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: ShamikS/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 sha256:4e955291f305d18f9ddbf34c6d7317fb9e5e533408b1a522ef6539580f276359
+size 650646

SnowballTarget/SnowballTarget-149952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2be233a45c356d7bcb6cb7fb4d596adc2c9ea082d924139c54ce29e04702e5
+size 650646

SnowballTarget/SnowballTarget-149952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89111f511a95a467c047c1ba85382a57b0eedbde7c97f1d95f3cffe0a14c293
+size 3849710

SnowballTarget/SnowballTarget-199976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e955291f305d18f9ddbf34c6d7317fb9e5e533408b1a522ef6539580f276359
+size 650646

SnowballTarget/SnowballTarget-199976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c66e10b8681f234af8960b42ff6b786fce07bc01fa2e16f7465626eedde962
+size 3849710

SnowballTarget/SnowballTarget-200424.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e955291f305d18f9ddbf34c6d7317fb9e5e533408b1a522ef6539580f276359
+size 650646

SnowballTarget/SnowballTarget-200424.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:709d21dfe0b90c253ba9ee5e6ba254bfce2f0d1b6b1c151331c5936293c9f6a8
+size 3849710

SnowballTarget/SnowballTarget-2112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5701bbf5c00560f82809c90293cc01ca2f9d7a0b273986558ed852b89fb6a5a
+size 649740

SnowballTarget/SnowballTarget-2112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32875e0d8b4aa7fa36dc75274ea4b9379e69b2b63b970845752c62e02a5e550c
+size 1286056

SnowballTarget/SnowballTarget-4224.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5701bbf5c00560f82809c90293cc01ca2f9d7a0b273986558ed852b89fb6a5a
+size 649740

SnowballTarget/SnowballTarget-4224.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3be1fe676e36c1e7396678ea66f33f5371f46c50464ab1005a342e0a50d1ab6d
+size 1286056

SnowballTarget/SnowballTarget-49968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546bcac18603c3b31f0e8ba3d672f010565fb26e347037ec337379d8cf828d7c
+size 650646

SnowballTarget/SnowballTarget-49968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555e7c1b0bd6ee517855b1ae47b39fdda04a5ff247ba0b3c830defb2227bc56a
+size 3849635

SnowballTarget/SnowballTarget-6336.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5701bbf5c00560f82809c90293cc01ca2f9d7a0b273986558ed852b89fb6a5a
+size 649740

SnowballTarget/SnowballTarget-6336.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a28493b7387b36d96d073b02af11bc72f5fa8e69a3185402469230ce813c9cb
+size 1286056

SnowballTarget/SnowballTarget-8448.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5701bbf5c00560f82809c90293cc01ca2f9d7a0b273986558ed852b89fb6a5a
+size 649740

SnowballTarget/SnowballTarget-8448.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:846ff2cf31f1bf1ff22828a4cd10fd7c4f76d13678292fcb66ed04cadef54399
+size 1286056

SnowballTarget/SnowballTarget-99992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3676ed675cd117ac884655ea79801a5541cbb8d74c54414d188a9c5e8d40340c
+size 650646

SnowballTarget/SnowballTarget-99992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d649cbbbde926b469fe16da8ae280f12a6f2861276e2e1d82133776a43e9026
+size 3849635

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f24eeee24484c6be6f5ee1c8bf1eb2e24ef79cca584366a84b8f77bb768e71
+size 3848821

SnowballTarget/events.out.tfevents.1784466973.shamik.90651.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e605628468fb1b008f25f76e62a2e8221fda1a900ed3d390900bbde0be377e
+size 1114

SnowballTarget/events.out.tfevents.1784467255.shamik.91932.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b608b1288f21c8c2568423a9b87025d18f4c6695d42a17e5da9d6c3ecb7c9b
+size 1114

SnowballTarget/events.out.tfevents.1784467691.shamik.93972.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d5f45c1d5151dd704718e3de848661980ae54931f99162ace99dd56408f67ce
+size 1114

SnowballTarget/events.out.tfevents.1784476751.shamik.135377.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:138c726938f3b8261f02bd476a82de858fc2d35b88a44f360fcafe7cb5b38330
+size 1114

SnowballTarget/events.out.tfevents.1784477784.shamik.140075.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc4aed3341e2af81370a97c4fab8eaa7e7c23e8265a92417ae635ecc4f3038da
+size 1114

SnowballTarget/events.out.tfevents.1784478007.shamik.141252.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50003c05e38b50f01bca56b0604200087d98fca9598d9d17af24a481aedab0c5
+size 1114

SnowballTarget/events.out.tfevents.1784478088.shamik.141897.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c2b8a741a61f2c1caa8c1902f721df72c4abd9d5ddc0607169c7b7ba01a6ea
+size 22886

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": "./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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "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: ./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: SnowballTarget1
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,309 @@
+Mono path[0] = '/home/shamik/Documents/RL/HF_course/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/home/shamik/Documents/RL/HF_course/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 /home/shamik/Documents/RL/HF_course/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
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.043 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: 0.349685 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 8 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]: 5155 frames, [16.0 KB-32.0 KB]: 87 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 252 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 14]
+      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_Job.Worker 13]
+      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 8
+      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 15
+      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_Job.Worker 11]
+      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 12]
+      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 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]: 5243 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5243 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]: 4247 frames, [64.0 KB-128.0 KB]: 996 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 68.2 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5243 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]: 5243 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]: 5242 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]: 5243 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]: 5243 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": 0.9232632517814636,
+            "min": 0.9232632517814636,
+            "max": 2.8903205394744873,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 9526.23046875,
+            "min": 6136.150390625,
+            "max": 27763.0234375,
+            "count": 20
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199976.0,
+            "min": 9984.0,
+            "max": 199976.0,
+            "count": 20
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199976.0,
+            "min": 9984.0,
+            "max": 199976.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.52334976196289,
+            "min": 0.04826056957244873,
+            "max": 12.52334976196289,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2567.28662109375,
+            "min": 1.1582536697387695,
+            "max": 2567.28662109375,
+            "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
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 19
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 19
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06464404309232372,
+            "min": 0.06402833573277651,
+            "max": 0.07461803034290343,
+            "count": 19
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.3232202154616186,
+            "min": 0.25611334293110605,
+            "max": 0.3674637621993943,
+            "count": 19
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.20672569923541126,
+            "min": 0.12773027302076417,
+            "max": 0.2861822873353958,
+            "count": 19
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 1.0336284961770563,
+            "min": 0.6386513651038209,
+            "max": 1.430911436676979,
+            "count": 19
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 6.96009768e-06,
+            "min": 6.96009768e-06,
+            "max": 0.00027756000748,
+            "count": 19
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.48004884e-05,
+            "min": 3.48004884e-05,
+            "max": 0.0013878000374,
+            "count": 19
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10232,
+            "min": 0.10232,
+            "max": 0.19251999999999997,
+            "count": 19
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5115999999999999,
+            "min": 0.4290800000000001,
+            "max": 0.9625999999999999,
+            "count": 19
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.000125768,
+            "min": 0.000125768,
+            "max": 0.004626748000000001,
+            "count": 19
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00062884,
+            "min": 0.00062884,
+            "max": 0.023133740000000003,
+            "count": 19
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.0,
+            "min": 3.6363636363636362,
+            "max": 25.0,
+            "count": 19
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1375.0,
+            "min": 200.0,
+            "max": 1375.0,
+            "count": 19
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.0,
+            "min": 3.6363636363636362,
+            "max": 25.0,
+            "count": 19
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1375.0,
+            "min": 200.0,
+            "max": 1375.0,
+            "count": 19
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1784478087",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/home/shamik/anaconda3/envs/rl-env-py310/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
+        "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": "1784478244"
+    },
+    "total": 156.51600448099998,
+    "count": 1,
+    "self": 0.16676497899970855,
+    "children": {
+        "run_training.setup": {
+            "total": 0.01253139199980069,
+            "count": 1,
+            "self": 0.01253139199980069
+        },
+        "TrainerController.start_learning": {
+            "total": 156.33670811000047,
+            "count": 1,
+            "self": 0.26522381715403753,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.2688414640033443,
+                    "count": 1,
+                    "self": 1.2688414640033443
+                },
+                "TrainerController.advance": {
+                    "total": 154.76168821884494,
+                    "count": 17474,
+                    "self": 0.11390320175632951,
+                    "children": {
+                        "env_step": {
+                            "total": 154.6477850170886,
+                            "count": 17474,
+                            "self": 101.56403748774028,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 52.95641476590754,
+                                    "count": 17474,
+                                    "self": 0.6337312098221446,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 52.322683556085394,
+                                            "count": 17474,
+                                            "self": 52.322683556085394
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.1273327634407906,
+                                    "count": 17474,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 156.04375941084072,
+                                            "count": 17474,
+                                            "is_parallel": true,
+                                            "self": 81.45517131637826,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0012604310031747445,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0003426160074013751,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0009178149957733694,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0009178149957733694
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.012819602001400199,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00023316800070460886,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00015630300185875967,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00015630300185875967
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.011519275001774076,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.011519275001774076
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0009108559970627539,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00020338399554020725,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0007074720015225466,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0007074720015225466
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 74.58858809446247,
+                                                    "count": 17473,
+                                                    "is_parallel": true,
+                                                    "self": 3.2417108550071134,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 1.6185265582935244,
+                                                            "count": 17473,
+                                                            "is_parallel": true,
+                                                            "self": 1.6185265582935244
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 60.54157073416718,
+                                                            "count": 17473,
+                                                            "is_parallel": true,
+                                                            "self": 60.54157073416718
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 9.186779946994648,
+                                                            "count": 17473,
+                                                            "is_parallel": true,
+                                                            "self": 1.8350566700937634,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 7.351723276900884,
+                                                                    "count": 174730,
+                                                                    "is_parallel": true,
+                                                                    "self": 7.351723276900884
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00013597200086223893,
+                    "count": 1,
+                    "self": 0.00013597200086223893,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 154.52339641787694,
+                                    "count": 166930,
+                                    "is_parallel": true,
+                                    "self": 1.196502853414131,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 86.64063019246532,
+                                            "count": 166930,
+                                            "is_parallel": true,
+                                            "self": 86.30622246046914,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.3344077319961798,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.3344077319961798
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 66.68626337199748,
+                                            "count": 87,
+                                            "is_parallel": true,
+                                            "self": 14.914750962019752,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 51.77151240997773,
+                                                    "count": 4434,
+                                                    "is_parallel": true,
+                                                    "self": 51.77151240997773
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.04081863799729035,
+                    "count": 1,
+                    "self": 0.00046686999485245906,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.04035176800243789,
+                            "count": 1,
+                            "self": 0.04035176800243789
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,101 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 6336,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-6336.onnx",
+                "reward": null,
+                "creation_time": 1784476729.2685928,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-6336.pt"
+                ]
+            },
+            {
+                "steps": 8448,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-8448.onnx",
+                "reward": null,
+                "creation_time": 1784476757.8706763,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-8448.pt"
+                ]
+            },
+            {
+                "steps": 8448,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-8448.onnx",
+                "reward": null,
+                "creation_time": 1784477785.846445,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-8448.pt"
+                ]
+            },
+            {
+                "steps": 8448,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-8448.onnx",
+                "reward": null,
+                "creation_time": 1784478007.9467611,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-8448.pt"
+                ]
+            },
+            {
+                "steps": 49968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49968.onnx",
+                "reward": 13.363636363636363,
+                "creation_time": 1784478125.1754537,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49968.pt"
+                ]
+            },
+            {
+                "steps": 99992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99992.onnx",
+                "reward": 21.0,
+                "creation_time": 1784478164.5934114,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99992.pt"
+                ]
+            },
+            {
+                "steps": 149952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149952.onnx",
+                "reward": 23.454545454545453,
+                "creation_time": 1784478204.5125003,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149952.pt"
+                ]
+            },
+            {
+                "steps": 199976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199976.onnx",
+                "reward": 24.818181818181817,
+                "creation_time": 1784478244.2386763,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199976.pt"
+                ]
+            },
+            {
+                "steps": 200424,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200424.onnx",
+                "reward": 24.818181818181817,
+                "creation_time": 1784478244.3031275,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200424.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 200424,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 24.818181818181817,
+            "creation_time": 1784478244.3031275,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200424.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cu128"
+    }
+}