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: salym/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 sha256:85a48dff334d3dcb0d19ed3820031918e269017b3352180eec61908bf393371a
+size 2867524

SnowballTarget/SnowballTarget-128.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37cf3dd85f9471c57d30c3171d20be8c3145c0832029b6ef17dd3b0c6c6df541
+size 2863606

SnowballTarget/SnowballTarget-128.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8693c49c548b835926bdd5e0d6f9150596954de47e8365e869a360bea817f7b2
+size 5712538

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:464fa4bf08f5b10a74cf6dbdf023bae08f16c46c596d550548cf659bc3e3f11a
+size 2867524

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a1d9c991a28fbca8e30d9fd64631e3309420569a54790c929d7285a1167c55
+size 17129483

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bba81252265546c8f12072f4ba80765c5d34c143c2fdba98a7d0b94b061f4e6
+size 2867524

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e00ec3b305632b7cd67d8cb7be96952f7e3aafab17a7930568c3865550ba36
+size 17129483

SnowballTarget/SnowballTarget-249880.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d5ce5069f9711a5ec5c5118c03fe6bc64b838872078d52952538d7830b2548
+size 2867524

SnowballTarget/SnowballTarget-249880.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e03f86aa4209694001f6f92fb07527fecbefe921872108895c6ba0a52e43c6
+size 17129483

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a48dff334d3dcb0d19ed3820031918e269017b3352180eec61908bf393371a
+size 2867524

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:175309d02d30b0ee9dba30f3ec9144f11429bffbf45d51a041b1ccdc021f2b1e
+size 17129483

SnowballTarget/SnowballTarget-300608.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a48dff334d3dcb0d19ed3820031918e269017b3352180eec61908bf393371a
+size 2867524

SnowballTarget/SnowballTarget-300608.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1309e40fc4a07a0a1a87c4c397f5d124e71d910561fcfc29af61c55522112d11
+size 17129483

SnowballTarget/SnowballTarget-49952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fafb60863b7cd40804c83167203f46a1bed2a75631a79dcdd83ac5bb2b7a8d2
+size 2867524

SnowballTarget/SnowballTarget-49952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567b859ffd2a0b50146e059e60351c68afa267e29f74fe846b0095c4e58e0103
+size 17129392

SnowballTarget/SnowballTarget-99896.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6444ba6a8f6ec3f3beb0ee79b45db476d248106f294821d25a143bc6ac34f49c
+size 2867524

SnowballTarget/SnowballTarget-99896.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b719f555d65ed5867dd4823613f554e59f85581b00c436acfef81ad28c85bb7
+size 17129392

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a19ea5f7ddc4ed90807aeac678cc22233051c5c8273e94d5700baa34d8cab12
+size 17128482

SnowballTarget/events.out.tfevents.1742421723.24d00c3ac542.463.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18fa22bb6807a21c5d36b60e950a566bebf778bc57fa9b41ce107e52b9a69057
+size 39595

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 1024, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 4, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "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": 300000, "time_horizon": 128, "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": false, "force": true, "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: 1024
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 4
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 3
+      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: 300000
+    time_horizon: 128
+    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: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,269 @@
+Mono path[0] = '/kaggle/working/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/kaggle/working/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 /kaggle/working/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  0.093 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: 0.703234 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 2 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]: 8062 frames, [16.0 KB-32.0 KB]: 136 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 212 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] x 2
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 3
+      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_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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 40
+    [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]: 8199 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 7.4 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 8199 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.7 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]: 7084 frames, [64.0 KB-128.0 KB]: 1115 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]: 8199 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]: 8199 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]: 8198 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]: 8199 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]: 8199 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": 2.0211870670318604,
+            "min": 2.0211870670318604,
+            "max": 2.890355110168457,
+            "count": 30
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 20632.27734375,
+            "min": 19609.34765625,
+            "max": 31793.90625,
+            "count": 30
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 299968.0,
+            "min": 9952.0,
+            "max": 299968.0,
+            "count": 30
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 299968.0,
+            "min": 9952.0,
+            "max": 299968.0,
+            "count": 30
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 6.206444263458252,
+            "min": 0.0072152577340602875,
+            "max": 6.206444263458252,
+            "count": 30
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 620.6444091796875,
+            "min": 0.7359563112258911,
+            "max": 620.6444091796875,
+            "count": 30
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 30
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 30
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 18.04,
+            "min": 2.6136363636363638,
+            "max": 18.04,
+            "count": 30
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 902.0,
+            "min": 115.0,
+            "max": 940.0,
+            "count": 30
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 18.04,
+            "min": 2.6136363636363638,
+            "max": 18.04,
+            "count": 30
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 902.0,
+            "min": 115.0,
+            "max": 940.0,
+            "count": 30
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 30
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 30
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.021776044233160975,
+            "min": 0.021257978291635025,
+            "max": 0.028197265916969628,
+            "count": 14
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.021776044233160975,
+            "min": 0.021257978291635025,
+            "max": 0.028197265916969628,
+            "count": 14
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.2791651332750916,
+            "min": 0.09541434375569224,
+            "max": 0.3243330538272858,
+            "count": 14
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.2791651332750916,
+            "min": 0.09541434375569224,
+            "max": 0.3243330538272858,
+            "count": 14
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 7.400097533333317e-06,
+            "min": 7.400097533333317e-06,
+            "max": 0.00027879200706933333,
+            "count": 14
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 7.400097533333317e-06,
+            "min": 7.400097533333317e-06,
+            "max": 0.00027879200706933333,
+            "count": 14
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10246666666666668,
+            "min": 0.10246666666666668,
+            "max": 0.19293066666666672,
+            "count": 14
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.10246666666666668,
+            "min": 0.10246666666666668,
+            "max": 0.19293066666666672,
+            "count": 14
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.00013308666666666643,
+            "min": 0.00013308666666666643,
+            "max": 0.004647240266666667,
+            "count": 14
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00013308666666666643,
+            "min": 0.00013308666666666643,
+            "max": 0.004647240266666667,
+            "count": 14
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1742421722",
+        "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 --force --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "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": "1742422279"
+    },
+    "total": 557.1427988669998,
+    "count": 1,
+    "self": 0.32937241699983133,
+    "children": {
+        "run_training.setup": {
+            "total": 0.023361000000022614,
+            "count": 1,
+            "self": 0.023361000000022614
+        },
+        "TrainerController.start_learning": {
+            "total": 556.7900654499999,
+            "count": 1,
+            "self": 0.4980271520144015,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.033088264000071,
+                    "count": 1,
+                    "self": 2.033088264000071
+                },
+                "TrainerController.advance": {
+                    "total": 554.1067161589854,
+                    "count": 27328,
+                    "self": 0.5131484539442681,
+                    "children": {
+                        "env_step": {
+                            "total": 423.3628580420036,
+                            "count": 27328,
+                            "self": 312.00436787992794,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 111.04953330206399,
+                                    "count": 27328,
+                                    "self": 1.803791116098182,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 109.24574218596581,
+                                            "count": 27328,
+                                            "self": 109.24574218596581
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.3089568600116763,
+                                    "count": 27328,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 555.4250960720055,
+                                            "count": 27328,
+                                            "is_parallel": true,
+                                            "self": 280.4062517719817,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002166887999919709,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006821630004196777,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0014847249995000311,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0014847249995000311
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.039336656000159564,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00040775800016490393,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004708569999820611,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004708569999820611
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.0371828639999876,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0371828639999876
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0012751770000249962,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00029860299900974496,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0009765740010152513,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0009765740010152513
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 275.01884430002383,
+                                                    "count": 27327,
+                                                    "is_parallel": true,
+                                                    "self": 11.418572458020208,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 6.42339337799649,
+                                                            "count": 27327,
+                                                            "is_parallel": true,
+                                                            "self": 6.42339337799649
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 218.12262301996043,
+                                                            "count": 27327,
+                                                            "is_parallel": true,
+                                                            "self": 218.12262301996043
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 39.0542554440467,
+                                                            "count": 27327,
+                                                            "is_parallel": true,
+                                                            "self": 7.3725552941059505,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 31.681700149940752,
+                                                                    "count": 273270,
+                                                                    "is_parallel": true,
+                                                                    "self": 31.681700149940752
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 130.2307096630375,
+                            "count": 27328,
+                            "self": 0.6010766931067337,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 31.85877447093071,
+                                    "count": 27328,
+                                    "self": 30.862882198930947,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.9958922719997645,
+                                            "count": 6,
+                                            "self": 0.9958922719997645
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 97.77085849900004,
+                                    "count": 14,
+                                    "self": 72.12570073999541,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 25.645157759004633,
+                                            "count": 1120,
+                                            "self": 25.645157759004633
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 8.649999472254422e-07,
+                    "count": 1,
+                    "self": 8.649999472254422e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.15223301000014544,
+                    "count": 1,
+                    "self": 0.0033827040001597197,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.14885030599998572,
+                            "count": 1,
+                            "self": 0.14885030599998572
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,83 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 49952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49952.onnx",
+                "reward": 6.2,
+                "creation_time": 1742421814.8899975,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49952.pt"
+                ]
+            },
+            {
+                "steps": 99896,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.onnx",
+                "reward": 8.623376623376624,
+                "creation_time": 1742421904.8023248,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 11.454545454545455,
+                "creation_time": 1742422002.4064312,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 14.253968253968255,
+                "creation_time": 1742422091.2790582,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 249880,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249880.onnx",
+                "reward": 16.11111111111111,
+                "creation_time": 1742422181.0064538,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249880.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 17.96969696969697,
+                "creation_time": 1742422279.3280458,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 300608,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.onnx",
+                "reward": 17.96969696969697,
+                "creation_time": 1742422279.5442076,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 300608,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 17.96969696969697,
+            "creation_time": 1742422279.5442076,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.6.0+cu124"
+    }
+}