First Push

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SnowballTarget
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SnowballTarget
+---
+
+  # **ppo** Agent playing **SnowballTarget**
+  This is a trained model of a **ppo** agent playing **SnowballTarget**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+
+  ## Usage (with ML-Agents)
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: St-ep/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:bc277c6a10ffd0eafdd235fc8d8eeff002c88774176fba059c691dd03857d710
+size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeca99ffcefa3c72297c7cd4bffe5d336d981806122249655c79292bc5a54de8
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e342b69c46fabf0bc60a60424882b07c919be89c88e26c365b10e8001f2433a0
+size 3850564

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7ae0bfd9b04250aa42f719b68c605242ef02572478dab5fcaa9c556dae35f2
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8bf3bf666a6139b611a990abfc54eac02e6c9def4a4513300b78624774e3d31
+size 3850564

SnowballTarget/SnowballTarget-249944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807328eecb7527e99d323330b145773711a5f7151b7631d04a2e28ccd7bce000
+size 650646

SnowballTarget/SnowballTarget-249944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f808f3a244b260e6c536a7d4a08780d73b3e60b4b8e0e3747681290f697b1d04
+size 3850564

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f1f76795c34c24e7fd56a5f3ba639c7cf60ae1c1a7bac58d0bfc7c3047128d9
+size 650646

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac7439487bf17a756e64fb65becd029ba2e65cd88273cef38a74423ae6a0a38
+size 3850564

SnowballTarget/SnowballTarget-349992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba4e19ba5a795c46e73fce80dd8de9bc0515e1a97eddfd4f77153cb35c3b417a
+size 650646

SnowballTarget/SnowballTarget-349992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f6a0c537a37307194002fc8358e50d613c68b5ef4563fc1add02a30d6be3bd
+size 3850564

SnowballTarget/SnowballTarget-399992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c0f8e5accc4c02b14abed9b254198ed4548877f5d1900de1b1d5d7ce09a526
+size 650646

SnowballTarget/SnowballTarget-399992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b203fec5431b28172af0a4bccd60aa6630ab30b2286423a6f04cc3a878f5a3
+size 3850564

SnowballTarget/SnowballTarget-449952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:857e9dea25a78df353cf289b1a841da3a2d7ba21cfa9354b2f02d2598dd1219d
+size 650646

SnowballTarget/SnowballTarget-449952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2669888eb5f913f333f1af9d89f549cd2d73109e599c15161580d75ee02bc596
+size 3850564

SnowballTarget/SnowballTarget-499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc277c6a10ffd0eafdd235fc8d8eeff002c88774176fba059c691dd03857d710
+size 650646

SnowballTarget/SnowballTarget-499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3748764d8eb7136fc8219dc589414e662b6eed266e0fb94cc61551e9182937d
+size 3850564

SnowballTarget/SnowballTarget-500104.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc277c6a10ffd0eafdd235fc8d8eeff002c88774176fba059c691dd03857d710
+size 650646

SnowballTarget/SnowballTarget-500104.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a3b15f3c1b96bae73d5867da6299f0766da6dfa58e4fd3570cfe400e9b281d4
+size 3850564

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9f24c77d433f9b55052bcbaa5a8bb4ca69bf89bf9b19a3073fb79c8e490682
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94595d708b557741a8dd72841f4c321c1d2c05e8d962eeba6e59c7f244167e69
+size 3850487

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93ff2b5874c124599ade336c2373bbe98c661711b2dca265c53f595934e010a
+size 3849717

SnowballTarget/events.out.tfevents.1753665213.49c5b82d8e09.7514.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21073a23b18c474181eb3b1e06be880ae7669404ce3e5225c4ba94efe69bf343
+size 17923

SnowballTarget/events.out.tfevents.1753665410.49c5b82d8e09.8518.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b110f5d0854a9c185a1efdb4909a6b9219b0815625b3c941a8d91808f2fa163d
+size 37463

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 10240, "learning_rate": 0.0003, "beta": 0.01, "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, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 10240
+      learning_rate: 0.0003
+      beta: 0.01
+      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
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SnowballTarget1
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,309 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.090 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: 0.739970 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 6 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]: 11406 frames, [16.0 KB-32.0 KB]: 193 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_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 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 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 5]
+      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 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_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      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 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 6
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 11
+      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_Job.Worker 9]
+      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 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      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 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 36
+    [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]: 11598 frames, [8.0 MB-16.0 MB]: 2 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 9.1 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 11600 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.5 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]: 10339 frames, [64.0 KB-128.0 KB]: 1261 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 67.3 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 11600 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]: 11600 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]: 11599 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]: 11600 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]: 11600 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": 1.1762984991073608,
+            "min": 1.1756806373596191,
+            "max": 2.621238946914673,
+            "count": 43
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 11283.0546875,
+            "min": 11283.0546875,
+            "max": 25987.68359375,
+            "count": 43
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 499976.0,
+            "min": 79968.0,
+            "max": 499976.0,
+            "count": 43
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 499976.0,
+            "min": 79968.0,
+            "max": 499976.0,
+            "count": 43
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.787611961364746,
+            "min": 2.283193588256836,
+            "max": 12.787611961364746,
+            "count": 43
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2621.46044921875,
+            "min": 228.31935119628906,
+            "max": 2621.46044921875,
+            "count": 43
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 43
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 4378.0,
+            "max": 10945.0,
+            "count": 43
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.90909090909091,
+            "min": 10.090909090909092,
+            "max": 26.266666666666666,
+            "count": 43
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1425.0,
+            "min": 222.0,
+            "max": 1425.0,
+            "count": 43
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.90909090909091,
+            "min": 10.090909090909092,
+            "max": 26.266666666666666,
+            "count": 43
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1425.0,
+            "min": 222.0,
+            "max": 1425.0,
+            "count": 43
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 43
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 43
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06489407757253503,
+            "min": 0.06036975931660417,
+            "max": 0.08248073132896631,
+            "count": 40
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.06489407757253503,
+            "min": 0.06036975931660417,
+            "max": 0.08248073132896631,
+            "count": 40
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.18900001337751746,
+            "min": 0.18232523016631602,
+            "max": 0.29615254122763873,
+            "count": 40
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.18900001337751746,
+            "min": 0.18232523016631602,
+            "max": 0.29615254122763873,
+            "count": 40
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 4.320098559999991e-06,
+            "min": 4.320098559999991e-06,
+            "max": 0.0002485728171424,
+            "count": 40
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 4.320098559999991e-06,
+            "min": 4.320098559999991e-06,
+            "max": 0.0002485728171424,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10143999999999999,
+            "min": 0.10143999999999999,
+            "max": 0.18285759999999998,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.10143999999999999,
+            "min": 0.10143999999999999,
+            "max": 0.18285759999999998,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0001538559999999997,
+            "min": 0.0001538559999999997,
+            "max": 0.008287474239999997,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0001538559999999997,
+            "min": 0.0001538559999999997,
+            "max": 0.008287474239999997,
+            "count": 40
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1753665409",
+        "python_version": "3.10.12 (main, May 27 2025, 17:12:29) [GCC 11.4.0]",
+        "command_line_arguments": "/content/myenv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.7.1+cu126",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1753666228"
+    },
+    "total": 818.3160977670002,
+    "count": 1,
+    "self": 0.3216678219998812,
+    "children": {
+        "run_training.setup": {
+            "total": 0.018376912000121592,
+            "count": 1,
+            "self": 0.018376912000121592
+        },
+        "TrainerController.start_learning": {
+            "total": 817.9760530330002,
+            "count": 1,
+            "self": 0.8359626409924203,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.10856075300012,
+                    "count": 1,
+                    "self": 2.10856075300012
+                },
+                "TrainerController.advance": {
+                    "total": 814.9496127620077,
+                    "count": 38664,
+                    "self": 0.7878320360491671,
+                    "children": {
+                        "env_step": {
+                            "total": 565.1716780359611,
+                            "count": 38664,
+                            "self": 422.3052517529202,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 142.35733210701142,
+                                    "count": 38664,
+                                    "self": 2.5657066400149233,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 139.7916254669965,
+                                            "count": 38664,
+                                            "self": 139.7916254669965
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.5090941760295209,
+                                    "count": 38664,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 816.4277501870142,
+                                            "count": 38664,
+                                            "is_parallel": true,
+                                            "self": 444.1115703140108,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002225774999942587,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0008115320001707005,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0014142429997718864,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0014142429997718864
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.02700871299998653,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0003939330001685448,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0002823669999543199,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002823669999543199
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.02495286699991084,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.02495286699991084
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0013795459999528248,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00030719899973519205,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0010723470002176327,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0010723470002176327
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 372.3161798730034,
+                                                    "count": 38663,
+                                                    "is_parallel": true,
+                                                    "self": 12.848969081934456,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 7.157196803053239,
+                                                            "count": 38663,
+                                                            "is_parallel": true,
+                                                            "self": 7.157196803053239
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 310.17692784402584,
+                                                            "count": 38663,
+                                                            "is_parallel": true,
+                                                            "self": 310.17692784402584
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 42.133086143989885,
+                                                            "count": 38663,
+                                                            "is_parallel": true,
+                                                            "self": 8.218537388873983,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 33.9145487551159,
+                                                                    "count": 386630,
+                                                                    "is_parallel": true,
+                                                                    "self": 33.9145487551159
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 248.99010268999746,
+                            "count": 38664,
+                            "self": 0.998618152046447,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 54.729835017951245,
+                                    "count": 38664,
+                                    "self": 53.9497587029507,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.7800763150005423,
+                                            "count": 9,
+                                            "self": 0.7800763150005423
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 193.26164951999976,
+                                    "count": 40,
+                                    "self": 78.79377621699314,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 114.46787330300663,
+                                            "count": 9750,
+                                            "self": 114.46787330300663
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.0369999472459313e-06,
+                    "count": 1,
+                    "self": 1.0369999472459313e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.0819158399999651,
+                    "count": 1,
+                    "self": 0.0010463180001352157,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.08086952199982989,
+                            "count": 1,
+                            "self": 0.08086952199982989
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 13.181818181818182,
+                "creation_time": 1753665459.5908377,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 18.181818181818183,
+                "creation_time": 1753665557.4202387,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 18.84090909090909,
+                "creation_time": 1753665649.6565306,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 249944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
+                "reward": 20.484848484848484,
+                "creation_time": 1753665746.241933,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 22.666666666666668,
+                "creation_time": 1753665844.0985198,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 349992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
+                "reward": 23.90909090909091,
+                "creation_time": 1753665940.6794858,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
+                ]
+            },
+            {
+                "steps": 399992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
+                "reward": null,
+                "creation_time": 1753666038.1488457,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
+                ]
+            },
+            {
+                "steps": 449952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
+                "reward": 26.25,
+                "creation_time": 1753666130.6985924,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
+                ]
+            },
+            {
+                "steps": 499976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
+                "reward": 25.939393939393938,
+                "creation_time": 1753666227.7359884,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
+                ]
+            },
+            {
+                "steps": 500104,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.onnx",
+                "reward": 25.939393939393938,
+                "creation_time": 1753666227.8298798,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 500104,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 25.939393939393938,
+            "creation_time": 1753666227.8298798,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.7.1+cu126"
+    }
+}