First Push

README.md

@@ -1,3 +1,35 @@
 ---
-license: unknown
+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: ExusBurn/Pyramids
+  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:c23b69809fba8f215b2340744654eea85e81764c20453eba15e7c2ee5e600f77
+size 650646

SnowballTarget/SnowballTarget-219992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975008f144c64db8f74f46e18965e34b694af6f682f71fb1b94e699ae966f4ac
+size 650646

SnowballTarget/SnowballTarget-219992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1791d33a81ef5f815b83eb59cf118fef4126059950ed24dd9cb118ee90c50312
+size 3850075

SnowballTarget/SnowballTarget-229952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aea9e5d9b79468d3a0d6a1aff70b5e0a0d51ee72196ebeb02d1b22301b8c2dc
+size 650646

SnowballTarget/SnowballTarget-229952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee2c8913fd1d36f5fabbfa8abb6316059bc87883992e78faf70411b3dcd531c
+size 3850075

SnowballTarget/SnowballTarget-239992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a04d7aabe0205143a742f70dddb31fafcdb3d51fdb661984e04b381b75dd8735
+size 650646

SnowballTarget/SnowballTarget-239992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4586df19a45f1389066b68191baba0526b8be7b3379459f944fc944ee8323fac
+size 3850075

SnowballTarget/SnowballTarget-249944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3611b8d0312e87ccdb44ee87b632097b9cc30b8a07e3ab6dfed85071953a318
+size 650646

SnowballTarget/SnowballTarget-249944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a81bc525d532f15f92ca00679696c4636d1eb976720249774646e672064dfc7
+size 3850075

SnowballTarget/SnowballTarget-259984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00bb1e047f8daa867c11fe879c9c5577cb1b6c361b272b427e25f1ae0ef3572c
+size 650646

SnowballTarget/SnowballTarget-259984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b3123a6dc9a48f1f59e7705bee544a91f40f26e9ba2ea74256496d6cf6fe76d
+size 3850075

SnowballTarget/SnowballTarget-269936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ff3717b699565e7095810a2a963fe903ed045cf37430513bc469fc74a398ab
+size 650646

SnowballTarget/SnowballTarget-269936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d90cbf374d85bc543fe9fe9d0020edb93c27aa106f047948221742e05fa352
+size 3850075

SnowballTarget/SnowballTarget-279976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c665d01ef9c3257b68bcf51540910610c3689beac92b2468109de8f880b7278a
+size 650646

SnowballTarget/SnowballTarget-279976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44022a073ed6653e6991db1bc68efe60327ae96e03406cefc50c0f65ac48c5de
+size 3850075

SnowballTarget/SnowballTarget-289992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee354fecc41eb9f311ce0a730709fdac83881f365cd16eca3390523f79b327c
+size 650646

SnowballTarget/SnowballTarget-289992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e3c32e59ed848296e355a54e9b94671ef3843ec1f31de25ec90544b374f679
+size 3850075

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c23b69809fba8f215b2340744654eea85e81764c20453eba15e7c2ee5e600f77
+size 650646

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474b5bbcfe363b3cd719dd07d3cbd860aa98f6127fd357935a0b46203c568b5a
+size 3850075

SnowballTarget/SnowballTarget-300608.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c23b69809fba8f215b2340744654eea85e81764c20453eba15e7c2ee5e600f77
+size 650646

SnowballTarget/SnowballTarget-300608.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc85f9091623b7b6512245675147d0b295e59aee8eddec17fa0455150962ac46
+size 3850075

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e736298c9fa22544c0a843668ff82b1441592944f56b313a4591bd5a51a341eb
+size 3849250

SnowballTarget/events.out.tfevents.1709622541.6d83d588a2e4.2030.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5f2e2a81d0b85bfcf3d68268253a6794946b79b31b551854004447883a0e73
+size 41762

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "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": 10000, "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": 300000, "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": "SnowballTarget1", "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: 128
+      buffer_size: 2048
+      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: 10000
+    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: 300000
+    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: SnowballTarget1
+  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 +1,262 @@
+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'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
+Unable to load player prefs
+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  0.088 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: 0.673522 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]: 8063 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 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 44
+    [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]: 8200 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]: 8200 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]: 7287 frames, [64.0 KB-128.0 KB]: 913 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]: 8200 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]: 8200 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]: 8199 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]: 8200 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]: 8200 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": 0.8302021026611328,
+            "min": 0.8302021026611328,
+            "max": 2.8782455921173096,
+            "count": 30
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 8520.3642578125,
+            "min": 8240.2080078125,
+            "max": 29507.7734375,
+            "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": 13.184460639953613,
+            "min": 0.35725894570350647,
+            "max": 13.18896198272705,
+            "count": 30
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2689.6298828125,
+            "min": 69.30823516845703,
+            "max": 2696.407470703125,
+            "count": 30
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 30
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 30
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07016346581846901,
+            "min": 0.06261018357261883,
+            "max": 0.07606870673172286,
+            "count": 30
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.35081732909234503,
+            "min": 0.2504407342904753,
+            "max": 0.3803435336586143,
+            "count": 30
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.19849070842359579,
+            "min": 0.13108704224406909,
+            "max": 0.2855049737674349,
+            "count": 30
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.992453542117979,
+            "min": 0.5243481689762763,
+            "max": 1.3212304509737913,
+            "count": 30
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 3.5254315706666646e-06,
+            "min": 3.5254315706666646e-06,
+            "max": 0.00019639200180400005,
+            "count": 30
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 1.7627157853333323e-05,
+            "min": 1.7627157853333323e-05,
+            "max": 0.00094896002552,
+            "count": 30
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10176266666666667,
+            "min": 0.10176266666666667,
+            "max": 0.198196,
+            "count": 30
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5088133333333333,
+            "min": 0.42025066666666666,
+            "max": 0.97448,
+            "count": 30
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 9.795706666666662e-05,
+            "min": 9.795706666666662e-05,
+            "max": 0.0049099804000000006,
+            "count": 30
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0004897853333333331,
+            "min": 0.0004897853333333331,
+            "max": 0.023726551999999998,
+            "count": 30
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.6,
+            "min": 3.2954545454545454,
+            "max": 26.054545454545455,
+            "count": 30
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1408.0,
+            "min": 145.0,
+            "max": 1433.0,
+            "count": 30
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.6,
+            "min": 3.2954545454545454,
+            "max": 26.054545454545455,
+            "count": 30
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1408.0,
+            "min": 145.0,
+            "max": 1433.0,
+            "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
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1709622540",
+        "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=SnowballTarget1 --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": "1709623177"
+    },
+    "total": 636.9537627970001,
+    "count": 1,
+    "self": 0.43438160400012293,
+    "children": {
+        "run_training.setup": {
+            "total": 0.04906087699998807,
+            "count": 1,
+            "self": 0.04906087699998807
+        },
+        "TrainerController.start_learning": {
+            "total": 636.470320316,
+            "count": 1,
+            "self": 0.8182911329979561,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.3064533680000068,
+                    "count": 1,
+                    "self": 3.3064533680000068
+                },
+                "TrainerController.advance": {
+                    "total": 632.2536601190021,
+                    "count": 27332,
+                    "self": 0.3724649230008481,
+                    "children": {
+                        "env_step": {
+                            "total": 631.8811951960013,
+                            "count": 27332,
+                            "self": 405.44968545097475,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 226.02945619701836,
+                                    "count": 27332,
+                                    "self": 2.0867117090122633,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 223.9427444880061,
+                                            "count": 27332,
+                                            "self": 223.9427444880061
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.40205354800815485,
+                                    "count": 27332,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 634.910365822011,
+                                            "count": 27332,
+                                            "is_parallel": true,
+                                            "self": 317.3698741610138,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.005236830000001191,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0036111739998432313,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.00162565600015796,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00162565600015796
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03809372499995334,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007135779999316583,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00040767100000493883,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00040767100000493883
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03487212499999259,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03487212499999259
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0021003510000241477,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00046960100002024774,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0016307500000039,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0016307500000039
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 317.54049166099725,
+                                                    "count": 27331,
+                                                    "is_parallel": true,
+                                                    "self": 15.619649653011379,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 7.713544319001812,
+                                                            "count": 27331,
+                                                            "is_parallel": true,
+                                                            "self": 7.713544319001812
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 245.71628289900127,
+                                                            "count": 27331,
+                                                            "is_parallel": true,
+                                                            "self": 245.71628289900127
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 48.491014789982785,
+                                                            "count": 27331,
+                                                            "is_parallel": true,
+                                                            "self": 8.843670360015153,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 39.64734442996763,
+                                                                    "count": 273310,
+                                                                    "is_parallel": true,
+                                                                    "self": 39.64734442996763
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0004568059998746321,
+                    "count": 1,
+                    "self": 0.0004568059998746321,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 624.5793353869763,
+                                    "count": 962887,
+                                    "is_parallel": true,
+                                    "self": 20.048923227022442,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 345.28379113595355,
+                                            "count": 962887,
+                                            "is_parallel": true,
+                                            "self": 340.95320233995335,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 4.3305887960002,
+                                                    "count": 30,
+                                                    "is_parallel": true,
+                                                    "self": 4.3305887960002
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 259.2466210240002,
+                                            "count": 136,
+                                            "is_parallel": true,
+                                            "self": 76.02750755398978,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 183.21911347001043,
+                                                    "count": 6933,
+                                                    "is_parallel": true,
+                                                    "self": 183.21911347001043
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.09145889000001262,
+                    "count": 1,
+                    "self": 0.0010628370000631548,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.09039605299994946,
+                            "count": 1,
+                            "self": 0.09039605299994946
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 219992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-219992.onnx",
+                "reward": 24.3,
+                "creation_time": 1709623009.630262,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-219992.pt"
+                ]
+            },
+            {
+                "steps": 229952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-229952.onnx",
+                "reward": 24.90909090909091,
+                "creation_time": 1709623028.8604286,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-229952.pt"
+                ]
+            },
+            {
+                "steps": 239992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-239992.onnx",
+                "reward": 25.454545454545453,
+                "creation_time": 1709623050.564408,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-239992.pt"
+                ]
+            },
+            {
+                "steps": 249944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
+                "reward": 24.90909090909091,
+                "creation_time": 1709623070.6402118,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
+                ]
+            },
+            {
+                "steps": 259984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-259984.onnx",
+                "reward": 26.818181818181817,
+                "creation_time": 1709623092.1867228,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-259984.pt"
+                ]
+            },
+            {
+                "steps": 269936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-269936.onnx",
+                "reward": 25.90909090909091,
+                "creation_time": 1709623113.0352645,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-269936.pt"
+                ]
+            },
+            {
+                "steps": 279976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-279976.onnx",
+                "reward": 26.272727272727273,
+                "creation_time": 1709623134.16969,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-279976.pt"
+                ]
+            },
+            {
+                "steps": 289992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-289992.onnx",
+                "reward": 25.454545454545453,
+                "creation_time": 1709623154.7998548,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-289992.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 25.363636363636363,
+                "creation_time": 1709623176.864819,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 300608,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.onnx",
+                "reward": 25.363636363636363,
+                "creation_time": 1709623177.0242183,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 300608,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 25.363636363636363,
+            "creation_time": 1709623177.0242183,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.1+cu121"
+    }
+}