2m steps Push

README.md

@@ -0,0 +1,29 @@
+---
+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://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  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. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
+  2. Step 1: Find your model_id: messham/ppo-SnowballTarget2
+  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:ce0224424b03b4707ec8db04f184a98ac8dda310f1d20252c3b7d3b6b6f60365
+size 646532

SnowballTarget/SnowballTarget-1599976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b3ff5e385e08817fb890c38a326c8495f8293d05bf361e91b44f299338fd0ec
+size 646532

SnowballTarget/SnowballTarget-1599976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe5409eaae0f5b3b87a4a1203758ba8df59be23d73848b6c6d36853d5130a90
+size 3843200

SnowballTarget/SnowballTarget-1649992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebe0339286117ac72602e1de5af8c7ed728eb9ee1684febd5e45a17c11d5938
+size 646532

SnowballTarget/SnowballTarget-1649992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4a748cec82d99ce8093af8ea6170866bad9d9824c0986c3288a90ac6fb8920
+size 3843200

SnowballTarget/SnowballTarget-1699936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca3ced2e16342300acb811fbafbd6aeff0fbcbd7305fa077fd0865da20750426
+size 646532

SnowballTarget/SnowballTarget-1699936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d59c66c93efb1f974429c580d9cfa40e4aa3dc7de27899c01f8133d63c36a3d
+size 3843200

SnowballTarget/SnowballTarget-1749960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e2aa63ef5af888e2d2f72f9b0fd4dba6fe380162a835ddfc22a450e1ca60dc
+size 646532

SnowballTarget/SnowballTarget-1749960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8c1283497945419023d8633e49a1e7ec3d756ccd2cdac8f972fa2933e2dfab5
+size 3843200

SnowballTarget/SnowballTarget-1799984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d797f5f87463452045bdfce8f68170242c6dc93cf71613fff6d82eb20bf19422
+size 646532

SnowballTarget/SnowballTarget-1799984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b3265670f090657985d9874324212e4348436d2c1720ee440993be47e29bb6f
+size 3843200

SnowballTarget/SnowballTarget-1849984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:433b90fa6cdb36d5dcc0bcb498858f864ee905c637b48977a5a59987cd32d1b4
+size 646532

SnowballTarget/SnowballTarget-1849984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535fd36d2af7b33c46add9d51a1c1127a62b232203073060fc8b8db0711acdd9
+size 3843200

SnowballTarget/SnowballTarget-1899944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd851733b43b9fc2881e2bcb0872a5964b0770a04a3d5a173760c2c68771060
+size 646532

SnowballTarget/SnowballTarget-1899944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b087fdfbb466d629afc96fe7cde11555ad658f93024b1a408fa9f5e78b18c0f0
+size 3843200

SnowballTarget/SnowballTarget-1949968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c204ab112fe23ac4436493eec3c11a4b9998db87bdfef8f419f3cabd4f909a6
+size 646532

SnowballTarget/SnowballTarget-1949968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abbb69ffd9d4fd483a28433324c5847bdc443ce62c9a76b125ce216237a196a
+size 3843200

SnowballTarget/SnowballTarget-1999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce0224424b03b4707ec8db04f184a98ac8dda310f1d20252c3b7d3b6b6f60365
+size 646532

SnowballTarget/SnowballTarget-1999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9afe087ea15fd01dabe6b54616cd274809a703b42dcda9e58357c5ec0bfe1e6
+size 3843200

SnowballTarget/SnowballTarget-2000376.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce0224424b03b4707ec8db04f184a98ac8dda310f1d20252c3b7d3b6b6f60365
+size 646532

SnowballTarget/SnowballTarget-2000376.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31b821af5e8900f82d2aca6af813f8fc05e2f5bc9b0bb586507030408b097cfa
+size 3843200

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31b821af5e8900f82d2aca6af813f8fc05e2f5bc9b0bb586507030408b097cfa
+size 3843200

SnowballTarget/events.out.tfevents.1680947606.9e6351dc9172.6669.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b982e6c5e014e217938a1b3ff2f3c242c414554d26ee80c5ea208c8879897a8
+size 175385

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": "SnowballTarget2", "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: SnowballTarget2
+  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 +1,259 @@
+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:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(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:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(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  0.143 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: 1.035197 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 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]: 11499 frames, [8.0 MB-16.0 MB]: 29913 frames, [16.0 MB-32.0 MB]: 13150 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]: 53010 frames, [64.0 KB-128.0 KB]: 1552 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 67.6 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": 0.5073500871658325,
+            "min": 0.44612881541252136,
+            "max": 2.8709447383880615,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 5218.095703125,
+            "min": 4313.69921875,
+            "max": 29432.92578125,
+            "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": 14.333270072937012,
+            "min": 0.2767333686351776,
+            "max": 14.410740852355957,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2938.3203125,
+            "min": 53.68627166748047,
+            "max": 2952.8720703125,
+            "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": 0.07231564274441232,
+            "min": 0.06043865533295092,
+            "max": 0.07629179319334856,
+            "count": 200
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.3615782137220616,
+            "min": 0.24175462133180367,
+            "max": 0.3814589659667428,
+            "count": 200
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.14176157613595325,
+            "min": 0.11787958366239407,
+            "max": 0.2759304280374565,
+            "count": 200
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7088078806797663,
+            "min": 0.47151833464957627,
+            "max": 1.3280392432329702,
+            "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": 28.036363636363635,
+            "min": 3.2045454545454546,
+            "max": 28.545454545454547,
+            "count": 200
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1542.0,
+            "min": 141.0,
+            "max": 1562.0,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 28.036363636363635,
+            "min": 3.2045454545454546,
+            "max": 28.545454545454547,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1542.0,
+            "min": 141.0,
+            "max": 1562.0,
+            "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": "1680947605",
+        "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --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": "1680953821"
+    },
+    "total": 6216.0523109509995,
+    "count": 1,
+    "self": 0.6432689249995747,
+    "children": {
+        "run_training.setup": {
+            "total": 0.13959167000007255,
+            "count": 1,
+            "self": 0.13959167000007255
+        },
+        "TrainerController.start_learning": {
+            "total": 6215.269450356,
+            "count": 1,
+            "self": 9.836011857989433,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 0.8482601200000772,
+                    "count": 1,
+                    "self": 0.8482601200000772
+                },
+                "TrainerController.advance": {
+                    "total": 6204.421568810009,
+                    "count": 181873,
+                    "self": 5.122590321077041,
+                    "children": {
+                        "env_step": {
+                            "total": 6199.298978488932,
+                            "count": 181873,
+                            "self": 5046.155034286932,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1148.3035975169971,
+                                    "count": 181873,
+                                    "self": 29.348385014975065,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1118.955212502022,
+                                            "count": 181873,
+                                            "self": 1118.955212502022
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 4.840346685002714,
+                                    "count": 181873,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 6191.093568429078,
+                                            "count": 181873,
+                                            "is_parallel": true,
+                                            "self": 2630.802529453923,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0033474710000973573,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0011056989999360667,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0022417720001612906,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0022417720001612906
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.04783905599992977,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007138229998417955,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003933509999569651,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003933509999569651
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.04408974600005422,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.04408974600005422
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.002642136000076789,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005435770003714424,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0020985589997053467,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0020985589997053467
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 3560.291038975155,
+                                                    "count": 181872,
+                                                    "is_parallel": true,
+                                                    "self": 146.50199550708567,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 76.8901836070695,
+                                                            "count": 181872,
+                                                            "is_parallel": true,
+                                                            "self": 76.8901836070695
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2873.9393243660525,
+                                                            "count": 181872,
+                                                            "is_parallel": true,
+                                                            "self": 2873.9393243660525
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 462.95953549494766,
+                                                            "count": 181872,
+                                                            "is_parallel": true,
+                                                            "self": 96.8290968019362,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 366.13043869301146,
+                                                                    "count": 1818720,
+                                                                    "is_parallel": true,
+                                                                    "self": 366.13043869301146
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0007093419999364414,
+                    "count": 1,
+                    "self": 0.0007093419999364414,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 6141.456610045923,
+                                    "count": 7205549,
+                                    "is_parallel": true,
+                                    "self": 176.47311314596482,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 3298.8974320339503,
+                                            "count": 7205549,
+                                            "is_parallel": true,
+                                            "self": 3285.0486143369544,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 13.848817696996093,
+                                                    "count": 40,
+                                                    "is_parallel": true,
+                                                    "self": 13.848817696996093
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 2666.086064866008,
+                                            "count": 909,
+                                            "is_parallel": true,
+                                            "self": 891.3026456340563,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 1774.783419231952,
+                                                    "count": 46353,
+                                                    "is_parallel": true,
+                                                    "self": 1774.783419231952
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.16290022600060183,
+                    "count": 1,
+                    "self": 0.0013970910003990866,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.16150313500020275,
+                            "count": 1,
+                            "self": 0.16150313500020275
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 1599976,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1599976.onnx",
+                "reward": 27.09090909090909,
+                "creation_time": 1680952570.3405933,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1599976.pt"
+                ]
+            },
+            {
+                "steps": 1649992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1649992.onnx",
+                "reward": 28.9,
+                "creation_time": 1680952727.4756439,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1649992.pt"
+                ]
+            },
+            {
+                "steps": 1699936,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1699936.onnx",
+                "reward": 28.272727272727273,
+                "creation_time": 1680952883.0861616,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1699936.pt"
+                ]
+            },
+            {
+                "steps": 1749960,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1749960.onnx",
+                "reward": 27.454545454545453,
+                "creation_time": 1680953039.0432372,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1749960.pt"
+                ]
+            },
+            {
+                "steps": 1799984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1799984.onnx",
+                "reward": 27.727272727272727,
+                "creation_time": 1680953194.711919,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1799984.pt"
+                ]
+            },
+            {
+                "steps": 1849984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1849984.onnx",
+                "reward": 28.363636363636363,
+                "creation_time": 1680953349.116452,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1849984.pt"
+                ]
+            },
+            {
+                "steps": 1899944,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1899944.onnx",
+                "reward": 27.636363636363637,
+                "creation_time": 1680953505.0640543,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1899944.pt"
+                ]
+            },
+            {
+                "steps": 1949968,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1949968.onnx",
+                "reward": 27.636363636363637,
+                "creation_time": 1680953662.997076,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1949968.pt"
+                ]
+            },
+            {
+                "steps": 1999992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1999992.onnx",
+                "reward": 27.454545454545453,
+                "creation_time": 1680953820.7321014,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1999992.pt"
+                ]
+            },
+            {
+                "steps": 2000376,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-2000376.onnx",
+                "reward": 27.454545454545453,
+                "creation_time": 1680953820.9456942,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-2000376.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 2000376,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 27.454545454545453,
+            "creation_time": 1680953820.9456942,
+            "auxillary_file_paths": [
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-2000376.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}