First Try

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: janzw/ppo-SnowballTarget1
+  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:ebd5a82c2736532a7bf46840d6ac33e19da99845c040bc3443d40822a18cd023
+size 646532

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e4df01bcafd8440982f21f990fe2e99ed8df1313d53b9711c550326828b01c
+size 646532

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e756e9b0ff145e7d6020c057c5c9303595d937a3770a021ffe04c574dc7e73
+size 3843968

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69fcfd5ec3b52f66818bdf72d4415d0458a32293cba39b5a42d8cf7eae3b86bd
+size 646532

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1050d004c2ce00d207eafafa6c0bffa437cc3c87481a5d37af8e59fdc2f37d4
+size 3843968

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b8751b493c6f1eca779a9a2dfdafb97117e5df95ed92d80ca695814ad329f57
+size 646532

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf134c3625ad5515a303905b11ccaee8fdc77cc97c09625f166354b8a6b5924
+size 3843968

SnowballTarget/SnowballTarget-249944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa2fcac4127a10e394101ddb2541b8e6e9287335e6959440a41a1e36b572f48
+size 646532

SnowballTarget/SnowballTarget-249944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84ddff62d453ed4cc1ef2c7055bae9924ddd86e13f4f6573025fbe13857832ab
+size 3843968

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4079c48ffe08bbe47037f1df61cc6557f81542809e111033b9d75301a315373
+size 646532

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f63f65c4244b615dd6fb1754a986d2573b632ae48e4e2543ef4c2ea48603071
+size 3843968

SnowballTarget/SnowballTarget-349992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba9ed2a359c5a5c78fb65c52cd8bb4bcd28e8b8ceeed2a0f0865bbbaa352c624
+size 646532

SnowballTarget/SnowballTarget-349992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30fe25fd13b68aa7558fab2f7c62bc5d6e628fea8e41835383fba622bc10090b
+size 3843968

SnowballTarget/SnowballTarget-399992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd5a82c2736532a7bf46840d6ac33e19da99845c040bc3443d40822a18cd023
+size 646532

SnowballTarget/SnowballTarget-399992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3911f1dd1aa222c777672d221de87d178b4be08d38309016c092b778637c54eb
+size 3843968

SnowballTarget/SnowballTarget-400312.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd5a82c2736532a7bf46840d6ac33e19da99845c040bc3443d40822a18cd023
+size 646532

SnowballTarget/SnowballTarget-400312.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acfec05e1b1b9cff98b60b8b5f526c0bc701b2a7c50ed51de8a8b20398e081bc
+size 3843968

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6e53b75d5a658444abce29297416b7c63697e586613fa3b57db3610c5c5a4f
+size 646532

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ca2e94d80af7cc5d578681616e33811bafd35a3059ca812833bdc698c002d3
+size 3843968

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c3b9ff6b93b4359e320b12c549a21254b4a892a709dd6d66fa30ba95eb509bf
+size 646532

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432af3311c413a26a5bf7ee0d8cfd4df4a813262e06673f101e0bfe630e38bbb
+size 3843968

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acfec05e1b1b9cff98b60b8b5f526c0bc701b2a7c50ed51de8a8b20398e081bc
+size 3843968

SnowballTarget/events.out.tfevents.1679250876.0cf92822df4f.7419.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092c5cf5a98d8fd450db92888e22238fa5a219e86ad0fd4a6211556e62f7a013
+size 39872

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": 400000, "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": true, "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: 400000
+    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: 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: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  0.082 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: 0.669050 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]: 10740 frames, [16.0 KB-32.0 KB]: 182 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]: 10923 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 8.7 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 10923 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]: 9554 frames, [64.0 KB-128.0 KB]: 1369 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.8 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 10923 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]: 10923 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]: 10922 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]: 10923 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]: 10923 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": 0.7540989518165588,
+            "min": 0.7509713768959045,
+            "max": 2.8544716835021973,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7631.4814453125,
+            "min": 7178.53515625,
+            "max": 29232.64453125,
+            "count": 40
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 399992.0,
+            "min": 9952.0,
+            "max": 399992.0,
+            "count": 40
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 399992.0,
+            "min": 9952.0,
+            "max": 399992.0,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.709442138671875,
+            "min": 0.37919145822525024,
+            "max": 13.748085975646973,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2673.34130859375,
+            "min": 73.56314086914062,
+            "max": 2813.556640625,
+            "count": 40
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 40
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 40
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06753559517200497,
+            "min": 0.06183863029844931,
+            "max": 0.0765778742175362,
+            "count": 40
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.2701423806880199,
+            "min": 0.24752901096484956,
+            "max": 0.36887590581717833,
+            "count": 40
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.17932815506469968,
+            "min": 0.1226801106183534,
+            "max": 0.26482234918603714,
+            "count": 40
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7173126202587987,
+            "min": 0.4907204424734136,
+            "max": 1.3241117459301857,
+            "count": 40
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 3.891098702999994e-06,
+            "min": 3.891098702999994e-06,
+            "max": 0.000295941001353,
+            "count": 40
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 1.5564394811999976e-05,
+            "min": 1.5564394811999976e-05,
+            "max": 0.0014425800191399996,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.101297,
+            "min": 0.101297,
+            "max": 0.19864700000000002,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.405188,
+            "min": 0.405188,
+            "max": 0.98086,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 7.472029999999992e-05,
+            "min": 7.472029999999992e-05,
+            "max": 0.004932485299999999,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00029888119999999966,
+            "min": 0.00029888119999999966,
+            "max": 0.024044914,
+            "count": 40
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 27.068181818181817,
+            "min": 3.272727272727273,
+            "max": 27.068181818181817,
+            "count": 40
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1191.0,
+            "min": 144.0,
+            "max": 1469.0,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 27.068181818181817,
+            "min": 3.272727272727273,
+            "max": 27.068181818181817,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1191.0,
+            "min": 144.0,
+            "max": 1469.0,
+            "count": 40
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 40
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 40
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1679250873",
+        "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 --force ./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": "1679251765"
+    },
+    "total": 891.8117125760002,
+    "count": 1,
+    "self": 0.8525653340002464,
+    "children": {
+        "run_training.setup": {
+            "total": 0.09895160700011729,
+            "count": 1,
+            "self": 0.09895160700011729
+        },
+        "TrainerController.start_learning": {
+            "total": 890.8601956349999,
+            "count": 1,
+            "self": 1.0520900850065118,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.457522214000164,
+                    "count": 1,
+                    "self": 5.457522214000164
+                },
+                "TrainerController.advance": {
+                    "total": 884.1411102139932,
+                    "count": 36410,
+                    "self": 0.48831130802022926,
+                    "children": {
+                        "env_step": {
+                            "total": 883.652798905973,
+                            "count": 36410,
+                            "self": 636.8254537769212,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 246.3199526060389,
+                                    "count": 36410,
+                                    "self": 4.135007505025669,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 242.18494510101323,
+                                            "count": 36410,
+                                            "self": 242.18494510101323
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.507392523012868,
+                                    "count": 36410,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 888.0916931100242,
+                                            "count": 36410,
+                                            "is_parallel": true,
+                                            "self": 421.3944678570206,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0019270519999281532,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005869359995358536,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0013401160003922996,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0013401160003922996
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.04759080799999538,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0004915520000849938,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.000303345000020272,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000303345000020272
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.04522522000002027,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.04522522000002027
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0015706909998698393,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003334949999498349,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0012371959999200044,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0012371959999200044
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 466.6972252530036,
+                                                    "count": 36409,
+                                                    "is_parallel": true,
+                                                    "self": 18.36872623301565,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 10.109062429934966,
+                                                            "count": 36409,
+                                                            "is_parallel": true,
+                                                            "self": 10.109062429934966
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 376.9459000480133,
+                                                            "count": 36409,
+                                                            "is_parallel": true,
+                                                            "self": 376.9459000480133
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 61.273536542039665,
+                                                            "count": 36409,
+                                                            "is_parallel": true,
+                                                            "self": 11.93635280790022,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 49.337183734139444,
+                                                                    "count": 364090,
+                                                                    "is_parallel": true,
+                                                                    "self": 49.337183734139444
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0002868589999707183,
+                    "count": 1,
+                    "self": 0.0002868589999707183,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 877.583537931085,
+                                    "count": 773222,
+                                    "is_parallel": true,
+                                    "self": 20.18850114104498,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 487.6788062670373,
+                                            "count": 773222,
+                                            "is_parallel": true,
+                                            "self": 485.30850892303783,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 2.370297343999482,
+                                                    "count": 8,
+                                                    "is_parallel": true,
+                                                    "self": 2.370297343999482
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 369.71623052300265,
+                                            "count": 181,
+                                            "is_parallel": true,
+                                            "self": 136.69635624398938,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 233.01987427901327,
+                                                    "count": 9228,
+                                                    "is_parallel": true,
+                                                    "self": 233.01987427901327
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.20918626299999232,
+                    "count": 1,
+                    "self": 0.002009664000070188,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.20717659899992213,
+                            "count": 1,
+                            "self": 0.20717659899992213
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,101 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 13.272727272727273,
+                "creation_time": 1679250990.9877121,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 20.545454545454547,
+                "creation_time": 1679251101.704787,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 24.272727272727273,
+                "creation_time": 1679251213.4032304,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 24.90909090909091,
+                "creation_time": 1679251322.2511601,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 249944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
+                "reward": 25.727272727272727,
+                "creation_time": 1679251431.4669619,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 26.818181818181817,
+                "creation_time": 1679251543.8751936,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 349992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
+                "reward": 27.363636363636363,
+                "creation_time": 1679251654.2755432,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
+                ]
+            },
+            {
+                "steps": 399992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
+                "reward": 27.272727272727273,
+                "creation_time": 1679251764.5977087,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
+                ]
+            },
+            {
+                "steps": 400312,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.onnx",
+                "reward": 27.272727272727273,
+                "creation_time": 1679251764.8490276,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 400312,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 27.272727272727273,
+            "creation_time": 1679251764.8490276,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}