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: partzel/ppo-SnowballTarget-no-curiosity
+  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 sha256:69e65f15485356024585c31246bf55991b71c6cd3fe7d7e325d0a1f69921057e
+size 331587

SnowballTarget/SnowballTarget-149960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff4077140f34952a05c67864412ccb9b40dd884cdb74e9a6bf9596e8ea666e7
+size 331587

SnowballTarget/SnowballTarget-149960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4262870b0867a1161a18a8f22d68b11a3019c0d2cf40ae1c8d3328410f4f8ba4
+size 1946420

SnowballTarget/SnowballTarget-199976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b90065642f2107a5141e9b1619f73500b3970be136868e6c1dcd63aa38b003
+size 331587

SnowballTarget/SnowballTarget-199976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09236f5d580c82756ef47260f15022a045ee38453eb27bae2f2cb29394a0d9d
+size 1946420

SnowballTarget/SnowballTarget-249968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e65f15485356024585c31246bf55991b71c6cd3fe7d7e325d0a1f69921057e
+size 331587

SnowballTarget/SnowballTarget-249968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7daaf87fac123c58c5db0d2059f73be2904cc3f9fcbc8de1ac63b2950ef1887e
+size 1946420

SnowballTarget/SnowballTarget-250184.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e65f15485356024585c31246bf55991b71c6cd3fe7d7e325d0a1f69921057e
+size 331587

SnowballTarget/SnowballTarget-250184.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd1b8eaa0152b6cfda0ce8265c8656bb405ad74911a0ec24b9e23f33c8d248e2
+size 1946420

SnowballTarget/SnowballTarget-49984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f088aa081145e16bd1f5b02f679f05f6fa5660cc8922262b2ce040fb5c758efe
+size 331587

SnowballTarget/SnowballTarget-49984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8078649235d490eaa2af68f7ed53258e80f20ea5ca30f83bf255569b9597c3ce
+size 1946327

SnowballTarget/SnowballTarget-99936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e02ebb74b5cbc28833283e9c46b96e2b4695d50f2186d665bf59cd0f84d9609
+size 331587

SnowballTarget/SnowballTarget-99936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e96207489e115b915c5d9a27366d93acd499e34774ee31c68d18729b6bf4cc1
+size 1946327

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd250f8890e33ac1c33dcadcb98ba8fd083fa1504ff2443d34f480046989afe6
+size 1945397

SnowballTarget/events.out.tfevents.1756157624.50aa3ff16095.16435.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a8aa4b463ee3682c7c98a4be93750d4e45a8006c3fb23c62fdb909d7cfe0ea4
+size 32832

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 4096, "learning_rate": 0.0005, "beta": 0.007, "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": 128, "num_layers": 3, "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": 250000, "time_horizon": 72, "summary_freq": 10000, "threaded": false, "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": "SnowballTarget_nocuriosity_emp", "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: 4096
+      learning_rate: 0.0005
+      beta: 0.007
+      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: 128
+      num_layers: 3
+      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: 250000
+    time_horizon: 72
+    summary_freq: 10000
+    threaded: false
+    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: SnowballTarget_nocuriosity_emp
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,259 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c: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  0.087 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: 0.641150 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]: 6710 frames, [16.0 KB-32.0 KB]: 113 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]: 6824 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 7.5 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 6824 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]: 6234 frames, [64.0 KB-128.0 KB]: 590 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]: 6824 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]: 6824 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]: 6823 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]: 6824 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]: 6824 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 +1,362 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 1.1421180963516235,
+            "min": 1.1329169273376465,
+            "max": 2.879828691482544,
+            "count": 25
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 10955.197265625,
+            "min": 10955.197265625,
+            "max": 29904.140625,
+            "count": 25
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 249968.0,
+            "min": 9952.0,
+            "max": 249968.0,
+            "count": 25
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 249968.0,
+            "min": 9952.0,
+            "max": 249968.0,
+            "count": 25
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.810078620910645,
+            "min": 0.18433061242103577,
+            "max": 12.810078620910645,
+            "count": 25
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1908.70166015625,
+            "min": 27.280929565429688,
+            "max": 1916.487548828125,
+            "count": 25
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 25
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 25
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.772727272727273,
+            "min": 3.25,
+            "max": 25.772727272727273,
+            "count": 25
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1134.0,
+            "min": 143.0,
+            "max": 1416.0,
+            "count": 25
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.772727272727273,
+            "min": 3.25,
+            "max": 25.772727272727273,
+            "count": 25
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1134.0,
+            "min": 143.0,
+            "max": 1416.0,
+            "count": 25
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07090350354109451,
+            "min": 0.06402847969587253,
+            "max": 0.0773912613367429,
+            "count": 25
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.14180700708218902,
+            "min": 0.12805695939174505,
+            "max": 0.2230018813179948,
+            "count": 25
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.21668023360418337,
+            "min": 0.12169648905960367,
+            "max": 0.2935980224336674,
+            "count": 25
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.43336046720836674,
+            "min": 0.24339297811920735,
+            "max": 0.8807940673010022,
+            "count": 25
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 1.1600097680000001e-05,
+            "min": 1.1600097680000001e-05,
+            "max": 0.0004868000026399999,
+            "count": 25
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 2.3200195360000002e-05,
+            "min": 2.3200195360000002e-05,
+            "max": 0.00128880004224,
+            "count": 25
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10231999999999997,
+            "min": 0.10231999999999997,
+            "max": 0.19736,
+            "count": 25
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.20463999999999993,
+            "min": 0.20463999999999993,
+            "max": 0.55776,
+            "count": 25
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.000172168,
+            "min": 0.000172168,
+            "max": 0.006815464,
+            "count": 25
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.000344336,
+            "min": 0.000344336,
+            "max": 0.018047424,
+            "count": 25
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 25
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 25
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1756157623",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget_nocuriosity_emp --no-graphics",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.8.0+cu128",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1756158157"
+    },
+    "total": 533.699400899,
+    "count": 1,
+    "self": 0.4432885069995791,
+    "children": {
+        "run_training.setup": {
+            "total": 0.022569133000160946,
+            "count": 1,
+            "self": 0.022569133000160946
+        },
+        "TrainerController.start_learning": {
+            "total": 533.2335432590003,
+            "count": 1,
+            "self": 0.46520541799918647,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.8440969479997875,
+                    "count": 1,
+                    "self": 1.8440969479997875
+                },
+                "TrainerController.advance": {
+                    "total": 530.8450164240012,
+                    "count": 22744,
+                    "self": 0.47770008594443425,
+                    "children": {
+                        "env_step": {
+                            "total": 380.2842085210391,
+                            "count": 22744,
+                            "self": 291.2741662920548,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 88.71820381199313,
+                                    "count": 22744,
+                                    "self": 1.5717487309275384,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 87.1464550810656,
+                                            "count": 22744,
+                                            "self": 87.1464550810656
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.29183841699114055,
+                                    "count": 22744,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 531.6714237400356,
+                                            "count": 22744,
+                                            "is_parallel": true,
+                                            "self": 276.2444947450508,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002012717000070552,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006104379995122144,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0014022790005583374,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0014022790005583374
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.038336489999892365,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006188199999996868,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004377780001050269,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004377780001050269
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03521203699983744,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03521203699983744
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.002067854999950214,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00039770599960320396,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0016701490003470099,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0016701490003470099
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 255.4269289949848,
+                                                    "count": 22743,
+                                                    "is_parallel": true,
+                                                    "self": 12.147335247943374,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 6.841720388033082,
+                                                            "count": 22743,
+                                                            "is_parallel": true,
+                                                            "self": 6.841720388033082
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 196.38263730192875,
+                                                            "count": 22743,
+                                                            "is_parallel": true,
+                                                            "self": 196.38263730192875
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 40.05523605707958,
+                                                            "count": 22743,
+                                                            "is_parallel": true,
+                                                            "self": 7.111828846165736,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 32.94340721091385,
+                                                                    "count": 227430,
+                                                                    "is_parallel": true,
+                                                                    "self": 32.94340721091385
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 150.08310781701766,
+                            "count": 22744,
+                            "self": 0.5490512520032098,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 30.811707147016023,
+                                    "count": 22744,
+                                    "self": 30.327101302016217,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.4846058449998054,
+                                            "count": 5,
+                                            "self": 0.4846058449998054
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 118.72234941799843,
+                                    "count": 56,
+                                    "self": 48.25640896302639,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 70.46594045497204,
+                                            "count": 5712,
+                                            "self": 70.46594045497204
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 9.770001270226203e-07,
+                    "count": 1,
+                    "self": 9.770001270226203e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.0792234919999828,
+                    "count": 1,
+                    "self": 0.0006349229997795192,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.07858856900020328,
+                            "count": 1,
+                            "self": 0.07858856900020328
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,74 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 49984,
+                "file_path": "results/SnowballTarget_nocuriosity_emp/SnowballTarget/SnowballTarget-49984.onnx",
+                "reward": null,
+                "creation_time": 1756157733.4097483,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget_nocuriosity_emp/SnowballTarget/SnowballTarget-49984.pt"
+                ]
+            },
+            {
+                "steps": 99936,
+                "file_path": "results/SnowballTarget_nocuriosity_emp/SnowballTarget/SnowballTarget-99936.onnx",
+                "reward": 18.818181818181817,
+                "creation_time": 1756157837.6120212,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget_nocuriosity_emp/SnowballTarget/SnowballTarget-99936.pt"
+                ]
+            },
+            {
+                "steps": 149960,
+                "file_path": "results/SnowballTarget_nocuriosity_emp/SnowballTarget/SnowballTarget-149960.onnx",
+                "reward": null,
+                "creation_time": 1756157944.6659415,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget_nocuriosity_emp/SnowballTarget/SnowballTarget-149960.pt"
+                ]
+            },
+            {
+                "steps": 199976,
+                "file_path": "results/SnowballTarget_nocuriosity_emp/SnowballTarget/SnowballTarget-199976.onnx",
+                "reward": 24.142857142857142,
+                "creation_time": 1756158051.2552476,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget_nocuriosity_emp/SnowballTarget/SnowballTarget-199976.pt"
+                ]
+            },
+            {
+                "steps": 249968,
+                "file_path": "results/SnowballTarget_nocuriosity_emp/SnowballTarget/SnowballTarget-249968.onnx",
+                "reward": 26.272727272727273,
+                "creation_time": 1756158156.6103802,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget_nocuriosity_emp/SnowballTarget/SnowballTarget-249968.pt"
+                ]
+            },
+            {
+                "steps": 250184,
+                "file_path": "results/SnowballTarget_nocuriosity_emp/SnowballTarget/SnowballTarget-250184.onnx",
+                "reward": 26.272727272727273,
+                "creation_time": 1756158156.709328,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget_nocuriosity_emp/SnowballTarget/SnowballTarget-250184.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 250184,
+            "file_path": "results/SnowballTarget_nocuriosity_emp/SnowballTarget.onnx",
+            "reward": 26.272727272727273,
+            "creation_time": 1756158156.709328,
+            "auxillary_file_paths": [
+                "results/SnowballTarget_nocuriosity_emp/SnowballTarget/SnowballTarget-250184.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cu128"
+    }
+}