empty

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-SnowballTarget
+      library_name: ml-agents
+---
+    
+  # **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://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  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. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
+  2. Step 1: Write your model_id: Agog/SnowballTarget3
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SnowballTarget.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373c177415c6799515ef86b1d64381973ad0beaa39f8a0fcca96c446f5b4c3ae
+size 645119

SnowballTarget/SnowballTarget-149976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c87432e3e5efd3a07682337a0838d0079af663a9afbe7fb6f9af2d0325bff5f7
+size 645119

SnowballTarget/SnowballTarget-149976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e349b5dee9bbc009c124acc2a7d11250086e01521ac6315f5918992a3ed11bb0
+size 3845224

SnowballTarget/SnowballTarget-199936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61771309f0e7abd0be6227df2dbef6d73b114bde60fffd37ffcd8100f7e2cacf
+size 645119

SnowballTarget/SnowballTarget-199936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4efb13a049b05bf474a119d411a7c5dd93177b157404c7be34264a4577771fdb
+size 3845224

SnowballTarget/SnowballTarget-200640.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61771309f0e7abd0be6227df2dbef6d73b114bde60fffd37ffcd8100f7e2cacf
+size 645119

SnowballTarget/SnowballTarget-200640.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b87397fa55fd8535345b682331202d2332c81a88c37cca6311f17e538b7f72
+size 3845210

SnowballTarget/SnowballTarget-249936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e895183f2e414b3ae9e711e1c2d001ebd22537962822b76d24b4fe73933483
+size 645119

SnowballTarget/SnowballTarget-249936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5698d29ecb16b24bcdc99d29af1a8444353b1b9dd435a59daa6bde9e79cf6e86
+size 3845210

SnowballTarget/SnowballTarget-299960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3fa5f37dd98b42d0c46b2e2a78473bf852342974eb94135181f635b9bf7ea93
+size 645119

SnowballTarget/SnowballTarget-299960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae5374fdfba7acd7a0628c797c85747b11d8af132800b6e36fcaecb2c611199
+size 3845210

SnowballTarget/SnowballTarget-349960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2982d6247509dc8858e427fe53f0358f800fe58e433cd90b13e8b0f323da94f3
+size 645119

SnowballTarget/SnowballTarget-349960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e7143ca00705fd52234282031cfdd4080de06e8115e4e1cbd57d93aba4434a
+size 3845210

SnowballTarget/SnowballTarget-399984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373c177415c6799515ef86b1d64381973ad0beaa39f8a0fcca96c446f5b4c3ae
+size 645119

SnowballTarget/SnowballTarget-399984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad5a2897a650f8d55c4bb58a1d856fc7618a199f0b4914b93051845b0a7d12c
+size 3845210

SnowballTarget/SnowballTarget-400048.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373c177415c6799515ef86b1d64381973ad0beaa39f8a0fcca96c446f5b4c3ae
+size 645119

SnowballTarget/SnowballTarget-400048.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0176415d13dd740a43bfa871adee030ed43cded25cee4e85658758c5fb82bc
+size 3845210

SnowballTarget/SnowballTarget-99976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a33f01c80b6f5615c9c9e3d6ab26ae4add69b0043f23c14ba0c181c110c2250
+size 645119

SnowballTarget/SnowballTarget-99976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66989e40616fe6657bb166c2a7b1b33d22e8aaf2d561e4c9a898914a6a1ff32a
+size 3845224

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0176415d13dd740a43bfa871adee030ed43cded25cee4e85658758c5fb82bc
+size 3845210

SnowballTarget/events.out.tfevents.1676486076.jonatan-System-Product-Name.4096940.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698b5230fe0227e086895eecd05135921dd622c9127c0963af158f8396b296d1
+size 6813

SnowballTarget/events.out.tfevents.1676486132.jonatan-System-Product-Name.4097855.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7730681822846f24a2685eda0b3502531f2412112ccb89a54f479b40f061f42d
+size 1983

SnowballTarget/events.out.tfevents.1676486170.jonatan-System-Product-Name.4098422.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c019c0cbfb210b682b17548657f39c2fd16fb0f2604173f02d77fd7327fceb
+size 16681

SnowballTarget/events.out.tfevents.1676486480.jonatan-System-Product-Name.4100994.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3bcd4a5f54b16788554c4257d6472f2ba376d27cde2006d9c62a5e81de36bdd
+size 1065

SnowballTarget/events.out.tfevents.1676486509.jonatan-System-Product-Name.4101350.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4fba80dd67209e28e1f2bd9ee9eff71f02f0cad514c747ca66d615b151ebd7c
+size 17617

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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 50000, "max_steps": 400000, "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, "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}, "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 +1,75 @@
+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
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    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
+    checkpoint_interval: 50000
+    max_steps: 400000
+    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
+  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
+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/jonatan/PycharmProjects/HuggingfaceDeepRLCourse/Unit5/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/home/jonatan/PycharmProjects/HuggingfaceDeepRLCourse/Unit5/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/jonatan/PycharmProjects/HuggingfaceDeepRLCourse/Unit5/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  0.078 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: 0.657072 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]: 5351 frames, [16.0 KB-32.0 KB]: 90 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 280 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 229.0 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 6
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 11
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 36
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5442 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.8 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5442 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.6 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]: 5281 frames, [64.0 KB-128.0 KB]: 161 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.0 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5442 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]: 5442 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]: 5441 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]: 5442 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]: 5442 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 +1,384 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.7013018727302551,
+            "min": 0.6640027165412903,
+            "max": 0.8622682094573975,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 6680.6015625,
+            "min": 6339.89794921875,
+            "max": 8294.6728515625,
+            "count": 20
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 399984.0,
+            "min": 209952.0,
+            "max": 399984.0,
+            "count": 20
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 399984.0,
+            "min": 209952.0,
+            "max": 399984.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.379910469055176,
+            "min": 12.89579963684082,
+            "max": 13.408547401428223,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2609.08251953125,
+            "min": 2372.8271484375,
+            "max": 2735.34375,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.0686802695690858,
+            "min": 0.06430996767263494,
+            "max": 0.0772170364093743,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.2747210782763432,
+            "min": 0.2572398706905398,
+            "max": 0.3721021125777898,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.17806019392960212,
+            "min": 0.1707822937591403,
+            "max": 0.2220527931171305,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7122407757184085,
+            "min": 0.6831291750365612,
+            "max": 1.1102639655856525,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 3.561098812999997e-06,
+            "min": 3.561098812999997e-06,
+            "max": 0.000145461051513,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 1.4244395251999988e-05,
+            "min": 1.4244395251999988e-05,
+            "max": 0.0006571802809399999,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.101187,
+            "min": 0.101187,
+            "max": 0.148487,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.404748,
+            "min": 0.404748,
+            "max": 0.71906,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 6.923129999999995e-05,
+            "min": 6.923129999999995e-05,
+            "max": 0.0024295013000000007,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0002769251999999998,
+            "min": 0.0002769251999999998,
+            "max": 0.010981094,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.34090909090909,
+            "min": 25.327272727272728,
+            "max": 26.522727272727273,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1159.0,
+            "min": 1120.0,
+            "max": 1446.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.34090909090909,
+            "min": 25.327272727272728,
+            "max": 26.522727272727273,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1159.0,
+            "min": 1120.0,
+            "max": 1446.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1676486508",
+        "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
+        "command_line_arguments": "/home/jonatan/PycharmProjects/HuggingfaceDeepRLCourse/Unit5/venv/bin/mlagents-learn ./content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
+        "mlagents_version": "0.29.0.dev0",
+        "mlagents_envs_version": "0.29.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.8.1+cu102",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1676486828"
+    },
+    "total": 319.7264541609911,
+    "count": 1,
+    "self": 0.3750912419054657,
+    "children": {
+        "run_training.setup": {
+            "total": 0.01992227102164179,
+            "count": 1,
+            "self": 0.01992227102164179
+        },
+        "TrainerController.start_learning": {
+            "total": 319.331440648064,
+            "count": 1,
+            "self": 0.44656072894576937,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.602945677936077,
+                    "count": 1,
+                    "self": 2.602945677936077
+                },
+                "TrainerController.advance": {
+                    "total": 316.15822794416454,
+                    "count": 18140,
+                    "self": 0.20747006044257432,
+                    "children": {
+                        "env_step": {
+                            "total": 315.95075788372196,
+                            "count": 18140,
+                            "self": 215.02938846347388,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 100.67914684314746,
+                                    "count": 18140,
+                                    "self": 1.143365952768363,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 99.5357808903791,
+                                            "count": 18140,
+                                            "self": 24.05113153764978,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 75.48464935272932,
+                                                    "count": 18140,
+                                                    "self": 75.48464935272932
+                                                }
+                                            }
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.24222257710061967,
+                                    "count": 18140,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 318.66177946177777,
+                                            "count": 18140,
+                                            "is_parallel": true,
+                                            "self": 163.58133103558794,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0014973619254305959,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00041328067891299725,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0010840812465175986,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0010840812465175986
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.022471531061455607,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00029101502150297165,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00020799902267754078,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00020799902267754078
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.021059047081507742,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.021059047081507742
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0009134699357673526,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002164661418646574,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0006970037939026952,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0006970037939026952
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 155.08044842618983,
+                                                    "count": 18139,
+                                                    "is_parallel": true,
+                                                    "self": 7.599670621799305,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 4.053588181035593,
+                                                            "count": 18139,
+                                                            "is_parallel": true,
+                                                            "self": 4.053588181035593
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 123.36690755712334,
+                                                            "count": 18139,
+                                                            "is_parallel": true,
+                                                            "self": 123.36690755712334
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 20.060282066231593,
+                                                            "count": 18139,
+                                                            "is_parallel": true,
+                                                            "self": 4.2335486222291365,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 15.826733444002457,
+                                                                    "count": 181390,
+                                                                    "is_parallel": true,
+                                                                    "self": 15.826733444002457
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.423898205161095e-05,
+                    "count": 1,
+                    "self": 7.423898205161095e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 314.5764184364816,
+                                    "count": 361499,
+                                    "is_parallel": true,
+                                    "self": 4.800364643684588,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 175.4521761490032,
+                                            "count": 361499,
+                                            "is_parallel": true,
+                                            "self": 174.722319738823,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.7298564101802185,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.7298564101802185
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 134.32387764379382,
+                                            "count": 90,
+                                            "is_parallel": true,
+                                            "self": 39.981511781108566,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 94.34236586268526,
+                                                    "count": 4587,
+                                                    "is_parallel": true,
+                                                    "self": 94.34236586268526
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1236320580355823,
+                    "count": 1,
+                    "self": 0.000865268986672163,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.12276678904891014,
+                            "count": 1,
+                            "self": 0.12276678904891014
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 99976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99976.onnx",
+                "reward": 21.545454545454547,
+                "creation_time": 1676486301.5258534,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99976.pt"
+                ]
+            },
+            {
+                "steps": 149976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149976.onnx",
+                "reward": 24.636363636363637,
+                "creation_time": 1676486377.8093677,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149976.pt"
+                ]
+            },
+            {
+                "steps": 199936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199936.onnx",
+                "reward": 25.727272727272727,
+                "creation_time": 1676486459.4695227,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199936.pt"
+                ]
+            },
+            {
+                "steps": 200640,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200640.onnx",
+                "reward": 25.727272727272727,
+                "creation_time": 1676486459.6635382,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200640.pt"
+                ]
+            },
+            {
+                "steps": 200640,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200640.onnx",
+                "reward": null,
+                "creation_time": 1676486482.3948216,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200640.pt"
+                ]
+            },
+            {
+                "steps": 249936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249936.onnx",
+                "reward": 25.272727272727273,
+                "creation_time": 1676486588.3003159,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249936.pt"
+                ]
+            },
+            {
+                "steps": 299960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299960.onnx",
+                "reward": 25.90909090909091,
+                "creation_time": 1676486668.3812163,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299960.pt"
+                ]
+            },
+            {
+                "steps": 349960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349960.onnx",
+                "reward": 26.454545454545453,
+                "creation_time": 1676486748.1607993,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349960.pt"
+                ]
+            },
+            {
+                "steps": 399984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399984.onnx",
+                "reward": 26.727272727272727,
+                "creation_time": 1676486828.1636865,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399984.pt"
+                ]
+            },
+            {
+                "steps": 400048,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400048.onnx",
+                "reward": 26.727272727272727,
+                "creation_time": 1676486828.309916,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-400048.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 400048,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 26.727272727272727,
+            "creation_time": 1676486828.309916,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-400048.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.29.0.dev0",
+        "torch_version": "1.8.1+cu102"
+    }
+}