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: amanoyaku/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 sha256:216536f541b3b49d9ef5f7339119f79a4f6fd23a1bcf4cdf1b227daf3b9cb58f
+size 650646

SnowballTarget/SnowballTarget-149936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d880e01fde5dc97f29e69694a2a83ddc916a052d065018d744c326d50669e2
+size 650646

SnowballTarget/SnowballTarget-149936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f84350515c036faa3c64938b52349d7668366a4e62785e08b2dd63340dd0ad
+size 3850075

SnowballTarget/SnowballTarget-199960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8e9af729f71423ecd484c4508964dcc8bfc0e849e54a12868c07964fd56b23
+size 650646

SnowballTarget/SnowballTarget-199960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ba4eccb600d4c668f1fb7026f2ca2102d939c0879736b21544dc4f3c5d22d5
+size 3850075

SnowballTarget/SnowballTarget-20480.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e11584d725ba1efe93678f4b8cd7bee26ed25aefc00e636f3b06f2cf3e0753
+size 650646

SnowballTarget/SnowballTarget-20480.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a1c677465641cd2a169ee5a0fe5cf6430f5bf4ba9a53c07605f89550b569d5
+size 3850000

SnowballTarget/SnowballTarget-249984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b48b1661555d1aa255bef2083108be39f49e8dc17087826c421492c6ea3dc5
+size 650646

SnowballTarget/SnowballTarget-249984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91737a32f8cb996c8226fc157ba65117a6d94fb2866a2b62fec940229718087d
+size 3850075

SnowballTarget/SnowballTarget-268288.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216536f541b3b49d9ef5f7339119f79a4f6fd23a1bcf4cdf1b227daf3b9cb58f
+size 650646

SnowballTarget/SnowballTarget-268288.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5c1528f8219a743d1301b363d06fdb35eb5eba16eda87ba10dec1e17a3fcb4f
+size 3850075

SnowballTarget/SnowballTarget-49976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a4995142ad5fb85c62c99b1dc5ce5417f49943b2756299fce5f7756a315197
+size 650646

SnowballTarget/SnowballTarget-49976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f7fb4f888da2c290516f818d68c7d79339ca73462d3f75c9e95b4e624f84b47
+size 3850000

SnowballTarget/SnowballTarget-64.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3368f4f37d7fe27521610470ceedfb8e41edb5a61efe4c7ceaeade5a761f9da
+size 649740

SnowballTarget/SnowballTarget-64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3860c43670d154eff51b15531f3134212822360ef6804c10f25ed4a1308dcfb8
+size 1286175

SnowballTarget/SnowballTarget-768.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3368f4f37d7fe27521610470ceedfb8e41edb5a61efe4c7ceaeade5a761f9da
+size 649740

SnowballTarget/SnowballTarget-768.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f0ed1f718b74a613581ee455d10e8203d8a64be72ff0c3676c0f4286cf35fc
+size 1286202

SnowballTarget/SnowballTarget-99936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c176bfadb68ae3714531897c933c3aeb44fda62b7cd2306744061b7cb415d15c
+size 650646

SnowballTarget/SnowballTarget-99936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b241a17a38c9639e29acc1133d757ccd5ff59130dea3b1faad02d400ab77d13
+size 3850000

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3d4d37300b04d80833cdfbde1290ad4a224c6f1ba955c62ddc3a3604d3290a
+size 3849250

SnowballTarget/events.out.tfevents.1731712144.d05eb623fe2b.1819.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0f798f0fc869c7ee9ba394b984d9646fc4937bdb54baa72e9f20c7d37bb489e
+size 1111

SnowballTarget/events.out.tfevents.1731712548.d05eb623fe2b.3632.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e379d62e2397cfe524863f37e427ec6c99143947b04bce100764a76d34420ba
+size 1111

SnowballTarget/events.out.tfevents.1731712603.d05eb623fe2b.3925.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3177ac4efa7b5f398bd5df6071979065a99ddb9e739f41f26790fe11eeefe26
+size 1112

SnowballTarget/events.out.tfevents.1731712639.d05eb623fe2b.4135.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e3b9bfc23c56f882f17a3aa4cb385c6ab852cb18a6a67aa5f5bbc7f6df5f2d
+size 8022

SnowballTarget/events.out.tfevents.1731712755.d05eb623fe2b.4682.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6df07b858cd4b5954e8a752fec09984ff9d3dc88e9649d0697ef86e9d33f56d4
+size 22547

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 700000, "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": "cuda"}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 10
+    even_checkpoints: false
+    max_steps: 700000
+    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: cuda
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,259 @@
+Mono path[0] = '/content/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/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/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  0.080 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: 0.643108 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]: 6656 frames, [16.0 KB-32.0 KB]: 112 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 178 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 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]: 6769 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 7.1 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 6769 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]: 6286 frames, [64.0 KB-128.0 KB]: 483 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.4 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 6769 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]: 6769 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]: 6768 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]: 6769 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]: 6769 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.7 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,362 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.8242748379707336,
+            "min": 0.8242748379707336,
+            "max": 2.6825032234191895,
+            "count": 24
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7833.908203125,
+            "min": 7833.908203125,
+            "max": 27382.9921875,
+            "count": 24
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 259936.0,
+            "min": 29984.0,
+            "max": 259936.0,
+            "count": 24
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 259936.0,
+            "min": 29984.0,
+            "max": 259936.0,
+            "count": 24
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.458937644958496,
+            "min": 2.1360836029052734,
+            "max": 13.458937644958496,
+            "count": 24
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2611.033935546875,
+            "min": 399.4476318359375,
+            "max": 2755.2294921875,
+            "count": 24
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06904763720579948,
+            "min": 0.06163043446063324,
+            "max": 0.07554938888514538,
+            "count": 24
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.27619054882319793,
+            "min": 0.24652173784253295,
+            "max": 0.36025234447315957,
+            "count": 24
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.19327187676932298,
+            "min": 0.19327187676932298,
+            "max": 0.29792546984903956,
+            "count": 24
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7730875070772919,
+            "min": 0.7730875070772919,
+            "max": 1.4480793026148102,
+            "count": 24
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 0.00019084632209885716,
+            "min": 0.00019084632209885716,
+            "max": 0.0002889034322702857,
+            "count": 24
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 0.0007633852883954286,
+            "min": 0.0007633852883954286,
+            "max": 0.0014044457461371428,
+            "count": 24
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.16361542857142858,
+            "min": 0.16361542857142858,
+            "max": 0.1963011428571429,
+            "count": 24
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.6544617142857143,
+            "min": 0.6544617142857143,
+            "max": 0.9681485714285716,
+            "count": 24
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.003184409885714286,
+            "min": 0.003184409885714286,
+            "max": 0.00481542702857143,
+            "count": 24
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.012737639542857143,
+            "min": 0.012737639542857143,
+            "max": 0.02341061371428571,
+            "count": 24
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 24
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 24
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.045454545454547,
+            "min": 7.590909090909091,
+            "max": 26.045454545454547,
+            "count": 24
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1146.0,
+            "min": 334.0,
+            "max": 1411.0,
+            "count": 24
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.045454545454547,
+            "min": 7.590909090909091,
+            "max": 26.045454545454547,
+            "count": 24
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1146.0,
+            "min": 334.0,
+            "max": 1411.0,
+            "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": "1731712754",
+        "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --torch-device cuda --resume",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1731713294"
+    },
+    "total": 539.61505422,
+    "count": 1,
+    "self": 0.26906913400000576,
+    "children": {
+        "run_training.setup": {
+            "total": 0.058036136000055194,
+            "count": 1,
+            "self": 0.058036136000055194
+        },
+        "TrainerController.start_learning": {
+            "total": 539.28794895,
+            "count": 1,
+            "self": 0.4362329969661687,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.9356087439999783,
+                    "count": 1,
+                    "self": 1.9356087439999783
+                },
+                "TrainerController.advance": {
+                    "total": 536.7620196090339,
+                    "count": 22563,
+                    "self": 0.4618441650176237,
+                    "children": {
+                        "env_step": {
+                            "total": 380.27504954601363,
+                            "count": 22563,
+                            "self": 289.49349043403174,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 90.51927752399763,
+                                    "count": 22563,
+                                    "self": 1.6182248720142525,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 88.90105265198338,
+                                            "count": 22563,
+                                            "self": 88.90105265198338
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.26228158798426193,
+                                    "count": 22562,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 537.7300130879993,
+                                            "count": 22562,
+                                            "is_parallel": true,
+                                            "self": 284.49012951896407,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0022845830000051137,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007333489999155063,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0015512340000896074,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0015512340000896074
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03806616999997914,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006805680000070424,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004608269999835102,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004608269999835102
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03478646899998239,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03478646899998239
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.002138306000006196,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004805200001101184,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0016577859998960776,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0016577859998960776
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 253.23988356903521,
+                                                    "count": 22561,
+                                                    "is_parallel": true,
+                                                    "self": 12.47235408805443,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 6.891570990009313,
+                                                            "count": 22561,
+                                                            "is_parallel": true,
+                                                            "self": 6.891570990009313
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 192.95240642899,
+                                                            "count": 22561,
+                                                            "is_parallel": true,
+                                                            "self": 192.95240642899
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 40.92355206198147,
+                                                            "count": 22561,
+                                                            "is_parallel": true,
+                                                            "self": 7.45475248291973,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 33.46879957906174,
+                                                                    "count": 225610,
+                                                                    "is_parallel": true,
+                                                                    "self": 33.46879957906174
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 156.02512589800267,
+                            "count": 22562,
+                            "self": 0.5257124300102305,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 35.37274289899267,
+                                    "count": 22562,
+                                    "self": 34.82233673699227,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.5504061620003995,
+                                            "count": 5,
+                                            "self": 0.5504061620003995
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 120.12667056899977,
+                                    "count": 112,
+                                    "self": 49.56214591699916,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 70.56452465200061,
+                                            "count": 5709,
+                                            "self": 70.56452465200061
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.427999904990429e-06,
+                    "count": 1,
+                    "self": 1.427999904990429e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.15408617200000663,
+                    "count": 1,
+                    "self": 0.001510591999931421,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1525755800000752,
+                            "count": 1,
+                            "self": 0.1525755800000752
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,101 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 64,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-64.onnx",
+                "reward": null,
+                "creation_time": 1731712269.5035892,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-64.pt"
+                ]
+            },
+            {
+                "steps": 768,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-768.onnx",
+                "reward": null,
+                "creation_time": 1731712606.7549987,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-768.pt"
+                ]
+            },
+            {
+                "steps": 20480,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-20480.onnx",
+                "reward": 6.545454545454546,
+                "creation_time": 1731712683.0945492,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-20480.pt"
+                ]
+            },
+            {
+                "steps": 49976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49976.onnx",
+                "reward": 12.909090909090908,
+                "creation_time": 1731712821.9121144,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49976.pt"
+                ]
+            },
+            {
+                "steps": 99936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.onnx",
+                "reward": 21.09090909090909,
+                "creation_time": 1731712931.4344592,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.pt"
+                ]
+            },
+            {
+                "steps": 149936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149936.onnx",
+                "reward": 24.545454545454547,
+                "creation_time": 1731713038.3016548,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149936.pt"
+                ]
+            },
+            {
+                "steps": 199960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1731713146.0653207,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.pt"
+                ]
+            },
+            {
+                "steps": 249984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1731713255.9924617,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
+                ]
+            },
+            {
+                "steps": 268288,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-268288.onnx",
+                "reward": 25.818181818181817,
+                "creation_time": 1731713294.2595928,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-268288.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 268288,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 25.818181818181817,
+            "creation_time": 1731713294.2595928,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-268288.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1+cu121"
+    }
+}