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: rwr20/ppo-SnowballTarget3
+  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:d74a1c41240422a4b01f69857f59d540c7b3b5ac90d95a5e5df7c4115bf7074d
+size 650646

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ebb4c3a72bc4398528428b105a470cce48a1800a8afacbfdba8055e32edb892
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e677b0010ae633e497cb80f9606505f13846b20d0c7a629b096d7d77775073d
+size 3850075

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e173d52aa824bf6818f98385efba1a7c2178309162f92465f5fa5e6a2c9b49d7
+size 650646

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4071b43829ab5f7b076e47e47940e508355173e4ac607bb525d7feb48522d17c
+size 3850075

SnowballTarget/SnowballTarget-362912.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d74a1c41240422a4b01f69857f59d540c7b3b5ac90d95a5e5df7c4115bf7074d
+size 650646

SnowballTarget/SnowballTarget-362912.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b292b092abfa1c5a0df556081396c1d03982acf0eebbd5186610f52f8c5580
+size 3850075

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5af2e242858d93023bbdc74a617e9c1327f82ecc0ad745790f0ea02d2618c3
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20680afd93a0e01c6db7605ae8c9f2b88a90c7dccc436560b93370c6a66ee8a1
+size 3850000

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ccfbb177cef617d81cadbf9451658c1133d0bba9d34062982d66ba5762603ad
+size 3849250

SnowballTarget/events.out.tfevents.1714813703.690628bcd0a1.11332.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c39678c2f0b5dfb7a32829bd8439fb8060954b13c76c7580fdc4c11ebe547ee3
+size 41488

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": 100000, "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": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget3", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 100000
+    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: 500000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SnowballTarget3
+  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  0.085 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: 0.646585 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]: 9735 frames, [16.0 KB-32.0 KB]: 165 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 40
+    [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]: 9901 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 8.2 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 9901 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.3 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]: 9219 frames, [64.0 KB-128.0 KB]: 682 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]: 9901 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]: 9901 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]: 9900 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]: 9901 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]: 9901 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": 0.816674530506134,
+            "min": 0.7926225066184998,
+            "max": 2.8568437099456787,
+            "count": 36
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7743.7080078125,
+            "min": 7741.38330078125,
+            "max": 29256.9375,
+            "count": 36
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 359944.0,
+            "min": 9952.0,
+            "max": 359944.0,
+            "count": 36
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 359944.0,
+            "min": 9952.0,
+            "max": 359944.0,
+            "count": 36
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.722535133361816,
+            "min": 0.29261475801467896,
+            "max": 13.722535133361816,
+            "count": 36
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2662.171875,
+            "min": 56.76726150512695,
+            "max": 2802.098876953125,
+            "count": 36
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 36
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 36
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06622977422118899,
+            "min": 0.06128641730337061,
+            "max": 0.0728793583022814,
+            "count": 36
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.26491909688475596,
+            "min": 0.24921138306101553,
+            "max": 0.364396791511407,
+            "count": 36
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.17329898845477432,
+            "min": 0.1065496731236778,
+            "max": 0.3044767375378048,
+            "count": 36
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.6931959538190973,
+            "min": 0.4261986924947112,
+            "max": 1.295578857555109,
+            "count": 36
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.68728710424e-05,
+            "min": 8.68728710424e-05,
+            "max": 0.00029675280108239997,
+            "count": 36
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 0.0003474914841696,
+            "min": 0.0003474914841696,
+            "max": 0.001454064015312,
+            "count": 36
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.1289576,
+            "min": 0.1289576,
+            "max": 0.19891759999999997,
+            "count": 36
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5158304,
+            "min": 0.5158304,
+            "max": 0.984688,
+            "count": 36
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0014549842400000002,
+            "min": 0.0014549842400000002,
+            "max": 0.00494598824,
+            "count": 36
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.005819936960000001,
+            "min": 0.005819936960000001,
+            "max": 0.0242359312,
+            "count": 36
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.90909090909091,
+            "min": 3.022727272727273,
+            "max": 26.90909090909091,
+            "count": 36
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1184.0,
+            "min": 133.0,
+            "max": 1480.0,
+            "count": 36
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.90909090909091,
+            "min": 3.022727272727273,
+            "max": 26.90909090909091,
+            "count": 36
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1184.0,
+            "min": 133.0,
+            "max": 1480.0,
+            "count": 36
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 36
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 36
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1714813702",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --force --run-id=SnowballTarget3 --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1714814511"
+    },
+    "total": 808.9773728229998,
+    "count": 1,
+    "self": 0.012453610999273224,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05065045300034399,
+            "count": 1,
+            "self": 0.05065045300034399
+        },
+        "TrainerController.start_learning": {
+            "total": 808.9142687590002,
+            "count": 1,
+            "self": 1.9795725669919193,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.5851128809999864,
+                    "count": 1,
+                    "self": 2.5851128809999864
+                },
+                "TrainerController.advance": {
+                    "total": 804.0989159740084,
+                    "count": 33001,
+                    "self": 0.4834191440154427,
+                    "children": {
+                        "env_step": {
+                            "total": 803.6154968299929,
+                            "count": 33001,
+                            "self": 520.7575256590162,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 282.35716918894013,
+                                    "count": 33001,
+                                    "self": 2.5989544428734916,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 279.75821474606664,
+                                            "count": 33001,
+                                            "self": 279.75821474606664
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.5008019820365917,
+                                    "count": 33000,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 805.5951890579781,
+                                            "count": 33000,
+                                            "is_parallel": true,
+                                            "self": 402.1318842810192,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0032390200003646896,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0008766969999669527,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.002362323000397737,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002362323000397737
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03659387499965305,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006553569996867736,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003889899999194313,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003889899999194313
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.0336073779999424,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0336073779999424
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0019421500001044478,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003677839999909338,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001574366000113514,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001574366000113514
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 403.4633047769589,
+                                                    "count": 32999,
+                                                    "is_parallel": true,
+                                                    "self": 18.4526843290937,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 9.606960499925663,
+                                                            "count": 32999,
+                                                            "is_parallel": true,
+                                                            "self": 9.606960499925663
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 315.35880058793555,
+                                                            "count": 32999,
+                                                            "is_parallel": true,
+                                                            "self": 315.35880058793555
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 60.04485936000401,
+                                                            "count": 32999,
+                                                            "is_parallel": true,
+                                                            "self": 11.246593000818393,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 48.79826635918562,
+                                                                    "count": 329990,
+                                                                    "is_parallel": true,
+                                                                    "self": 48.79826635918562
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00010824699984368635,
+                    "count": 1,
+                    "self": 0.00010824699984368635,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 794.0796448990204,
+                                    "count": 1171886,
+                                    "is_parallel": true,
+                                    "self": 24.530406085900722,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 437.4762247271183,
+                                            "count": 1171887,
+                                            "is_parallel": true,
+                                            "self": 437.0641351051181,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.41208962200016686,
+                                                    "count": 3,
+                                                    "is_parallel": true,
+                                                    "self": 0.41208962200016686
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 332.0730140860014,
+                                            "count": 164,
+                                            "is_parallel": true,
+                                            "self": 97.32214598001883,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 234.7508681059826,
+                                                    "count": 8378,
+                                                    "is_parallel": true,
+                                                    "self": 234.7508681059826
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.2505590900000243,
+                    "count": 1,
+                    "self": 0.001279290000184119,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.24927979999984018,
+                            "count": 1,
+                            "self": 0.24927979999984018
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,56 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 21.636363636363637,
+                "creation_time": 1714813928.020272,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.636363636363637,
+                "creation_time": 1714814149.7606823,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 26.636363636363637,
+                "creation_time": 1714814373.3220341,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 362912,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-362912.onnx",
+                "reward": null,
+                "creation_time": 1714814511.5292404,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-362912.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 362912,
+            "file_path": "results/SnowballTarget3/SnowballTarget.onnx",
+            "reward": null,
+            "creation_time": 1714814511.5292404,
+            "auxillary_file_paths": [
+                "results/SnowballTarget3/SnowballTarget/SnowballTarget-362912.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.1+cu121"
+    }
+}