.0192455620783676,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 59.971309867966056,
+                                    "count": 45464,
+                                    "self": 58.45250307496599,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.518806793000067,
+                                            "count": 10,
+                                            "self": 1.518806793000067
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 225.82749807800224,
+                                    "count": 227,
+                                    "self": 119.3114454989909,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 106.51605257901133,
+                                            "count": 11574,
+                                            "self": 106.51605257901133
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 8.849997357174288e-07,
+                    "count": 1,
+                    "self": 8.849997357174288e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.12538087700022515,
+                    "count": 1,
+                    "self": 0.0009051020001606958,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.12447577500006446,
+                            "count": 1,
+                            "self": 0.12447577500006446
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 20.818181818181817,
+                "creation_time": 1680007157.470396,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 25.818181818181817,
+                "creation_time": 1680007254.368876,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.0,
+                "creation_time": 1680007351.4710746,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 249944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
+                "reward": 27.636363636363637,
+                "creation_time": 1680007451.0181072,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 26.09090909090909,
+                "creation_time": 1680007548.4457278,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 349992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
+                "reward": 26.454545454545453,
+                "creation_time": 1680007646.538704,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
+                ]
+            },
+            {
+                "steps": 399992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
+                "reward": 26.90909090909091,
+                "creation_time": 1680007745.274753,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
+                ]
+            },
+            {
+                "steps": 449952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
+                "reward": 27.363636363636363,
+                "creation_time": 1680007841.8691738,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
+                ]
+            },
+            {
+                "steps": 499976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
+                "reward": 26.818181818181817,
+                "creation_time": 1680007939.830557,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
+                ]
+            },
+            {
+                "steps": 500104,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.onnx",
+                "reward": 26.818181818181817,
+                "creation_time": 1680007939.9646103,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 500104,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 26.818181818181817,
+            "creation_time": 1680007939.9646103,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}