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: fangyima/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 sha256:3f0c96a542ec401471521d6766ae2d6efe2e4237125bc9a2ec81bbb46736d150
+size 650646

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97c81e416291761656f15cbbbc954801bb12f14cd114eec7f8b9b195c6cb3f82
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfcbf8c4f5c457c48eb21e07d25518122ed072a06545f1f984c82dc790dc7061
+size 3849115

SnowballTarget/SnowballTarget-399992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb7353514a4ff7a682b2793680f0e95bd8c227410498f0d2ce8ca03f9368d822
+size 650646

SnowballTarget/SnowballTarget-399992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4e08d7a05f15df29942f634309d5e830feeb70d1cbf9bbb2655e565798e83d9
+size 3849115

SnowballTarget/SnowballTarget-449952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a449f04efe60041f71a0ec48da5cc588e0d3ee8b928c08c3d18d1bff71a2bfbc
+size 650646

SnowballTarget/SnowballTarget-449952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0453d6186a638dea51f65232bc97211bb4de134c7e17ce2cc7181e8b2fad7928
+size 3849115

SnowballTarget/SnowballTarget-499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f73bf7111e3d31cf8b6c45ecef3b77764d584c69c7591c01837ed303ed0b9bc
+size 650646

SnowballTarget/SnowballTarget-499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f1f4f4667c57b13f143c5b8d5039bc65f0f5993d3df1e5b492bf88c4856a3ff
+size 3849115

SnowballTarget/SnowballTarget-549992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3421424d12d10628898437b80bd21f9eb041fe9d5d88266533798fbce3747fe8
+size 650646

SnowballTarget/SnowballTarget-549992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dca1477cd1f1f51328db2e07f824ec53439c17b2f53e674cc0f3a5f14c95725
+size 3849115

SnowballTarget/SnowballTarget-599936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a77da755a19d6fb8bb81d069fbea1d1d4362c792d81df1af1cecdd4901314ccf
+size 650646

SnowballTarget/SnowballTarget-599936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2415cefc6f420d8f7d3bfce7ea816de635a0426c38532f2d605d786c0d552773
+size 3849115

SnowballTarget/SnowballTarget-649960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc3e87c6c585000af41b12f9003f030971a822de4bb48e421645d50a32ae6e6
+size 650646

SnowballTarget/SnowballTarget-649960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:846d7ec8693245737ec6bb794b1779ce6f7ce0ace0a3aeeab62f2bc83acb9033
+size 3849115

SnowballTarget/SnowballTarget-699984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03b446745d83079a65323806b825d6f92147bd35ccd4d673adefba7fe3003d3b
+size 650646

SnowballTarget/SnowballTarget-699984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef6d1b66b7177a9ed075a7168f43b9531eddfb5522a3115b35e89f57467e260
+size 3849115

SnowballTarget/SnowballTarget-749984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa8c3c466de1ee26c2d7c43a0b98f07e63620fbd2f087b584f7d5310a3afbd68
+size 650646

SnowballTarget/SnowballTarget-749984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f828a95b19482ce6d200d98fa6f2fc5324f997c5530cb7c5248b39af2050e2d
+size 3849115

SnowballTarget/SnowballTarget-799944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0c96a542ec401471521d6766ae2d6efe2e4237125bc9a2ec81bbb46736d150
+size 650646

SnowballTarget/SnowballTarget-799944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa09bc9f1a001c0a0f0a46955521be20d43745d1c69fcdcd602fe25cec189bb
+size 3849115

SnowballTarget/SnowballTarget-800008.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0c96a542ec401471521d6766ae2d6efe2e4237125bc9a2ec81bbb46736d150
+size 650646

SnowballTarget/SnowballTarget-800008.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dead91cfbf8035797f27dc33067852160c917f47164f85004d4beea863660bd2
+size 3849115

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef6b51b82611394d223dcc519c2dbd6ec2bdee7d7be08f42ee89ef49cf817bc
+size 3848290

SnowballTarget/events.out.tfevents.1740847055.fe95594c5dd7.15000.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d2b1d1d18ab436bd403a2ba6618f66571a6040a01b900a41d71634a754ae34b
+size 72877

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": 800000, "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": 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: 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: 800000
+    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: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,259 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.122 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: 0.935309 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]: 21462 frames, [16.0 KB-32.0 KB]: 363 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 41
+    [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]: 11179 frames, [8.0 MB-16.0 MB]: 10647 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 13.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 21826 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]: 20576 frames, [64.0 KB-128.0 KB]: 1250 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]: 21826 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]: 21826 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]: 21825 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]: 21826 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]: 21826 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": 0.7284655570983887,
+            "min": 0.6516228318214417,
+            "max": 2.8669273853302,
+            "count": 80
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 6979.42822265625,
+            "min": 6417.11962890625,
+            "max": 29360.203125,
+            "count": 80
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 799944.0,
+            "min": 9952.0,
+            "max": 799944.0,
+            "count": 80
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 799944.0,
+            "min": 9952.0,
+            "max": 799944.0,
+            "count": 80
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.998396873474121,
+            "min": 0.4160343408584595,
+            "max": 14.025606155395508,
+            "count": 80
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2715.68896484375,
+            "min": 80.71066284179688,
+            "max": 2869.51123046875,
+            "count": 80
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 80
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 80
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07261805048248932,
+            "min": 0.057942750975352654,
+            "max": 0.07971613397510773,
+            "count": 80
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.29047220192995726,
+            "min": 0.2417547947820733,
+            "max": 0.37883085382682286,
+            "count": 80
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.16717612809118104,
+            "min": 0.12457735050360069,
+            "max": 0.2951477055310034,
+            "count": 80
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.6687045123647242,
+            "min": 0.49830940201440277,
+            "max": 1.377832377365991,
+            "count": 80
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 1.795599401499997e-06,
+            "min": 1.795599401499997e-06,
+            "max": 0.0002979705006765,
+            "count": 80
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 7.182397605999988e-06,
+            "min": 7.182397605999988e-06,
+            "max": 0.0014712900095699996,
+            "count": 80
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10059850000000001,
+            "min": 0.10059850000000001,
+            "max": 0.19932350000000001,
+            "count": 80
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.40239400000000003,
+            "min": 0.40239400000000003,
+            "max": 0.9904299999999999,
+            "count": 80
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 3.9865149999999955e-05,
+            "min": 3.9865149999999955e-05,
+            "max": 0.00496624265,
+            "count": 80
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00015946059999999982,
+            "min": 0.00015946059999999982,
+            "max": 0.024522457,
+            "count": 80
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 27.363636363636363,
+            "min": 3.340909090909091,
+            "max": 27.745454545454546,
+            "count": 80
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1204.0,
+            "min": 147.0,
+            "max": 1526.0,
+            "count": 80
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 27.363636363636363,
+            "min": 3.340909090909091,
+            "max": 27.745454545454546,
+            "count": 80
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1204.0,
+            "min": 147.0,
+            "max": 1526.0,
+            "count": 80
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 80
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 80
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1740847055",
+        "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 --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
+        "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": "1740849517"
+    },
+    "total": 2462.438581792,
+    "count": 1,
+    "self": 1.0023434469999302,
+    "children": {
+        "run_training.setup": {
+            "total": 0.030618020000019897,
+            "count": 1,
+            "self": 0.030618020000019897
+        },
+        "TrainerController.start_learning": {
+            "total": 2461.405620325,
+            "count": 1,
+            "self": 3.7951732509268368,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.3715797419999944,
+                    "count": 1,
+                    "self": 2.3715797419999944
+                },
+                "TrainerController.advance": {
+                    "total": 2455.1050870170734,
+                    "count": 72753,
+                    "self": 1.807663933004278,
+                    "children": {
+                        "env_step": {
+                            "total": 2453.297423084069,
+                            "count": 72753,
+                            "self": 1876.6934586979305,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 574.6882944080608,
+                                    "count": 72753,
+                                    "self": 10.74483610409834,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 563.9434583039624,
+                                            "count": 72753,
+                                            "self": 563.9434583039624
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.915669978077858,
+                                    "count": 72753,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2453.450717552986,
+                                            "count": 72753,
+                                            "is_parallel": true,
+                                            "self": 1167.6127296439236,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002658848000010039,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0008381720003853843,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0018206759996246547,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0018206759996246547
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.0480035619998489,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007002350002949242,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00048061899997264845,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00048061899997264845
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.04440194199969483,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.04440194199969483
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0024207659998864983,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005604559996754688,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0018603100002110295,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0018603100002110295
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1285.8379879090626,
+                                                    "count": 72752,
+                                                    "is_parallel": true,
+                                                    "self": 56.30156733117792,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 30.78118091792203,
+                                                            "count": 72752,
+                                                            "is_parallel": true,
+                                                            "self": 30.78118091792203
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1020.7059219539542,
+                                                            "count": 72752,
+                                                            "is_parallel": true,
+                                                            "self": 1020.7059219539542
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 178.04931770600842,
+                                                            "count": 72752,
+                                                            "is_parallel": true,
+                                                            "self": 35.31857717452067,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 142.73074053148775,
+                                                                    "count": 727520,
+                                                                    "is_parallel": true,
+                                                                    "self": 142.73074053148775
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00018092200025421334,
+                    "count": 1,
+                    "self": 0.00018092200025421334,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 2423.8794823976496,
+                                    "count": 3214330,
+                                    "is_parallel": true,
+                                    "self": 76.69925394358233,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 1293.5289633050702,
+                                            "count": 3214330,
+                                            "is_parallel": true,
+                                            "self": 1290.0305020260703,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 3.498461278999912,
+                                                    "count": 16,
+                                                    "is_parallel": true,
+                                                    "self": 3.498461278999912
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 1053.651265148997,
+                                            "count": 363,
+                                            "is_parallel": true,
+                                            "self": 255.19505692296707,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 798.45620822603,
+                                                    "count": 18510,
+                                                    "is_parallel": true,
+                                                    "self": 798.45620822603
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.13359939299971302,
+                    "count": 1,
+                    "self": 0.00366399700033071,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1299353959993823,
+                            "count": 1,
+                            "self": 0.1299353959993823
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 399992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
+                "reward": 26.454545454545453,
+                "creation_time": 1740848277.7547007,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
+                ]
+            },
+            {
+                "steps": 449952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
+                "reward": 26.636363636363637,
+                "creation_time": 1740848431.5081267,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
+                ]
+            },
+            {
+                "steps": 499976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
+                "reward": 27.0,
+                "creation_time": 1740848583.8659947,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
+                ]
+            },
+            {
+                "steps": 549992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-549992.onnx",
+                "reward": 27.1,
+                "creation_time": 1740848742.3250253,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-549992.pt"
+                ]
+            },
+            {
+                "steps": 599936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.onnx",
+                "reward": 26.90909090909091,
+                "creation_time": 1740848899.746278,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.pt"
+                ]
+            },
+            {
+                "steps": 649960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.onnx",
+                "reward": 26.90909090909091,
+                "creation_time": 1740849056.651358,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.pt"
+                ]
+            },
+            {
+                "steps": 699984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.onnx",
+                "reward": 27.363636363636363,
+                "creation_time": 1740849210.507638,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.pt"
+                ]
+            },
+            {
+                "steps": 749984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.onnx",
+                "reward": 26.90909090909091,
+                "creation_time": 1740849363.380081,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.pt"
+                ]
+            },
+            {
+                "steps": 799944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.onnx",
+                "reward": 27.636363636363637,
+                "creation_time": 1740849516.4676876,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.pt"
+                ]
+            },
+            {
+                "steps": 800008,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-800008.onnx",
+                "reward": 27.636363636363637,
+                "creation_time": 1740849516.6316664,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-800008.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 800008,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 27.636363636363637,
+            "creation_time": 1740849516.6316664,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-800008.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.6.0+cu124"
+    }
+}