1

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: fetiska/cold_weapon
+  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 sha256:9328fe487185e9ccd9d02c6c3c6ba0084821d9824929d38e1816442e489e634e
+size 646532

SnowballTarget/SnowballTarget-100056.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9328fe487185e9ccd9d02c6c3c6ba0084821d9824929d38e1816442e489e634e
+size 646532

SnowballTarget/SnowballTarget-100056.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58738d4c48d2c925470687b9888e1a386396508b69f3c8cbd0c66e36e96d829d
+size 3843200

SnowballTarget/SnowballTarget-17512.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:401d02e38c38313521cc03d58cd90a1d70ecf576f960a446a72195ecdf652113
+size 646532

SnowballTarget/SnowballTarget-17512.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe78d5229bd5f7e9b0a0623c7331cfcec35f20a85a4f44a066c8933725aab75e
+size 3843200

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7e57f1ba5a5779a98b05f15047e131046737b4a30cdfb5d545e3ea559f8b23
+size 646532

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c2f562d40d749af3cd0e1c9845513ac618f370a28dff22cbfd543fa2989dda
+size 3843200

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9328fe487185e9ccd9d02c6c3c6ba0084821d9824929d38e1816442e489e634e
+size 646532

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b80166cf158682752e224f895ecce30a6643f79792377145fd90c9bcb38cd4df
+size 3843200

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58738d4c48d2c925470687b9888e1a386396508b69f3c8cbd0c66e36e96d829d
+size 3843200

SnowballTarget/events.out.tfevents.1694866241.2c7a28186045.7459.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46ff40642ec2197831d79be71048ed73b98d5876e71656ad96412a1c964fb72c
+size 44889

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": 0, "even_checkpoints": false, "max_steps": 100000, "time_horizon": 96, "summary_freq": 3000, "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: 0
+    even_checkpoints: false
+    max_steps: 100000
+    time_horizon: 96
+    summary_freq: 3000
+    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: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  0.107 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: 0.820411 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]: 2690 frames, [16.0 KB-32.0 KB]: 45 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 42
+    [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]: 2736 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.1 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 2736 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]: 1764 frames, [64.0 KB-128.0 KB]: 972 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]: 2736 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]: 2736 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]: 2735 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]: 2736 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]: 2736 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": 1.7313357591629028,
+            "min": 1.7127974033355713,
+            "max": 2.8897507190704346,
+            "count": 33
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 5789.5869140625,
+            "min": 3986.89013671875,
+            "max": 9949.412109375,
+            "count": 33
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 98992.0,
+            "min": 2968.0,
+            "max": 98992.0,
+            "count": 33
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 98992.0,
+            "min": 2968.0,
+            "max": 98992.0,
+            "count": 33
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 8.963665008544922,
+            "min": 0.10108505934476852,
+            "max": 8.963665008544922,
+            "count": 33
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 457.14691162109375,
+            "min": 4.144487380981445,
+            "max": 457.14691162109375,
+            "count": 33
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 33
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 4378.0,
+            "min": 2189.0,
+            "max": 4378.0,
+            "count": 33
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06821459705037448,
+            "min": 0.056161290620437676,
+            "max": 0.08300557076090984,
+            "count": 33
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.13642919410074897,
+            "min": 0.056161290620437676,
+            "max": 0.16539050954138385,
+            "count": 33
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.24401900318323397,
+            "min": 0.09071497918636191,
+            "max": 0.3442269283182481,
+            "count": 33
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.48803800636646794,
+            "min": 0.09071497918636191,
+            "max": 0.6462239623069763,
+            "count": 33
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 6.564097812000004e-06,
+            "min": 6.564097812000004e-06,
+            "max": 0.000293664002112,
+            "count": 33
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 1.3128195624000008e-05,
+            "min": 1.3128195624000008e-05,
+            "max": 0.000554328015224,
+            "count": 33
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10218800000000001,
+            "min": 0.10218800000000001,
+            "max": 0.19788800000000004,
+            "count": 33
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.20437600000000003,
+            "min": 0.10548800000000003,
+            "max": 0.38477600000000006,
+            "count": 33
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.00011918120000000008,
+            "min": 0.00011918120000000008,
+            "max": 0.0048946112,
+            "count": 33
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00023836240000000016,
+            "min": 0.00023836240000000016,
+            "max": 0.0092403224,
+            "count": 33
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 18.714285714285715,
+            "min": 2.727272727272727,
+            "max": 19.09090909090909,
+            "count": 33
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 393.0,
+            "min": 30.0,
+            "max": 406.0,
+            "count": 33
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 18.714285714285715,
+            "min": 2.727272727272727,
+            "max": 19.09090909090909,
+            "count": 33
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 393.0,
+            "min": 30.0,
+            "max": 406.0,
+            "count": 33
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1694866240",
+        "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
+        "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": "1694866533"
+    },
+    "total": 292.990521747,
+    "count": 1,
+    "self": 0.5265611539998645,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05236504100003003,
+            "count": 1,
+            "self": 0.05236504100003003
+        },
+        "TrainerController.start_learning": {
+            "total": 292.4115955520001,
+            "count": 1,
+            "self": 0.44906356599926767,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.0040535400000863,
+                    "count": 1,
+                    "self": 1.0040535400000863
+                },
+                "TrainerController.advance": {
+                    "total": 290.8054328090011,
+                    "count": 9117,
+                    "self": 0.2306598060079068,
+                    "children": {
+                        "env_step": {
+                            "total": 290.5747730029932,
+                            "count": 9117,
+                            "self": 232.47457808300373,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 57.89622661499152,
+                                    "count": 9117,
+                                    "self": 1.3152518990029876,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 56.58097471598853,
+                                            "count": 9117,
+                                            "self": 56.58097471598853
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.20396830499794305,
+                                    "count": 9117,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 291.25662964599746,
+                                            "count": 9117,
+                                            "is_parallel": true,
+                                            "self": 123.46436249100248,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002140725000117527,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006109940006808756,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0015297309994366515,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0015297309994366515
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.05819984600020689,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005269930002214096,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00045711899997513683,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00045711899997513683
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.05370774099992559,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.05370774099992559
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0035079930000847526,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0015020980004010198,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0020058949996837327,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0020058949996837327
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 167.792267154995,
+                                                    "count": 9116,
+                                                    "is_parallel": true,
+                                                    "self": 6.9609572139977445,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 3.7738556229912774,
+                                                            "count": 9116,
+                                                            "is_parallel": true,
+                                                            "self": 3.7738556229912774
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 132.94538953800497,
+                                                            "count": 9116,
+                                                            "is_parallel": true,
+                                                            "self": 132.94538953800497
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 24.112064780000992,
+                                                            "count": 9116,
+                                                            "is_parallel": true,
+                                                            "self": 4.669569226967724,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 19.442495553033268,
+                                                                    "count": 91160,
+                                                                    "is_parallel": true,
+                                                                    "self": 19.442495553033268
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 4.913099974146462e-05,
+                    "count": 1,
+                    "self": 4.913099974146462e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 288.7915713470172,
+                                    "count": 225280,
+                                    "is_parallel": true,
+                                    "self": 5.8745017050594015,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 129.6866089769578,
+                                            "count": 225280,
+                                            "is_parallel": true,
+                                            "self": 129.12433366295772,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.5622753140000896,
+                                                    "count": 2,
+                                                    "is_parallel": true,
+                                                    "self": 0.5622753140000896
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 153.230460665,
+                                            "count": 45,
+                                            "is_parallel": true,
+                                            "self": 50.57828893099645,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 102.65217173400356,
+                                                    "count": 2292,
+                                                    "is_parallel": true,
+                                                    "self": 102.65217173400356
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.15299650599990855,
+                    "count": 1,
+                    "self": 0.0013579679998656502,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1516385380000429,
+                            "count": 1,
+                            "self": 0.1516385380000429
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 15.545454545454545,
+                "creation_time": 1694866388.3406696,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 19.0,
+                "creation_time": 1694866532.5211375,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 100056,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-100056.onnx",
+                "reward": 19.0,
+                "creation_time": 1694866532.7060647,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-100056.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 100056,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 19.0,
+            "creation_time": 1694866532.7060647,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-100056.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}