First Push

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: MarcusAGray/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 sha256:7311306ada5cc36580c15a9624d6af9cc671c914a327930b84567a47b7947abe
+size 646532

SnowballTarget/SnowballTarget-149960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1419856b24106e288604fe36d163261047c495355465211532282d49a765f616
+size 646532

SnowballTarget/SnowballTarget-149960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a855396828988736e8673dfaaa49a738a8b31298076103694b207bc1ae512b
+size 3843968

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7311306ada5cc36580c15a9624d6af9cc671c914a327930b84567a47b7947abe
+size 646532

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7e8f959cb8e1366422f276cdbcf31c8f6ed5053855c740e5f4a148337bcdb1
+size 3843968

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7311306ada5cc36580c15a9624d6af9cc671c914a327930b84567a47b7947abe
+size 646532

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3426424826860487813e44323f55632a0e309c06fdde7c32378f5df917908f
+size 3843968

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a79ed9b0c4de26d497927df0925107ae75b1a2f5823fa2a6acfe0fb036834c
+size 646532

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3239b1009fcc6f1c2a0f0e29e4f4bedbcaf5acf1af86260194a4eae2e9115f
+size 3843968

SnowballTarget/SnowballTarget-5104.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9608caa2a05972cee6d5e5feb6fe7107f0ebdcd8ecb580c004652ce84ee3801f
+size 646532

SnowballTarget/SnowballTarget-5104.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9debdac3b4c1cf165a7d477e32f8a4344c24cc177a64dc3cbbaabd0815e60d60
+size 3843968

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d166db3dda6a1a21f0e2bf0579fd70d15e7783ba998cdc2dd73153557b690a
+size 646532

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a8b500ca89c1ab023a8bee86b24d93de75f9642939cb5d1c6effe4e9db79e5
+size 3843968

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3426424826860487813e44323f55632a0e309c06fdde7c32378f5df917908f
+size 3843968

SnowballTarget/events.out.tfevents.1679761748.53a6b6ef2d28.6199.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49790d0e8262ca610d0781e6f320344757e81789d839835e5cee4b10c477fe9a
+size 1066

SnowballTarget/events.out.tfevents.1679761887.53a6b6ef2d28.6869.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5eb851e3345466322447539a2ec9da6dc38ba63d29b2c849ac3bc2848dcbc60
+size 28459

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 +1,259 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.080 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: 0.670234 ms
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+Setting up 1 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5233 frames, [16.0 KB-32.0 KB]: 88 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 198 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 228.9 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 40
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5322 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]: 5322 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]: 4506 frames, [64.0 KB-128.0 KB]: 816 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]: 5322 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]: 5322 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]: 5321 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]: 5322 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]: 5322 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.7 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,377 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.7485129237174988,
+            "min": 0.7459189295768738,
+            "max": 2.8562512397766113,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7113.86669921875,
+            "min": 7113.86669921875,
+            "max": 27580.619140625,
+            "count": 20
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.931973457336426,
+            "min": 0.36002692580223083,
+            "max": 12.931973457336426,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2521.73486328125,
+            "min": 34.20255661010742,
+            "max": 2629.231201171875,
+            "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": 4378.0,
+            "max": 10945.0,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07143005984064932,
+            "min": 0.0634824107939779,
+            "max": 0.07450440518886728,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.2857202393625973,
+            "min": 0.1480563891693201,
+            "max": 0.37252202594433637,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.18356743458585412,
+            "min": 0.11577610888372303,
+            "max": 0.29279502110154015,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7342697383434165,
+            "min": 0.23155221776744606,
+            "max": 1.4639751055077008,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 7.0260976579999984e-06,
+            "min": 7.0260976579999984e-06,
+            "max": 0.000287526004158,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 2.8104390631999994e-05,
+            "min": 2.8104390631999994e-05,
+            "max": 0.0013138800620399998,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10234199999999999,
+            "min": 0.10234199999999999,
+            "max": 0.19584200000000002,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.40936799999999995,
+            "min": 0.39168400000000003,
+            "max": 0.93796,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0001268658,
+            "min": 0.0001268658,
+            "max": 0.004792515800000001,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005074632,
+            "min": 0.0005074632,
+            "max": 0.021904204,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.704545454545453,
+            "min": 3.1818181818181817,
+            "max": 25.704545454545453,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1131.0,
+            "min": 70.0,
+            "max": 1378.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.704545454545453,
+            "min": 3.1818181818181817,
+            "max": 25.704545454545453,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1131.0,
+            "min": 70.0,
+            "max": 1378.0,
+            "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": "1679761884",
+        "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
+        "command_line_arguments": "/usr/local/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": "1679762347"
+    },
+    "total": 463.17037403099994,
+    "count": 1,
+    "self": 0.43105761699985123,
+    "children": {
+        "run_training.setup": {
+            "total": 0.10540425099998174,
+            "count": 1,
+            "self": 0.10540425099998174
+        },
+        "TrainerController.start_learning": {
+            "total": 462.6339121630001,
+            "count": 1,
+            "self": 0.5867048149959828,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.944527345000097,
+                    "count": 1,
+                    "self": 5.944527345000097
+                },
+                "TrainerController.advance": {
+                    "total": 455.96854212000403,
+                    "count": 17737,
+                    "self": 0.3253818390219294,
+                    "children": {
+                        "env_step": {
+                            "total": 455.6431602809821,
+                            "count": 17737,
+                            "self": 328.5171771879816,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 126.83280138098235,
+                                    "count": 17737,
+                                    "self": 2.3277883179878245,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 124.50501306299452,
+                                            "count": 17737,
+                                            "self": 124.50501306299452
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.2931817120181677,
+                                    "count": 17737,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 461.0009280790043,
+                                            "count": 17737,
+                                            "is_parallel": true,
+                                            "self": 214.96186385500232,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0027792089999820746,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.000728120999838211,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0020510880001438636,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0020510880001438636
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.04824274600014178,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005894910000279197,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00038546900009350793,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00038546900009350793
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.04512782699998752,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.04512782699998752
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0021399590000328317,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005973410004571633,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0015426179995756684,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0015426179995756684
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 246.039064224002,
+                                                    "count": 17736,
+                                                    "is_parallel": true,
+                                                    "self": 9.403280328034043,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.098721370994781,
+                                                            "count": 17736,
+                                                            "is_parallel": true,
+                                                            "self": 5.098721370994781
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 200.8669338079908,
+                                                            "count": 17736,
+                                                            "is_parallel": true,
+                                                            "self": 200.8669338079908
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 30.67012871698239,
+                                                            "count": 17736,
+                                                            "is_parallel": true,
+                                                            "self": 6.321889531904844,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 24.348239185077546,
+                                                                    "count": 177360,
+                                                                    "is_parallel": true,
+                                                                    "self": 24.348239185077546
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 3.6843000088992994e-05,
+                    "count": 1,
+                    "self": 3.6843000088992994e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 452.60676231104935,
+                                    "count": 420773,
+                                    "is_parallel": true,
+                                    "self": 9.976955237974153,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 252.97012494807495,
+                                            "count": 420773,
+                                            "is_parallel": true,
+                                            "self": 252.15448749207508,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.8156374559998767,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.8156374559998767
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 189.65968212500024,
+                                            "count": 88,
+                                            "is_parallel": true,
+                                            "self": 68.43871314200942,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 121.22096898299083,
+                                                    "count": 4485,
+                                                    "is_parallel": true,
+                                                    "self": 121.22096898299083
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.13410103999990497,
+                    "count": 1,
+                    "self": 0.001158266999937041,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.13294277299996793,
+                            "count": 1,
+                            "self": 0.13294277299996793
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,74 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 5104,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-5104.onnx",
+                "reward": 2.727272727272727,
+                "creation_time": 1679761764.8545558,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-5104.pt"
+                ]
+            },
+            {
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 13.090909090909092,
+                "creation_time": 1679761995.1812577,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 21.181818181818183,
+                "creation_time": 1679762112.969713,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.onnx",
+                "reward": 25.181818181818183,
+                "creation_time": 1679762229.356321,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1679762346.920568,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1679762347.0839775,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 200112,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 25.545454545454547,
+            "creation_time": 1679762347.0839775,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}