First Push

README.md

@@ -1,3 +1,35 @@
----
-license: mit
----
+---
+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: mjm54/feb-learn6
+  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 sha256:267c94db54cda65ae97e1f75018127bcd5ce633b1ae95e2dff745b2e869d4458
+size 271829

SnowballTarget/SnowballTarget-0.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:014b9c1d2a53257dcebf69973d233d6a930f6ef0f3cff993c62b9ddbac38501e
+size 656391

SnowballTarget/SnowballTarget-0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8630c69e8f309198c80bf46607cda76d34cbe439b6ebdae78c109096e2fd4e46
+size 1688256

SnowballTarget/SnowballTarget-104936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c94cdff49d272e0846ab6be9ce2798354132c4c6c6e6f92567d7cd8d5b93e146
+size 271829

SnowballTarget/SnowballTarget-104936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dee7ce33d64ee0f576626665f49537f24eeaeef015202d00c5056a3d2743475
+size 1769790

SnowballTarget/SnowballTarget-119952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0da7c8234ae61772cc0851756198851ea0bb13a7835760e8a69d324a357e7a9
+size 271829

SnowballTarget/SnowballTarget-119952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94659abc17ef446062707bb37de7876f4e8ab7518a9c8bf10e8f6797c4f80600
+size 1769790

SnowballTarget/SnowballTarget-120984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:267c94db54cda65ae97e1f75018127bcd5ce633b1ae95e2dff745b2e869d4458
+size 271829

SnowballTarget/SnowballTarget-120984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6b88ac2b1ee9cb86e77e279f1d7b084ff02ced4794b04c6d3af025003d2b60
+size 1769790

SnowballTarget/SnowballTarget-14928.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a11288c9192cd2afcb1f6f5356645d72caaa3b8ab1e03ca514788fc2d0c294
+size 271829

SnowballTarget/SnowballTarget-14928.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63880430645dc557514451322c40b593d4d7f1c2beaf332cd974c85e8a893c16
+size 1769667

SnowballTarget/SnowballTarget-29944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1afb866e221eaac85de4075443349d7f450694e774c1aeb18986bd51878d82e
+size 271829

SnowballTarget/SnowballTarget-29944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0728602f649c7eeee5964833766db2ab14b8877fcd63d97e0bdf1d7662398438
+size 1769667

SnowballTarget/SnowballTarget-44960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b7f637bd55c78011a49e005012daa7b6346ded39380d9beaae3572995d148e8
+size 271829

SnowballTarget/SnowballTarget-44960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c433c77ae85b629050b8c3e96c44dbbb22ca74a05c800e19ee942e290aeed6
+size 1769667

SnowballTarget/SnowballTarget-59976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96389ca1daca45494e1b2080b550ae367f59c2b798403702dc191d48d251921a
+size 271829

SnowballTarget/SnowballTarget-59976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71ca660ded20c696df0b68dafaf176c7eb2af23886b065b968236c4d4df29e70
+size 1769667

SnowballTarget/SnowballTarget-74992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beea3de5f5e1d55d4a31c13e045732a9999359b185c06019f679508e1fdb2762
+size 271829

SnowballTarget/SnowballTarget-74992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:232a23199074246c59d752873e4ac35ea461fb33abb3e00cea486d0f38932c91
+size 1769667

SnowballTarget/SnowballTarget-89920.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b46c1157670dd846ccd4bfaf1cdf145b86a83062e0b112a639a1dde4b46c72a9
+size 271829

SnowballTarget/SnowballTarget-89920.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e22dcc40f79bc6c9934f99aaadae434d326ee7c7aae52c62e7d251a4417611f
+size 1769667

SnowballTarget/SnowballTarget-96.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39133531d234518608abc82be72f1e492b3566ce8a2e3991ef89245cb14e434
+size 704

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58e92c16cb417d3636f9b40c5af03fc23bd0516c48b2a88b5c494340be7b3cdf
+size 1768437

SnowballTarget/events.out.tfevents.1739206662.c442ff08d36d.6937.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233cde3a8985c570d62721a11c762285687b74c25ca620bf98964cad48daf381
+size 43795

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 64, "buffer_size": 1024, "learning_rate": 0.0004, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 4, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 15000, "network_settings": {"normalize": true, "hidden_units": 128, "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}}, "curiosity": {"gamma": 0.99, "strength": 0.02, "network_settings": {"normalize": false, "hidden_units": 32, "num_layers": 1, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0004, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 120000, "time_horizon": 96, "summary_freq": 5000, "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, "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": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,92 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 64
+      buffer_size: 1024
+      learning_rate: 0.0004
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 4
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 15000
+    network_settings:
+      normalize: true
+      hidden_units: 128
+      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
+      curiosity:
+        gamma: 0.99
+        strength: 0.02
+        network_settings:
+          normalize: false
+          hidden_units: 32
+          num_layers: 1
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0004
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 10
+    even_checkpoints: false
+    max_steps: 120000
+    time_horizon: 96
+    summary_freq: 5000
+    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
+  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: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,259 @@
+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  0.127 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: 0.976242 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]: 3246 frames, [16.0 KB-32.0 KB]: 55 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 42
+    [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]: 3302 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 3302 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 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 3178 frames, [64.0 KB-128.0 KB]: 124 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.0 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 3302 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]: 3302 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]: 3301 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]: 3302 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]: 3302 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 +1,425 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 1.5577729940414429,
+            "min": 1.5577729940414429,
+            "max": 2.8711555004119873,
+            "count": 24
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 8327.8544921875,
+            "min": 7152.794921875,
+            "max": 17492.96484375,
+            "count": 24
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 119952.0,
+            "min": 4976.0,
+            "max": 119952.0,
+            "count": 24
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 119952.0,
+            "min": 4976.0,
+            "max": 119952.0,
+            "count": 24
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 11.330068588256836,
+            "min": 0.4573516249656677,
+            "max": 11.330068588256836,
+            "count": 24
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 815.7649536132812,
+            "min": 32.929317474365234,
+            "max": 902.7938842773438,
+            "count": 24
+        },
+        "SnowballTarget.Policy.CuriosityValueEstimate.mean": {
+            "value": 0.11255823075771332,
+            "min": 0.10959342122077942,
+            "max": 0.25435778498649597,
+            "count": 24
+        },
+        "SnowballTarget.Policy.CuriosityValueEstimate.sum": {
+            "value": 8.104192733764648,
+            "min": 7.890726089477539,
+            "max": 18.31376075744629,
+            "count": 24
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 24
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 6368.0,
+            "min": 4378.0,
+            "max": 6567.0,
+            "count": 24
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.0906716643233696,
+            "min": 0.08936119078574505,
+            "max": 0.10692422976172196,
+            "count": 24
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.3626866572934784,
+            "min": 0.2680835723572351,
+            "max": 0.41460953043600357,
+            "count": 24
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.12022656089237826,
+            "min": 0.05834233026278092,
+            "max": 0.14807391013288293,
+            "count": 24
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.48090624356951306,
+            "min": 0.23336932105112368,
+            "max": 0.5922956405315317,
+            "count": 24
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.146764630000004e-06,
+            "min": 8.146764630000004e-06,
+            "max": 0.00039203555754666665,
+            "count": 24
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.2587058520000015e-05,
+            "min": 3.2587058520000015e-05,
+            "max": 0.00149925335852,
+            "count": 24
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10203666666666666,
+            "min": 0.10203666666666666,
+            "max": 0.1980088888888889,
+            "count": 24
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.40814666666666666,
+            "min": 0.31902666666666674,
+            "max": 0.7748133333333332,
+            "count": 24
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.00021346300000000008,
+            "min": 0.00021346300000000008,
+            "max": 0.009801088,
+            "count": 24
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0008538520000000003,
+            "min": 0.0008538520000000003,
+            "max": 0.037483852000000005,
+            "count": 24
+        },
+        "SnowballTarget.Losses.CuriosityForwardLoss.mean": {
+            "value": 0.049340017580563,
+            "min": 0.049340017580563,
+            "max": 0.11238793617953258,
+            "count": 24
+        },
+        "SnowballTarget.Losses.CuriosityForwardLoss.sum": {
+            "value": 0.197360070322252,
+            "min": 0.15563410755797008,
+            "max": 0.33716380853859773,
+            "count": 24
+        },
+        "SnowballTarget.Losses.CuriosityInverseLoss.mean": {
+            "value": 1.4141540664244727,
+            "min": 1.4141540664244727,
+            "max": 2.8354673816503912,
+            "count": 24
+        },
+        "SnowballTarget.Losses.CuriosityInverseLoss.sum": {
+            "value": 5.656616265697891,
+            "min": 4.2828076974346505,
+            "max": 10.669374022168101,
+            "count": 24
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 22.454545454545453,
+            "min": 2.909090909090909,
+            "max": 22.454545454545453,
+            "count": 24
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 494.0,
+            "min": 64.0,
+            "max": 711.0,
+            "count": 24
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 22.454545454545453,
+            "min": 2.909090909090909,
+            "max": 22.454545454545453,
+            "count": 24
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 494.0,
+            "min": 64.0,
+            "max": 711.0,
+            "count": 24
+        },
+        "SnowballTarget.Policy.CuriosityReward.mean": {
+            "value": 0.20842078646687281,
+            "min": 0.20536660502495413,
+            "max": 0.302854514691386,
+            "count": 24
+        },
+        "SnowballTarget.Policy.CuriosityReward.sum": {
+            "value": 4.585257302271202,
+            "min": 4.518065310548991,
+            "max": 7.958207841962576,
+            "count": 24
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 24
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 24
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1739206661",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.6.0+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1739207027"
+    },
+    "total": 366.6684852830001,
+    "count": 1,
+    "self": 0.43187780299990663,
+    "children": {
+        "run_training.setup": {
+            "total": 0.029345969000132754,
+            "count": 1,
+            "self": 0.029345969000132754
+        },
+        "TrainerController.start_learning": {
+            "total": 366.20726151100007,
+            "count": 1,
+            "self": 0.6093387509949935,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.414866170999858,
+                    "count": 1,
+                    "self": 2.414866170999858
+                },
+                "TrainerController.advance": {
+                    "total": 363.0920417230052,
+                    "count": 11005,
+                    "self": 0.2074296979983501,
+                    "children": {
+                        "env_step": {
+                            "total": 362.88461202500685,
+                            "count": 11005,
+                            "self": 284.4297636560018,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 78.26171221600043,
+                                    "count": 11005,
+                                    "self": 0.991260860004104,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 77.27045135599633,
+                                            "count": 11005,
+                                            "self": 77.27045135599633
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.19313615300461606,
+                                    "count": 11005,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 365.18384611800525,
+                                            "count": 11005,
+                                            "is_parallel": true,
+                                            "self": 220.45321479002064,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0028145039998435095,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007361789998867607,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.002078324999956749,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002078324999956749
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.06449263800004701,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005959709999387997,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003966610001953086,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003966610001953086
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.06152797400000054,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.06152797400000054
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0019720319999123603,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00038622000010946067,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0015858119998028997,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0015858119998028997
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 144.7306313279846,
+                                                    "count": 11004,
+                                                    "is_parallel": true,
+                                                    "self": 6.164258635984197,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 3.3917431570159806,
+                                                            "count": 11004,
+                                                            "is_parallel": true,
+                                                            "self": 3.3917431570159806
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 114.39247847900333,
+                                                            "count": 11004,
+                                                            "is_parallel": true,
+                                                            "self": 114.39247847900333
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 20.782151055981103,
+                                                            "count": 11004,
+                                                            "is_parallel": true,
+                                                            "self": 4.146583734015621,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 16.635567321965482,
+                                                                    "count": 110040,
+                                                                    "is_parallel": true,
+                                                                    "self": 16.635567321965482
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.001371276000099897,
+                    "count": 1,
+                    "self": 0.001371276000099897,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 363.6459302829876,
+                                    "count": 6012,
+                                    "is_parallel": true,
+                                    "self": 0.1291725459764166,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 56.10390000901111,
+                                            "count": 6012,
+                                            "is_parallel": true,
+                                            "self": 54.67397870901141,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 1.4299212999997053,
+                                                    "count": 8,
+                                                    "is_parallel": true,
+                                                    "self": 1.4299212999997053
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 307.41285772800006,
+                                            "count": 82,
+                                            "is_parallel": true,
+                                            "self": 152.3872712640043,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 155.02558646399575,
+                                                    "count": 7300,
+                                                    "is_parallel": true,
+                                                    "self": 155.02558646399575
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.08964358999992328,
+                    "count": 1,
+                    "self": 0.000892784999905416,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.08875080500001786,
+                            "count": 1,
+                            "self": 0.08875080500001786
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,101 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 14928,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-14928.onnx",
+                "reward": null,
+                "creation_time": 1739206708.0148225,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-14928.pt"
+                ]
+            },
+            {
+                "steps": 29944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-29944.onnx",
+                "reward": 14.5,
+                "creation_time": 1739206752.690121,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-29944.pt"
+                ]
+            },
+            {
+                "steps": 44960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-44960.onnx",
+                "reward": 15.545454545454545,
+                "creation_time": 1739206797.568683,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-44960.pt"
+                ]
+            },
+            {
+                "steps": 59976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-59976.onnx",
+                "reward": 16.5,
+                "creation_time": 1739206845.2035346,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-59976.pt"
+                ]
+            },
+            {
+                "steps": 74992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-74992.onnx",
+                "reward": 19.545454545454547,
+                "creation_time": 1739206890.7399461,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-74992.pt"
+                ]
+            },
+            {
+                "steps": 89920,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-89920.onnx",
+                "reward": null,
+                "creation_time": 1739206935.1486268,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-89920.pt"
+                ]
+            },
+            {
+                "steps": 104936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-104936.onnx",
+                "reward": 24.5,
+                "creation_time": 1739206979.6567256,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-104936.pt"
+                ]
+            },
+            {
+                "steps": 119952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-119952.onnx",
+                "reward": null,
+                "creation_time": 1739207027.254462,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-119952.pt"
+                ]
+            },
+            {
+                "steps": 120984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-120984.onnx",
+                "reward": 22.555555555555557,
+                "creation_time": 1739207027.5628595,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-120984.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 120984,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 22.555555555555557,
+            "creation_time": 1739207027.5628595,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-120984.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.6.0+cu124"
+    }
+}