Snow Ball Target

README.md

@@ -0,0 +1,29 @@
+---
+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://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: Find your model_id: Isaac009/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:c0cc3a9f79cbdace8c5566813052e472b01f77380ceab3b6fba52fa2e60e7877
+size 646532

SnowballTarget/SnowballTarget-13112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bacabf2654c5cfecc4cd46879a4e9c6330d947cf7463c8cb412e81b14e3b3295
+size 646532

SnowballTarget/SnowballTarget-13112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2058314676e15009cf46fc757d1014adaf1095fd1f2d55959775de909464d6a
+size 3843968

SnowballTarget/SnowballTarget-149960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04dce63ba6c6859671ff8e1dbcd08e2e2d74256f3b1065259753f50e83c2f63f
+size 646532

SnowballTarget/SnowballTarget-149960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2421c628ded7521fdb3f1e226c5b151ea31fb2a550bc8118fe3f79aaef33c8e4
+size 3843968

SnowballTarget/SnowballTarget-199960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0cc3a9f79cbdace8c5566813052e472b01f77380ceab3b6fba52fa2e60e7877
+size 646532

SnowballTarget/SnowballTarget-199960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3434744b992184e1d2a0734fca088243789a57134faaba7abc05ef152cffb35c
+size 3843968

SnowballTarget/SnowballTarget-200024.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0cc3a9f79cbdace8c5566813052e472b01f77380ceab3b6fba52fa2e60e7877
+size 646532

SnowballTarget/SnowballTarget-200024.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2413ad13817e265a2ccfeb85714b97c6141e43d46022d54c37dd2a7f174fa3
+size 3843968

SnowballTarget/SnowballTarget-49976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ad3992ee5ae6c896cc7941c1a051c136dcf79e5383d7eb01bd386fa466ce22
+size 646532

SnowballTarget/SnowballTarget-49976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b57f3a3b538bff470ba8644e3775bf1a41a1f1bf1a0b299ab83492cf8dfafaec
+size 3843968

SnowballTarget/SnowballTarget-99936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cedebecf9ec91091b76c9b7ce91f2de43320239934c2eac9ff3760ca375b85fe
+size 646532

SnowballTarget/SnowballTarget-99936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f59c4151b849976b96af8d5f2d3c487518d989a5a5978b40a3c843ce043ab81
+size 3843968

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2413ad13817e265a2ccfeb85714b97c6141e43d46022d54c37dd2a7f174fa3
+size 3843968

SnowballTarget/events.out.tfevents.1682472357.isaac-OMEN-lab-202.161811.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c5f71a372366a868a20089cc350e833a2e744a5233a7f3952bdf449900a71cb
+size 6894

SnowballTarget/events.out.tfevents.1682472565.isaac-OMEN-lab-202.162720.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e5a167e3360116e2b99ccfb44ff3fa41578bcbdcbc266fde70f426f4d76db2
+size 17794

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, "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 +1,77 @@
+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
+  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 +1,309 @@
+Mono path[0] = '/home/isaac/Documents/research/Reinforcement-Learning/HDRL/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/home/isaac/Documents/research/Reinforcement-Learning/HDRL/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/isaac/Documents/research/Reinforcement-Learning/HDRL/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  0.053 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: 0.414339 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]: 5016 frames, [16.0 KB-32.0 KB]: 85 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 298 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 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 39
+    [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]: 5102 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.7 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5102 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]: 3538 frames, [64.0 KB-128.0 KB]: 1564 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 67.3 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5102 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]: 5102 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]: 5101 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]: 5102 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]: 5102 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": 1.0305557250976562,
+            "min": 1.0305557250976562,
+            "max": 2.6767399311065674,
+            "count": 19
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 9873.75390625,
+            "min": 9873.75390625,
+            "max": 25146.279296875,
+            "count": 19
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199960.0,
+            "min": 19968.0,
+            "max": 199960.0,
+            "count": 19
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199960.0,
+            "min": 19968.0,
+            "max": 199960.0,
+            "count": 19
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.28280258178711,
+            "min": 1.582127332687378,
+            "max": 12.28280258178711,
+            "count": 19
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2395.146484375,
+            "min": 215.1693115234375,
+            "max": 2456.0576171875,
+            "count": 19
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 19
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 6567.0,
+            "max": 10945.0,
+            "count": 19
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07153849720534887,
+            "min": 0.0650355018891894,
+            "max": 0.07437872416180029,
+            "count": 19
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.2861539888213955,
+            "min": 0.20904549251695154,
+            "max": 0.37189362080900146,
+            "count": 19
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.21812057013020794,
+            "min": 0.18783810018908745,
+            "max": 0.26509962274747734,
+            "count": 19
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.8724822805208318,
+            "min": 0.5861201091833851,
+            "max": 1.299587918847215,
+            "count": 19
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.214097262000005e-06,
+            "min": 8.214097262000005e-06,
+            "max": 0.000273864008712,
+            "count": 19
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.285638904800002e-05,
+            "min": 3.285638904800002e-05,
+            "max": 0.00123732008756,
+            "count": 19
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10273800000000001,
+            "min": 0.10273800000000001,
+            "max": 0.19128799999999999,
+            "count": 19
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.41095200000000004,
+            "min": 0.41095200000000004,
+            "max": 0.9124400000000001,
+            "count": 19
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0001466262000000001,
+            "min": 0.0001466262000000001,
+            "max": 0.004565271199999999,
+            "count": 19
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005865048000000004,
+            "min": 0.0005865048000000004,
+            "max": 0.020630756,
+            "count": 19
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 24.568181818181817,
+            "min": 6.393939393939394,
+            "max": 24.78181818181818,
+            "count": 19
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1081.0,
+            "min": 211.0,
+            "max": 1363.0,
+            "count": 19
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 24.568181818181817,
+            "min": 6.393939393939394,
+            "max": 24.78181818181818,
+            "count": 19
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1081.0,
+            "min": 211.0,
+            "max": 1363.0,
+            "count": 19
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 19
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 19
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1682472564",
+        "python_version": "3.9.16 (main, Apr 26 2023, 09:57:11) \n[GCC 9.4.0]",
+        "command_line_arguments": "/home/isaac/python_envs/py3916_env/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1682472779"
+    },
+    "total": 215.00497559900396,
+    "count": 1,
+    "self": 0.2196071700018365,
+    "children": {
+        "run_training.setup": {
+            "total": 0.03277779099880718,
+            "count": 1,
+            "self": 0.03277779099880718
+        },
+        "TrainerController.start_learning": {
+            "total": 214.7525906380033,
+            "count": 1,
+            "self": 0.347331655677408,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.209427320995019,
+                    "count": 1,
+                    "self": 2.209427320995019
+                },
+                "TrainerController.advance": {
+                    "total": 212.10186213132693,
+                    "count": 17004,
+                    "self": 0.17319778741511982,
+                    "children": {
+                        "env_step": {
+                            "total": 211.9286643439118,
+                            "count": 17004,
+                            "self": 149.39888549630996,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 62.354847080874606,
+                                    "count": 17004,
+                                    "self": 0.8606052966497373,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 61.49424178422487,
+                                            "count": 17004,
+                                            "self": 61.49424178422487
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.17493176672724076,
+                                    "count": 17004,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 214.34768923617958,
+                                            "count": 17004,
+                                            "is_parallel": true,
+                                            "self": 123.48211874165281,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0010480040073161945,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0002753550070337951,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0007726490002823994,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0007726490002823994
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.015450181002961472,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00021916399418842047,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00017331501294393092,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00017331501294393092
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.014249605999793857,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.014249605999793857
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0008080959960352629,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00019075500313192606,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0006173409929033369,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0006173409929033369
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 90.86557049452676,
+                                                    "count": 17003,
+                                                    "is_parallel": true,
+                                                    "self": 3.9357192841998767,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 2.594641712945304,
+                                                            "count": 17003,
+                                                            "is_parallel": true,
+                                                            "self": 2.594641712945304
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 70.02356578952458,
+                                                            "count": 17003,
+                                                            "is_parallel": true,
+                                                            "self": 70.02356578952458
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 14.311643707857002,
+                                                            "count": 17003,
+                                                            "is_parallel": true,
+                                                            "self": 3.254882780223852,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 11.05676092763315,
+                                                                    "count": 170030,
+                                                                    "is_parallel": true,
+                                                                    "self": 11.05676092763315
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 6.265900447033346e-05,
+                    "count": 1,
+                    "self": 6.265900447033346e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 211.82577092766587,
+                                    "count": 127653,
+                                    "is_parallel": true,
+                                    "self": 1.4739056372345658,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 111.39946549842716,
+                                            "count": 127653,
+                                            "is_parallel": true,
+                                            "self": 110.85940189742541,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.5400636010017479,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.5400636010017479
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 98.95239979200414,
+                                            "count": 84,
+                                            "is_parallel": true,
+                                            "self": 32.9943716678099,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 65.95802812419424,
+                                                    "count": 4281,
+                                                    "is_parallel": true,
+                                                    "self": 65.95802812419424
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.09390687099948991,
+                    "count": 1,
+                    "self": 0.0005450370081234723,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.09336183399136644,
+                            "count": 1,
+                            "self": 0.09336183399136644
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,74 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 13112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-13112.onnx",
+                "reward": null,
+                "creation_time": 1682472374.2621648,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-13112.pt"
+                ]
+            },
+            {
+                "steps": 49976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49976.onnx",
+                "reward": 12.545454545454545,
+                "creation_time": 1682472609.6558309,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49976.pt"
+                ]
+            },
+            {
+                "steps": 99936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.onnx",
+                "reward": 20.0,
+                "creation_time": 1682472666.7543929,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.pt"
+                ]
+            },
+            {
+                "steps": 149960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.onnx",
+                "reward": 21.727272727272727,
+                "creation_time": 1682472724.0666249,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.pt"
+                ]
+            },
+            {
+                "steps": 199960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.onnx",
+                "reward": 25.363636363636363,
+                "creation_time": 1682472779.6514628,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.pt"
+                ]
+            },
+            {
+                "steps": 200024,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200024.onnx",
+                "reward": 25.363636363636363,
+                "creation_time": 1682472779.757323,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200024.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 200024,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 25.363636363636363,
+            "creation_time": 1682472779.757323,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200024.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}