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: dhinman/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 sha256:6b927fddc60280623862db647914b8f1163814cd5d3788229021e400fe4bee9f
+size 646532

SnowballTarget/SnowballTarget-1599976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8549354369f1a4a2789246f2384c0336b108f3557befbbc1d33b24af2540e523
+size 646532

SnowballTarget/SnowballTarget-1599976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8675aa75f7f980fd7d7e262a5fbaf2d72f837053615a08ceed3206ab8dff0f3f
+size 3843968

SnowballTarget/SnowballTarget-1649992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e6a74b335e1f41aff7c0f2bc5d69fe2b87a3a053db374bf8f97edf2dd73a62
+size 646532

SnowballTarget/SnowballTarget-1649992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6deb5a9e980b47f32e0d0b2492553e42754ebc647cb3f6519758a54c9db5fa1b
+size 3843968

SnowballTarget/SnowballTarget-1699936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09ffcd21a9b487768a83b1f21a0153e31fd08e153162cfa7fd1cbde51851711
+size 646532

SnowballTarget/SnowballTarget-1699936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f24b4a025fa5a4640a378dccc0fed42f8d1afc19b992135d329a5ecf8e27018
+size 3843968

SnowballTarget/SnowballTarget-1749960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f30638978e93a3de8f532d88c87ad6c8814b5f63a78da2f1cd59140ebc605a
+size 646532

SnowballTarget/SnowballTarget-1749960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d77e7118336140e35a742c4a10a64152b7b6e4a933ba0d202739b0361ff812f
+size 3843968

SnowballTarget/SnowballTarget-1799984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f18ea1b8eb172d4f190cb9320c538a2cbea2fb21b2bd5cd31be4202cdd508c9
+size 646532

SnowballTarget/SnowballTarget-1799984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c508547647e8ce4ae5c3c1f7f265bbce2d55b926b50837e12cfa3f34110e68a2
+size 3843968

SnowballTarget/SnowballTarget-1849984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b6939b848a6824545c0d81fc26482aa9375bb877d2d4cbad856bd20436b48b
+size 646532

SnowballTarget/SnowballTarget-1849984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a9bbafee67f61156f4472ff334f46c6229f47cd2618a96dda4764498b654f8
+size 3843968

SnowballTarget/SnowballTarget-1899944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9748d94a0d2eeab9061beed29bd01044bc67e2cf8d3e9d8823e8fe36128f4d3e
+size 646532

SnowballTarget/SnowballTarget-1899944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b5aa4f51360e9220a01604ff2b1b7118dbccf74f2b70f63654cbf5c22acef10
+size 3843968

SnowballTarget/SnowballTarget-1949968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ebfa1b1460fb1eff4149e10a1f0c8f63b4eab5afbb685be1f7042b66819759
+size 646532

SnowballTarget/SnowballTarget-1949968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61abb0b28624e7655e43e91e81fa79d38fa530bc40f316a577bfdd499fafc5cd
+size 3843968

SnowballTarget/SnowballTarget-1999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b927fddc60280623862db647914b8f1163814cd5d3788229021e400fe4bee9f
+size 646532

SnowballTarget/SnowballTarget-1999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680c09f14f010648739eae032597f0be140388461df30fea56d5a2a4d18347ba
+size 3843968

SnowballTarget/SnowballTarget-2000376.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b927fddc60280623862db647914b8f1163814cd5d3788229021e400fe4bee9f
+size 646532

SnowballTarget/SnowballTarget-2000376.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96dfcfcaee569ad3fd57fd9e47e57c5958b0433f50989637b82395632af826a3
+size 3843968

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96dfcfcaee569ad3fd57fd9e47e57c5958b0433f50989637b82395632af826a3
+size 3843968

SnowballTarget/events.out.tfevents.1691753276.c56a43b90ae1.2755.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542ddc0ba2f0ca7d475085619157aafb40aefc820996c859a70f5d2b4bd4db20
+size 170721

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": 2000000, "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, "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}, "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 +1,77 @@
+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: 2000000
+    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
+  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
+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  0.084 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: 0.686706 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]: 53652 frames, [16.0 KB-32.0 KB]: 909 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 45
+    [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]: 11142 frames, [8.0 MB-16.0 MB]: 28285 frames, [16.0 MB-32.0 MB]: 15135 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 24.3 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 54562 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]: 52726 frames, [64.0 KB-128.0 KB]: 1836 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 67.3 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 54562 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]: 54562 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]: 54561 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]: 54562 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]: 54562 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": 0.4351891577243805,
+            "min": 0.4124315679073334,
+            "max": 2.8701202869415283,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 4475.92041015625,
+            "min": 4037.46240234375,
+            "max": 29392.90234375,
+            "count": 200
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 1999992.0,
+            "min": 9952.0,
+            "max": 1999992.0,
+            "count": 200
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 1999992.0,
+            "min": 9952.0,
+            "max": 1999992.0,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 14.28770923614502,
+            "min": 0.2245347946882248,
+            "max": 14.431157112121582,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2928.98046875,
+            "min": 43.559749603271484,
+            "max": 2952.845703125,
+            "count": 200
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 200
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 200
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.0699265562830203,
+            "min": 0.06112103356951824,
+            "max": 0.0775976367634333,
+            "count": 200
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.3496327814151015,
+            "min": 0.24448413427807297,
+            "max": 0.3879881838171665,
+            "count": 200
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.1627186337522432,
+            "min": 0.11146447093308193,
+            "max": 0.26447473488309803,
+            "count": 200
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.813593168761216,
+            "min": 0.4458578837323277,
+            "max": 1.2789767162472594,
+            "count": 200
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 7.032997656000039e-07,
+            "min": 7.032997656000039e-07,
+            "max": 0.00029918820027059994,
+            "count": 200
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.5164988280000196e-06,
+            "min": 3.5164988280000196e-06,
+            "max": 0.0014885160038279998,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10023440000000002,
+            "min": 0.10023440000000002,
+            "max": 0.1997294,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5011720000000001,
+            "min": 0.4029176,
+            "max": 0.996172,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 2.1696560000000067e-05,
+            "min": 2.1696560000000067e-05,
+            "max": 0.004986497059999999,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00010848280000000034,
+            "min": 0.00010848280000000034,
+            "max": 0.024808982800000004,
+            "count": 200
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 27.836363636363636,
+            "min": 3.2045454545454546,
+            "max": 28.59090909090909,
+            "count": 200
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1531.0,
+            "min": 141.0,
+            "max": 1566.0,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 27.836363636363636,
+            "min": 3.2045454545454546,
+            "max": 28.59090909090909,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1531.0,
+            "min": 141.0,
+            "max": 1566.0,
+            "count": 200
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1691753275",
+        "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1691758072"
+    },
+    "total": 4797.353921215001,
+    "count": 1,
+    "self": 0.48705223700017086,
+    "children": {
+        "run_training.setup": {
+            "total": 0.0430377640000188,
+            "count": 1,
+            "self": 0.0430377640000188
+        },
+        "TrainerController.start_learning": {
+            "total": 4796.823831214,
+            "count": 1,
+            "self": 5.9265866639343585,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.720287638999935,
+                    "count": 1,
+                    "self": 4.720287638999935
+                },
+                "TrainerController.advance": {
+                    "total": 4786.035077367066,
+                    "count": 181872,
+                    "self": 2.8701099820254967,
+                    "children": {
+                        "env_step": {
+                            "total": 4783.164967385041,
+                            "count": 181872,
+                            "self": 3493.4310696112893,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1286.7908276269527,
+                                    "count": 181872,
+                                    "self": 18.777313051831698,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1268.013514575121,
+                                            "count": 181872,
+                                            "self": 1268.013514575121
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.9430701467985045,
+                                    "count": 181872,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 4781.1309507520855,
+                                            "count": 181872,
+                                            "is_parallel": true,
+                                            "self": 2244.634284836039,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.009122021000052882,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.007517592999988665,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0016044280000642175,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0016044280000642175
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.07782980299998599,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006065569999691434,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003981920000342143,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003981920000342143
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.07463931899997078,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.07463931899997078
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.002185735000011846,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003915009998536334,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0017942340001582124,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0017942340001582124
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 2536.4966659160464,
+                                                    "count": 181871,
+                                                    "is_parallel": true,
+                                                    "self": 107.16965771905052,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 53.56370950306939,
+                                                            "count": 181871,
+                                                            "is_parallel": true,
+                                                            "self": 53.56370950306939
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2010.717184664041,
+                                                            "count": 181871,
+                                                            "is_parallel": true,
+                                                            "self": 2010.717184664041
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 365.0461140298853,
+                                                            "count": 181871,
+                                                            "is_parallel": true,
+                                                            "self": 67.54184858460121,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 297.5042654452841,
+                                                                    "count": 1818710,
+                                                                    "is_parallel": true,
+                                                                    "self": 297.5042654452841
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0003264699998908327,
+                    "count": 1,
+                    "self": 0.0003264699998908327,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 4748.895687837884,
+                                    "count": 4393645,
+                                    "is_parallel": true,
+                                    "self": 96.52607736498157,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 2576.4395320578965,
+                                            "count": 4393645,
+                                            "is_parallel": true,
+                                            "self": 2561.9673742028976,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 14.472157854998727,
+                                                    "count": 40,
+                                                    "is_parallel": true,
+                                                    "self": 14.472157854998727
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 2075.9300784150055,
+                                            "count": 909,
+                                            "is_parallel": true,
+                                            "self": 824.9928528110536,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 1250.937225603952,
+                                                    "count": 46347,
+                                                    "is_parallel": true,
+                                                    "self": 1250.937225603952
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.14155307399960293,
+                    "count": 1,
+                    "self": 0.0009410039992872044,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.14061207000031573,
+                            "count": 1,
+                            "self": 0.14061207000031573
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 1599976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599976.onnx",
+                "reward": 27.727272727272727,
+                "creation_time": 1691757093.909787,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599976.pt"
+                ]
+            },
+            {
+                "steps": 1649992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649992.onnx",
+                "reward": 27.4,
+                "creation_time": 1691757217.1013343,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649992.pt"
+                ]
+            },
+            {
+                "steps": 1699936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699936.onnx",
+                "reward": 27.363636363636363,
+                "creation_time": 1691757330.673281,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699936.pt"
+                ]
+            },
+            {
+                "steps": 1749960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749960.onnx",
+                "reward": 28.545454545454547,
+                "creation_time": 1691757452.280837,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749960.pt"
+                ]
+            },
+            {
+                "steps": 1799984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799984.onnx",
+                "reward": 28.363636363636363,
+                "creation_time": 1691757575.7134864,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799984.pt"
+                ]
+            },
+            {
+                "steps": 1849984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849984.onnx",
+                "reward": 27.90909090909091,
+                "creation_time": 1691757699.5912766,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849984.pt"
+                ]
+            },
+            {
+                "steps": 1899944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899944.onnx",
+                "reward": 27.90909090909091,
+                "creation_time": 1691757823.7682006,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899944.pt"
+                ]
+            },
+            {
+                "steps": 1949968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949968.onnx",
+                "reward": 28.90909090909091,
+                "creation_time": 1691757948.1482708,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949968.pt"
+                ]
+            },
+            {
+                "steps": 1999992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999992.onnx",
+                "reward": 27.818181818181817,
+                "creation_time": 1691758071.6968732,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999992.pt"
+                ]
+            },
+            {
+                "steps": 2000376,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000376.onnx",
+                "reward": 27.818181818181817,
+                "creation_time": 1691758071.8877933,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000376.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 2000376,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 27.818181818181817,
+            "creation_time": 1691758071.8877933,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000376.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}