First Push

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SnowballTarget
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SnowballTarget
+---
+
+  # **ppo** Agent playing **SnowballTarget**
+  This is a trained model of a **ppo** agent playing **SnowballTarget**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+
+  ## Usage (with ML-Agents)
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: qdzzzxc/ppo-SnowballTarget
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SnowballTarget.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51cb0a3909e2dbb941a5abfb61bd16bc3c5c74901d4bc58858d860f06af4a271
+size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0032e1a7d0ee23296e7ff3fbfb24f29a3049abadfefe5b21d036dcafbec2e5b1
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5655fb03210310d220af7cb7e71a87cdb00a9f6a26d8dd7f189cd1f06d386c8d
+size 3849115

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51cb0a3909e2dbb941a5abfb61bd16bc3c5c74901d4bc58858d860f06af4a271
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a8dbe7ef2891b9b872b08d702b3c7844d67354eca856c6b87b56e6f93a5557
+size 3849115

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51cb0a3909e2dbb941a5abfb61bd16bc3c5c74901d4bc58858d860f06af4a271
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8749043c0a3767e88a936ee7d0959d7a8c7b442e4c6a7e7bac2e68cc99872220
+size 3849115

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6b4a2f1b892550b0b0b2cf24b8655b1997ecf041cc38bcf2d5a4bd8df2c6dcb
+size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7433aed39a373818cb5cf5a97da8b05c48c02092577d6f4518669d23010ac88c
+size 3849040

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3990e5517199f42c699321547a14f171b02450af8a1561d2fb2b4d983bcb5b5d
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90425fd0a049aa1054b0037c83f9450ac6923278cc7aa150e703708493eab786
+size 3849040

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bddbc36bd3b82b747d983cb8ca06da63ab3d9b77240c4112836576f4ac08707
+size 3848290

SnowballTarget/events.out.tfevents.1767897660.nikita-MS-7E24.10897.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36bd4e67f8ce3ff95fb55f1938a6732d48fe2e0338c4ad17089706d32d45260a
+size 23796

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": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "/home/nikita/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 10
+    even_checkpoints: false
+    max_steps: 200000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: /home/nikita/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SnowballTarget1
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,289 @@
+Mono path[0] = '/home/nikita/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/home/nikita/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 /home/nikita/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
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.037 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: 0.409530 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 6 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]: 5370 frames, [16.0 KB-32.0 KB]: 91 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 186 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_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      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 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 5]
+      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 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_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      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 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 6
+      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] x 11
+      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_Job.Worker 9]
+      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 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      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 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 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      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 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 36
+    [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]: 5462 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 7.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.4 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]: 5083 frames, [64.0 KB-128.0 KB]: 379 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.4 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5462 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]: 5462 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]: 5461 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]: 5462 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]: 5462 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": 0.8844785094261169,
+            "min": 0.8844785094261169,
+            "max": 2.871408224105835,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 8483.91796875,
+            "min": 8483.91796875,
+            "max": 29532.43359375,
+            "count": 20
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.862825393676758,
+            "min": 0.18974463641643524,
+            "max": 12.862825393676758,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2508.2509765625,
+            "min": 36.81045913696289,
+            "max": 2610.67919921875,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07260958947667592,
+            "min": 0.060446892916361857,
+            "max": 0.07854168385229594,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.2904383579067037,
+            "min": 0.24178757166544743,
+            "max": 0.361093250086175,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.21831531274844618,
+            "min": 0.08548859730488438,
+            "max": 0.29575785059554904,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.8732612509937847,
+            "min": 0.3419543892195375,
+            "max": 1.4480454062714296,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.082097306000005e-06,
+            "min": 8.082097306000005e-06,
+            "max": 0.000291882002706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.232838922400002e-05,
+            "min": 3.232838922400002e-05,
+            "max": 0.00138516003828,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10269400000000001,
+            "min": 0.10269400000000001,
+            "max": 0.19729400000000002,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.41077600000000003,
+            "min": 0.41077600000000003,
+            "max": 0.96172,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0001444306000000001,
+            "min": 0.0001444306000000001,
+            "max": 0.0048649706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005777224000000004,
+            "min": 0.0005777224000000004,
+            "max": 0.023089828,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.431818181818183,
+            "min": 2.5,
+            "max": 25.454545454545453,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1119.0,
+            "min": 110.0,
+            "max": 1380.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.431818181818183,
+            "min": 2.5,
+            "max": 25.454545454545453,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1119.0,
+            "min": 110.0,
+            "max": 1380.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1767897660",
+        "python_version": "3.10.19 (main, Dec  9 2025, 19:03:08) [Clang 21.1.4 ]",
+        "command_line_arguments": "/home/nikita/projects/deep_rl_course/.venv/bin/mlagents-learn /home/nikita/projects/deep_rl_course/notebooks/5_unity/SnowballTarget.yaml --env=/home/nikita/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics",
+        "mlagents_version": "1.1.0",
+        "mlagents_envs_version": "1.1.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1767897801"
+    },
+    "total": 141.71304698899985,
+    "count": 1,
+    "self": 0.16695211099977314,
+    "children": {
+        "run_training.setup": {
+            "total": 0.010325737999664852,
+            "count": 1,
+            "self": 0.010325737999664852
+        },
+        "TrainerController.start_learning": {
+            "total": 141.5357691400004,
+            "count": 1,
+            "self": 0.20120825096000772,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 0.7129085109991138,
+                    "count": 1,
+                    "self": 0.7129085109991138
+                },
+                "TrainerController.advance": {
+                    "total": 140.58434082904114,
+                    "count": 18205,
+                    "self": 0.09335715013548906,
+                    "children": {
+                        "env_step": {
+                            "total": 140.49098367890565,
+                            "count": 18205,
+                            "self": 113.33242977989903,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 27.050469190990952,
+                                    "count": 18205,
+                                    "self": 0.477427375057232,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 26.57304181593372,
+                                            "count": 18205,
+                                            "self": 26.57304181593372
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.10808470801566727,
+                                    "count": 18205,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 141.28384437989735,
+                                            "count": 18205,
+                                            "is_parallel": true,
+                                            "self": 62.425970987920664,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.000893668000571779,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00026503699973545736,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0006286310008363216,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0006286310008363216
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.012593366999681166,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0001503769990449655,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00017746800040185917,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00017746800040185917
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.011820468000223627,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.011820468000223627
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.00044505400001071393,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0001069289992301492,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.00033812500078056473,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.00033812500078056473
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 78.85787339197668,
+                                                    "count": 18204,
+                                                    "is_parallel": true,
+                                                    "self": 2.9824492509051197,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 1.6512604630579517,
+                                                            "count": 18204,
+                                                            "is_parallel": true,
+                                                            "self": 1.6512604630579517
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 65.55159172305866,
+                                                            "count": 18204,
+                                                            "is_parallel": true,
+                                                            "self": 65.55159172305866
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 8.672571954954947,
+                                                            "count": 18204,
+                                                            "is_parallel": true,
+                                                            "self": 1.665220050986136,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 7.007351903968811,
+                                                                    "count": 182040,
+                                                                    "is_parallel": true,
+                                                                    "self": 7.007351903968811
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.554900003015064e-05,
+                    "count": 1,
+                    "self": 7.554900003015064e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 140.23716055408022,
+                                    "count": 144147,
+                                    "is_parallel": true,
+                                    "self": 1.2771197501033384,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 75.79383476297426,
+                                            "count": 144147,
+                                            "is_parallel": true,
+                                            "self": 75.55847679597264,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.23535796700161882,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.23535796700161882
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 63.166206041002624,
+                                            "count": 90,
+                                            "is_parallel": true,
+                                            "self": 16.574616336953113,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 46.59158970404951,
+                                                    "count": 4587,
+                                                    "is_parallel": true,
+                                                    "self": 46.59158970404951
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.03723600000012084,
+                    "count": 1,
+                    "self": 0.0005067840002084267,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.03672921599991241,
+                            "count": 1,
+                            "self": 0.03672921599991241
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 13.909090909090908,
+                "creation_time": 1767897695.3615587,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 21.363636363636363,
+                "creation_time": 1767897730.0619078,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 24.0,
+                "creation_time": 1767897765.5210402,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 26.09090909090909,
+                "creation_time": 1767897801.7131286,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 26.09090909090909,
+                "creation_time": 1767897801.7620544,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 200112,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 26.09090909090909,
+            "creation_time": 1767897801.7620544,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0",
+        "torch_version": "2.1.1+cu121"
+    }
+}