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: pepijn223/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:fcf6e3a3a7f489b50c266d1825fd07a81931ce90f74d2a86df1915bceb682d9c
+size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7e234c60399e3ac2e205041aaeaf9e5f2ecbf8ab9b0a8d9b01daf0d6d22cc58
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054bc5ebce8432997c9eff24c25c7f1b44e9711eb89239bc46ede9b8c2bd7955
+size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e9465ee920dec00fb468611e9d832094b52b6a413ca483af8e0516cdfbcc56
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b5fd0beb086bf205e5992e7313e53feaea6debd345c578bdceadad8f98e697
+size 3850075

SnowballTarget/SnowballTarget-249944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c667403f34c5f06ece5f1299db0d0da50904bf2842049e27ac05d673f2e59cb7
+size 650646

SnowballTarget/SnowballTarget-249944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911d718a027e74a14a0593017c6d7f8f27b5285bb2583c5ceae998897d48d6ec
+size 3850075

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3d9f8a05572e880e8007c03b5f75bd8f20aac0229b799210c09e94bd0054b1
+size 650646

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0413abe69f29a19aa5dee2b65d4c750fffc575e9065ecf12e266081f8d1500
+size 3850075

SnowballTarget/SnowballTarget-349992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa73a32561662a537e0a30eeac8ec60692b94e2c7df72abb3ff1235129663d4
+size 650646

SnowballTarget/SnowballTarget-349992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42761c946c5beb425bb4cac9276c4d349b7f1a57d7fb881d45b626dd110e7100
+size 3850075

SnowballTarget/SnowballTarget-399992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7d014630e6134a2716970a6a920cdab6de6349b8bca702d5963a8702abfb46
+size 650646

SnowballTarget/SnowballTarget-399992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ab93836ad229f1a13c5ee5159c81cad1699857d5244add14dba654734792d01
+size 3850075

SnowballTarget/SnowballTarget-449952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c613979ce6605d482da4cff2dec81c5ae22fe26ce696b93db0c4dc912e8231
+size 650646

SnowballTarget/SnowballTarget-449952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:061681f169c5ae182b857810d17d00b512131e185b92a42df7f4aa8d0a1754fd
+size 3850075

SnowballTarget/SnowballTarget-499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcf6e3a3a7f489b50c266d1825fd07a81931ce90f74d2a86df1915bceb682d9c
+size 650646

SnowballTarget/SnowballTarget-499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b9797ce065df5ba85fbf7ce9e67d44e416a18a61cb98eb0d019333fb13b7e7
+size 3850075

SnowballTarget/SnowballTarget-500104.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcf6e3a3a7f489b50c266d1825fd07a81931ce90f74d2a86df1915bceb682d9c
+size 650646

SnowballTarget/SnowballTarget-500104.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:876b9b9c55cb6cf2067187bdacc211afbc3ecd001bb93fe4583490b3bfc17268
+size 3850075

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0336c4d2b95ec48a411341b86060e1f6364101657ee4773b41c4771eb5deab
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161bcafe106fc58483c58cef1298c06ac6c7a912155c85f46224fd1dd574b51e
+size 3850000

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5254445be5348b647096e6957e8842293cf40b76bc34e66b8063cbb28af981
+size 3849250

SnowballTarget/events.out.tfevents.1711044302.eea0f32c46ee.3066.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bcfc170d70fa94dc0c9593955b85a7ba588b332fd09bd1a5dd21b78d14428c1
+size 53777

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 4096, "learning_rate": 0.0002, "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": 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": "SnowballTarget2", "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 +1,79 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 256
+      buffer_size: 4096
+      learning_rate: 0.0002
+      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: 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: SnowballTarget2
+  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 +1,259 @@
+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  0.085 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: 0.666076 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]: 13413 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 38
+    [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]: 11982 frames, [8.0 MB-16.0 MB]: 1659 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]: 13641 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]: 11949 frames, [64.0 KB-128.0 KB]: 1692 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 67.6 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13641 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]: 13641 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]: 13640 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]: 13641 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]: 13641 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 +1,377 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.7020861506462097,
+            "min": 0.6678435802459717,
+            "max": 2.8831870555877686,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 6757.5791015625,
+            "min": 6444.51953125,
+            "max": 29558.43359375,
+            "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": 13.336587905883789,
+            "min": 0.18719394505023956,
+            "max": 13.336587905883789,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2734.00048828125,
+            "min": 36.31562423706055,
+            "max": 2734.00048828125,
+            "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": 26.836363636363636,
+            "min": 2.7954545454545454,
+            "max": 26.836363636363636,
+            "count": 50
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1476.0,
+            "min": 123.0,
+            "max": 1476.0,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.836363636363636,
+            "min": 2.7954545454545454,
+            "max": 26.836363636363636,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1476.0,
+            "min": 123.0,
+            "max": 1476.0,
+            "count": 50
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.047200521688757685,
+            "min": 0.04239615694214259,
+            "max": 0.054719337602899244,
+            "count": 50
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.09440104337751537,
+            "min": 0.08479231388428518,
+            "max": 0.15949399426451646,
+            "count": 50
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.18662139013701795,
+            "min": 0.10040532296760848,
+            "max": 0.2904681044758535,
+            "count": 50
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.3732427802740359,
+            "min": 0.20081064593521697,
+            "max": 0.7973586485775954,
+            "count": 50
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 2.3168988415999968e-06,
+            "min": 2.3168988415999968e-06,
+            "max": 0.00019739520130240002,
+            "count": 50
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 4.6337976831999935e-06,
+            "min": 4.6337976831999935e-06,
+            "max": 0.0005578656210672001,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10115840000000001,
+            "min": 0.10115840000000001,
+            "max": 0.1986976,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.20231680000000002,
+            "min": 0.20231680000000002,
+            "max": 0.5789328,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 6.780415999999992e-05,
+            "min": 6.780415999999992e-05,
+            "max": 0.00493501024,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00013560831999999984,
+            "min": 0.00013560831999999984,
+            "max": 0.013948746719999999,
+            "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": "1711044301",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1711045420"
+    },
+    "total": 1118.750854547,
+    "count": 1,
+    "self": 0.43801781099978143,
+    "children": {
+        "run_training.setup": {
+            "total": 0.04916694400003507,
+            "count": 1,
+            "self": 0.04916694400003507
+        },
+        "TrainerController.start_learning": {
+            "total": 1118.2636697920002,
+            "count": 1,
+            "self": 1.4661858929728169,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.8830164830000058,
+                    "count": 1,
+                    "self": 1.8830164830000058
+                },
+                "TrainerController.advance": {
+                    "total": 1114.8195225490272,
+                    "count": 45470,
+                    "self": 0.7584348530565421,
+                    "children": {
+                        "env_step": {
+                            "total": 1114.0610876959706,
+                            "count": 45470,
+                            "self": 733.2629173839914,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 380.04217328998106,
+                                    "count": 45470,
+                                    "self": 3.730284889943391,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 376.3118884000377,
+                                            "count": 45470,
+                                            "self": 376.3118884000377
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.7559970219981551,
+                                    "count": 45470,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1115.3382256719876,
+                                            "count": 45470,
+                                            "is_parallel": true,
+                                            "self": 545.0718076479881,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002339527000003727,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006865989997777433,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0016529280002259839,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0016529280002259839
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03961121199995432,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007222459998956765,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004383579999966969,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004383579999966969
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.036403407000079824,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.036403407000079824
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.002047200999982124,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00037907400007952674,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0016681269999025972,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0016681269999025972
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 570.2664180239996,
+                                                    "count": 45469,
+                                                    "is_parallel": true,
+                                                    "self": 26.367805365059326,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 14.053239061987483,
+                                                            "count": 45469,
+                                                            "is_parallel": true,
+                                                            "self": 14.053239061987483
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 441.8863037679773,
+                                                            "count": 45469,
+                                                            "is_parallel": true,
+                                                            "self": 441.8863037679773
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 87.95906982897543,
+                                                            "count": 45469,
+                                                            "is_parallel": true,
+                                                            "self": 16.670341911956257,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 71.28872791701917,
+                                                                    "count": 454690,
+                                                                    "is_parallel": true,
+                                                                    "self": 71.28872791701917
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00013695000006919145,
+                    "count": 1,
+                    "self": 0.00013695000006919145,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 1095.3698110068633,
+                                    "count": 2269254,
+                                    "is_parallel": true,
+                                    "self": 49.2096337677533,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 758.5563139661089,
+                                            "count": 2269254,
+                                            "is_parallel": true,
+                                            "self": 757.0495027791085,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 1.5068111870003804,
+                                                    "count": 10,
+                                                    "is_parallel": true,
+                                                    "self": 1.5068111870003804
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 287.603863273001,
+                                            "count": 113,
+                                            "is_parallel": true,
+                                            "self": 120.49240809699677,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 167.11145517600426,
+                                                    "count": 5748,
+                                                    "is_parallel": true,
+                                                    "self": 167.11145517600426
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.09480791700002555,
+                    "count": 1,
+                    "self": 0.000970894000147382,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.09383702299987817,
+                            "count": 1,
+                            "self": 0.09383702299987817
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 15.363636363636363,
+                "creation_time": 1711044532.3028293,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 20.181818181818183,
+                "creation_time": 1711044644.4342504,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 22.727272727272727,
+                "creation_time": 1711044753.8071804,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 249944,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-249944.onnx",
+                "reward": 24.59090909090909,
+                "creation_time": 1711044862.929963,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-249944.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1711044973.91618,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 349992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-349992.onnx",
+                "reward": 24.863636363636363,
+                "creation_time": 1711045081.330221,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-349992.pt"
+                ]
+            },
+            {
+                "steps": 399992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-399992.onnx",
+                "reward": null,
+                "creation_time": 1711045193.4048097,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-399992.pt"
+                ]
+            },
+            {
+                "steps": 449952,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-449952.onnx",
+                "reward": 25.09090909090909,
+                "creation_time": 1711045305.3887954,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-449952.pt"
+                ]
+            },
+            {
+                "steps": 499976,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-499976.onnx",
+                "reward": 26.90909090909091,
+                "creation_time": 1711045420.0019343,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-499976.pt"
+                ]
+            },
+            {
+                "steps": 500104,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-500104.onnx",
+                "reward": 26.90909090909091,
+                "creation_time": 1711045420.122263,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-500104.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 500104,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 26.90909090909091,
+            "creation_time": 1711045420.122263,
+            "auxillary_file_paths": [
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-500104.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.1+cu121"
+    }
+}