Unit 5 SnowballTarget

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: mhpromit7473/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:c09d2076bd507bf4cb74e903b4c1b172aff9d403720f4707ccd7ecf5e5d96563
+size 650647

SnowballTarget/SnowballTarget-1000248.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c09d2076bd507bf4cb74e903b4c1b172aff9d403720f4707ccd7ecf5e5d96563
+size 650647

SnowballTarget/SnowballTarget-1000248.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e65161e683f51739a28d418997fd0e41775efdeedaa366d6598f07bc1833cf
+size 3850705

SnowballTarget/SnowballTarget-599936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e34af52db2b901419f9ea8084f126d57f133d6820aebadd66a9f6f6d4cc78c1
+size 650647

SnowballTarget/SnowballTarget-599936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39eb8c18ee48817a8688049e9e88ce3ee0f5f8fe5442ebdd759f816fb65fb61e
+size 3850564

SnowballTarget/SnowballTarget-649936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc223839e6320868034bd7e5ba1a2d0909ad127f063c5cc3de2f5feccf8006e9
+size 650647

SnowballTarget/SnowballTarget-649936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:393fe1cff9d53571bee07e11bbd679d76b1ef1711d0080b7ed5cc164601e29ed
+size 3850564

SnowballTarget/SnowballTarget-699960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8670ef3a33e31886d4b6526ddd6d17f96205f22abb015be5d5c6f62e7f18995f
+size 650647

SnowballTarget/SnowballTarget-699960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e239acd0fb666d915a7039340126fe3a0e070cba8e1e44c5da8d3872c85b26
+size 3850564

SnowballTarget/SnowballTarget-749984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e67ad0cdb740ce6d95f71103a9b673853466add1ad31da609014015fcfea57d9
+size 650647

SnowballTarget/SnowballTarget-749984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2df85bba79b78150a27ce3d32ab91457f1f828b1ff8cb3499733d8a75053655
+size 3850564

SnowballTarget/SnowballTarget-799984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:790a2da5d721a8916c32c67e430881da220462a5d6b9862a8a34de9dd779d176
+size 650647

SnowballTarget/SnowballTarget-799984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b69e6b4f75542904c4aefad710dc35023b97a26fb2e2852994d2a761c0b7df1e
+size 3850564

SnowballTarget/SnowballTarget-849944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb555ed832b5707ac8095c0231427b5fb26f437f4c39cd4f06e78daf7bcd53b
+size 650647

SnowballTarget/SnowballTarget-849944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e51488b7a694bb0d5164aa3bb6c54a189db712fdbc9f315bbc711d3b6bf7cb
+size 3850564

SnowballTarget/SnowballTarget-899968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ad19a32f8d7559f32a231000eed44f888467481ccd179dc9f14d76142b33ee
+size 650647

SnowballTarget/SnowballTarget-899968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d92143084905579c44b492a9d2b3e0b00f96f33b1e410cb2c8ff75df29b38a
+size 3850564

SnowballTarget/SnowballTarget-949992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a270f0fbf237ed7596d3fdcd0c7dfe286eda16448e38865b6ec76e7160f13f
+size 650647

SnowballTarget/SnowballTarget-949992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb336b3d026e2dd17981cfa96806d98cc457e3305e0e79610991d026a352895d
+size 3850564

SnowballTarget/SnowballTarget-999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c09d2076bd507bf4cb74e903b4c1b172aff9d403720f4707ccd7ecf5e5d96563
+size 650647

SnowballTarget/SnowballTarget-999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ad3f5e41d5846b4d2d657e8d9fcd6b81b62fdac87f33a073aa8deaa1e277d5
+size 3850564

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860ef5aecefcc16e1ddf7a37aa3a9694ac0596584fe5c14dc7d92fb8df417203
+size 3849717

SnowballTarget/events.out.tfevents.1777467920.thinkbook.322372.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c168b904f0e8cca1b45c7efeb1f12d0d8de6f49bcb0404c081dc33f987d7b37
+size 10812

SnowballTarget/events.out.tfevents.1777468978.thinkbook.333009.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a328de7f14271570a71f495b26707f170909e3a3aea2d8115840439c5097cdf0
+size 1170

SnowballTarget/events.out.tfevents.1777469101.thinkbook.334283.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ee7870ddf40e2e83c58a16cb4b07dc8203d3fb25872c6e56a46e137d2c4531
+size 79272

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": 1000000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "training-envs-executables/linux/SnowballTarget/SnowballTarget/SnowballTarget.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": 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: 1000000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: training-envs-executables/linux/SnowballTarget/SnowballTarget/SnowballTarget.x86_64
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SnowballTarget1
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,289 @@
+Mono path[0] = '/home/mhpromit7473/deep-rl-course-hf/training-envs-executables/linux/SnowballTarget/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/home/mhpromit7473/deep-rl-course-hf/training-envs-executables/linux/SnowballTarget/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/mhpromit7473/deep-rl-course-hf/training-envs-executables/linux/SnowballTarget/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  0.121 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: 2.331025 ms
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+Setting up 6 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 25486 frames, [16.0 KB-32.0 KB]: 431 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 264 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 228.9 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 6
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 11
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 44
+    [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]: 11226 frames, [8.0 MB-16.0 MB]: 14692 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 14.3 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 25918 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.7 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]: 24901 frames, [64.0 KB-128.0 KB]: 1017 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.8 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 25918 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]: 25918 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]: 25917 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]: 25918 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]: 25918 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": 0.45387300848960876,
+            "min": 0.4342562258243561,
+            "max": 1.8801276683807373,
+            "count": 96
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 4633.1357421875,
+            "min": 1323.60986328125,
+            "max": 17677.826171875,
+            "count": 96
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 96
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 96
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 999992.0,
+            "min": 59952.0,
+            "max": 999992.0,
+            "count": 95
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 999992.0,
+            "min": 59952.0,
+            "max": 999992.0,
+            "count": 95
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 14.051997184753418,
+            "min": 6.840594291687012,
+            "max": 14.108394622802734,
+            "count": 95
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2740.139404296875,
+            "min": 1333.9158935546875,
+            "max": 2892.220947265625,
+            "count": 95
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07358759555398708,
+            "min": 0.05805854102586369,
+            "max": 0.07793183089540667,
+            "count": 95
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.29435038221594834,
+            "min": 0.23223416410345477,
+            "max": 0.3806744671314578,
+            "count": 95
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.15896714076984164,
+            "min": 0.14173051123233402,
+            "max": 0.3036635354407789,
+            "count": 95
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.6358685630793666,
+            "min": 0.5669220449293361,
+            "max": 1.3392533300554053,
+            "count": 95
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 1.5756994748000017e-06,
+            "min": 1.5756994748000017e-06,
+            "max": 0.0002833956055348,
+            "count": 95
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 6.302797899200007e-06,
+            "min": 6.302797899200007e-06,
+            "max": 0.001402128032624,
+            "count": 95
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.1005252,
+            "min": 0.1005252,
+            "max": 0.1944652,
+            "count": 95
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.4021008,
+            "min": 0.4021008,
+            "max": 0.967376,
+            "count": 95
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 3.6207480000000034e-05,
+            "min": 3.6207480000000034e-05,
+            "max": 0.00472381348,
+            "count": 95
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00014482992000000014,
+            "min": 0.00014482992000000014,
+            "max": 0.0233720624,
+            "count": 95
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 95
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 95
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 27.681818181818183,
+            "min": 17.954545454545453,
+            "max": 28.022727272727273,
+            "count": 95
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1218.0,
+            "min": 790.0,
+            "max": 1541.0,
+            "count": 95
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 27.681818181818183,
+            "min": 17.954545454545453,
+            "max": 28.022727272727273,
+            "count": 95
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1218.0,
+            "min": 790.0,
+            "max": 1541.0,
+            "count": 95
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1777469100",
+        "python_version": "3.10.12 (main, Mar  3 2026, 11:56:32) [GCC 11.4.0]",
+        "command_line_arguments": "/home/mhpromit7473/.local/bin/mlagents-learn config/ppo/SnowballTarget.yaml --env=training-envs-executables/linux/SnowballTarget/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --resume",
+        "mlagents_version": "1.1.0",
+        "mlagents_envs_version": "1.1.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.11.0+cu128",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1777473051"
+    },
+    "total": 3950.509240911004,
+    "count": 1,
+    "self": 0.529804032001266,
+    "children": {
+        "run_training.setup": {
+            "total": 0.10699782500159927,
+            "count": 1,
+            "self": 0.10699782500159927
+        },
+        "TrainerController.start_learning": {
+            "total": 3949.872439054001,
+            "count": 1,
+            "self": 4.581158673285245,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.192181657999754,
+                    "count": 1,
+                    "self": 3.192181657999754
+                },
+                "TrainerController.advance": {
+                    "total": 3941.933289790719,
+                    "count": 86392,
+                    "self": 5.132914953384898,
+                    "children": {
+                        "env_step": {
+                            "total": 2704.0614437438344,
+                            "count": 86392,
+                            "self": 1894.266331887131,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 806.8457410449664,
+                                    "count": 86392,
+                                    "self": 19.636642739027593,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 787.2090983059388,
+                                            "count": 86392,
+                                            "self": 787.2090983059388
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.949370811737026,
+                                    "count": 86392,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 3939.9174563852794,
+                                            "count": 86392,
+                                            "is_parallel": true,
+                                            "self": 2367.980027331032,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.00362984900129959,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0011823039967566729,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.002447545004542917,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002447545004542917
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.05104765400028555,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0004840279980271589,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003932760009774938,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003932760009774938
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.048161873000935884,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.048161873000935884
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0020084770003450103,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005820529950142372,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001426424005330773,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001426424005330773
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1571.9374290542473,
+                                                    "count": 86391,
+                                                    "is_parallel": true,
+                                                    "self": 55.13261123140546,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 42.41011388066909,
+                                                            "count": 86391,
+                                                            "is_parallel": true,
+                                                            "self": 42.41011388066909
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1315.6951957544334,
+                                                            "count": 86391,
+                                                            "is_parallel": true,
+                                                            "self": 1315.6951957544334
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 158.6995081877394,
+                                                            "count": 86391,
+                                                            "is_parallel": true,
+                                                            "self": 40.5069470071212,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 118.19256118061821,
+                                                                    "count": 863910,
+                                                                    "is_parallel": true,
+                                                                    "self": 118.19256118061821
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 1232.7389310934996,
+                            "count": 86392,
+                            "self": 6.652593582588452,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 274.38434630194024,
+                                    "count": 86392,
+                                    "self": 271.2760722069288,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 3.1082740950114385,
+                                            "count": 20,
+                                            "self": 3.1082740950114385
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 951.7019912089709,
+                                    "count": 431,
+                                    "self": 286.8661666713633,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 664.8358245376076,
+                                            "count": 21978,
+                                            "self": 664.8358245376076
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.243002770934254e-06,
+                    "count": 1,
+                    "self": 1.243002770934254e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.16580768899439136,
+                    "count": 1,
+                    "self": 0.0018561229953775182,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.16395156599901384,
+                            "count": 1,
+                            "self": 0.16395156599901384
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0",
+        "torch_version": "2.11.0+cu128"
+    },
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 599936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.onnx",
+                "reward": 26.727272727272727,
+                "creation_time": 1777471564.6333435,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.pt"
+                ]
+            },
+            {
+                "steps": 649936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.onnx",
+                "reward": 27.363636363636363,
+                "creation_time": 1777471749.256455,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.pt"
+                ]
+            },
+            {
+                "steps": 699960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699960.onnx",
+                "reward": 28.454545454545453,
+                "creation_time": 1777471935.1607049,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-699960.pt"
+                ]
+            },
+            {
+                "steps": 749984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.onnx",
+                "reward": 28.272727272727273,
+                "creation_time": 1777472121.2143943,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.pt"
+                ]
+            },
+            {
+                "steps": 799984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.onnx",
+                "reward": 26.818181818181817,
+                "creation_time": 1777472305.845005,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.pt"
+                ]
+            },
+            {
+                "steps": 849944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.onnx",
+                "reward": 27.272727272727273,
+                "creation_time": 1777472493.7242799,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.pt"
+                ]
+            },
+            {
+                "steps": 899968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899968.onnx",
+                "reward": 26.636363636363637,
+                "creation_time": 1777472679.6969743,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-899968.pt"
+                ]
+            },
+            {
+                "steps": 949992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-949992.onnx",
+                "reward": 27.818181818181817,
+                "creation_time": 1777472865.7359695,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-949992.pt"
+                ]
+            },
+            {
+                "steps": 999992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.onnx",
+                "reward": 28.0,
+                "creation_time": 1777473050.345841,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.pt"
+                ]
+            },
+            {
+                "steps": 1000248,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000248.onnx",
+                "reward": 28.0,
+                "creation_time": 1777473050.5650613,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000248.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000248,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 28.0,
+            "creation_time": 1777473050.5650613,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000248.pt"
+            ]
+        }
+    }
+}