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: tvnguyen/ppo-SnowballTargetTESTCOLAB
+  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 sha256:68aca155e1e0c964028e52a4b5698ae13fbc47c2a7f8bef7157e18dd0c26aae5
+size 646532

SnowballTarget/SnowballTarget-149960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1047e3a8e78f70677aa63cd5f1cbc92ec0d0f9915630ddca251de201d2d722e9
+size 646532

SnowballTarget/SnowballTarget-149960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:448cb1a815fc9d7a80b3b06af052cf465a5b6be903e84452bd91ed9a6e720784
+size 3843968

SnowballTarget/SnowballTarget-199960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68aca155e1e0c964028e52a4b5698ae13fbc47c2a7f8bef7157e18dd0c26aae5
+size 646532

SnowballTarget/SnowballTarget-199960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e497d61d9bd8e41f5796c721248ec7bb350d7c7fe5113d3815b2cd9fed838bd
+size 3843968

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68aca155e1e0c964028e52a4b5698ae13fbc47c2a7f8bef7157e18dd0c26aae5
+size 646532

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb447601c30ef3d29036f7da47ce5e41996e61ae4b9b14d40994640dcc76ff7
+size 3843968

SnowballTarget/SnowballTarget-49976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94ead253251bbdf73fd6a7c6fd4b8e2e95ea63238cec9314ce0b14ed0c38f4c1
+size 646532

SnowballTarget/SnowballTarget-49976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd6b009da5f9feb32115bfd3ba26619069eca8439de58a2397abbb5d12d7823
+size 3843968

SnowballTarget/SnowballTarget-8712.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3567e66c03107d209dda8f1484a0a7ff5c91b70445ca27faf8c402093b8c317
+size 646532

SnowballTarget/SnowballTarget-8712.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:687951e2d8f2ca25e0b9f35c128783a32d08530e1ced97e8d0ab3e40ca6b81d8
+size 3843968

SnowballTarget/SnowballTarget-99936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:354a9b33879ea349f1c11bc6350e9623297d7af6a5351e0047a35ca4b78fd0ab
+size 646532

SnowballTarget/SnowballTarget-99936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f3068b83e2cd5799fdc6aa2e5e588150cf5e900b32696d89c8cb82201fe9548
+size 3843968

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb447601c30ef3d29036f7da47ce5e41996e61ae4b9b14d40994640dcc76ff7
+size 3843968

SnowballTarget/events.out.tfevents.1681562221.076e9ce8859a.1548.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76155613c102e6859d0f10c0d0d7f4d6e35d7660d556084006fca8aa6fcdb613
+size 1114

SnowballTarget/events.out.tfevents.1681562252.076e9ce8859a.1749.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b31584378214b795a1ceb9b6f07fa6803c942ceed5c9c6c4a8cc1f258a2702
+size 18221

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  0.081 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: 0.673433 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]: 5133 frames, [16.0 KB-32.0 KB]: 87 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 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]: 5221 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.5 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5221 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.8 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]: 4500 frames, [64.0 KB-128.0 KB]: 721 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.8 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5221 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]: 5221 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]: 5220 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]: 5221 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]: 5221 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": 0.8531585931777954,
+            "min": 0.8531585931777954,
+            "max": 2.849118232727051,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 8155.3427734375,
+            "min": 4324.96142578125,
+            "max": 28748.00390625,
+            "count": 20
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199960.0,
+            "min": 9992.0,
+            "max": 199960.0,
+            "count": 20
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199960.0,
+            "min": 9992.0,
+            "max": 199960.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.663939476013184,
+            "min": 0.8249726295471191,
+            "max": 12.663939476013184,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2469.46826171875,
+            "min": 16.499452590942383,
+            "max": 2574.77685546875,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 19
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 19
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07553822325252102,
+            "min": 0.06370287543372707,
+            "max": 0.07553822325252102,
+            "count": 19
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.3021528930100841,
+            "min": 0.2555204649901248,
+            "max": 0.3708540599881078,
+            "count": 19
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.19784748159787233,
+            "min": 0.17910562882236405,
+            "max": 0.2845899269861334,
+            "count": 19
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7913899263914893,
+            "min": 0.7913899263914893,
+            "max": 1.2944463085310132,
+            "count": 19
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.214097262000005e-06,
+            "min": 8.214097262000005e-06,
+            "max": 0.000277164007612,
+            "count": 19
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.285638904800002e-05,
+            "min": 3.285638904800002e-05,
+            "max": 0.0013858200380599999,
+            "count": 19
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10273800000000001,
+            "min": 0.10273800000000001,
+            "max": 0.192388,
+            "count": 19
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.41095200000000004,
+            "min": 0.41095200000000004,
+            "max": 0.96194,
+            "count": 19
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0001466262000000001,
+            "min": 0.0001466262000000001,
+            "max": 0.0046201612,
+            "count": 19
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005865048000000004,
+            "min": 0.0005865048000000004,
+            "max": 0.023100806,
+            "count": 19
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 24.84090909090909,
+            "min": 5.781818181818182,
+            "max": 24.977272727272727,
+            "count": 19
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1093.0,
+            "min": 311.0,
+            "max": 1373.0,
+            "count": 19
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 24.84090909090909,
+            "min": 5.781818181818182,
+            "max": 24.977272727272727,
+            "count": 19
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1093.0,
+            "min": 311.0,
+            "max": 1373.0,
+            "count": 19
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1681562252",
+        "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": "1681562738"
+    },
+    "total": 485.960594868,
+    "count": 1,
+    "self": 0.4744572840000387,
+    "children": {
+        "run_training.setup": {
+            "total": 0.1134056799999712,
+            "count": 1,
+            "self": 0.1134056799999712
+        },
+        "TrainerController.start_learning": {
+            "total": 485.372731904,
+            "count": 1,
+            "self": 0.5937183789935148,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.991478709999967,
+                    "count": 1,
+                    "self": 3.991478709999967
+                },
+                "TrainerController.advance": {
+                    "total": 480.6398949070065,
+                    "count": 17402,
+                    "self": 0.3091692620120057,
+                    "children": {
+                        "env_step": {
+                            "total": 480.3307256449945,
+                            "count": 17402,
+                            "self": 351.2745105950102,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 128.7550710459829,
+                                    "count": 17402,
+                                    "self": 1.9882499359911776,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 126.76682110999172,
+                                            "count": 17402,
+                                            "self": 126.76682110999172
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.30114400400140084,
+                                    "count": 17402,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 483.77265355400385,
+                                            "count": 17402,
+                                            "is_parallel": true,
+                                            "self": 221.3265434610147,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0020873010000173053,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006741129999454643,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.001413188000071841,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.001413188000071841
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.11177193100002114,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006438959999854887,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0008097030000158156,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0008097030000158156
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.10845002799999293,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.10845002799999293
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0018683040000269102,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003876440001135961,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001480659999913314,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001480659999913314
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 262.44611009298916,
+                                                    "count": 17401,
+                                                    "is_parallel": true,
+                                                    "self": 10.348950656991178,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.870127904007518,
+                                                            "count": 17401,
+                                                            "is_parallel": true,
+                                                            "self": 5.870127904007518
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 210.43117276799734,
+                                                            "count": 17401,
+                                                            "is_parallel": true,
+                                                            "self": 210.43117276799734
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 35.795858763993124,
+                                                            "count": 17401,
+                                                            "is_parallel": true,
+                                                            "self": 7.208681513999693,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 28.58717724999343,
+                                                                    "count": 174010,
+                                                                    "is_parallel": true,
+                                                                    "self": 28.58717724999343
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00013196899999456946,
+                    "count": 1,
+                    "self": 0.00013196899999456946,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 476.6854514550191,
+                                    "count": 431054,
+                                    "is_parallel": true,
+                                    "self": 11.155984776013838,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 266.255469939005,
+                                            "count": 431054,
+                                            "is_parallel": true,
+                                            "self": 265.43889210700496,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.8165778320000641,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.8165778320000641
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 199.27399674000026,
+                                            "count": 86,
+                                            "is_parallel": true,
+                                            "self": 74.70472814300422,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 124.56926859699604,
+                                                    "count": 4383,
+                                                    "is_parallel": true,
+                                                    "self": 124.56926859699604
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.14750793899997916,
+                    "count": 1,
+                    "self": 0.00119498999993084,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.14631294900004832,
+                            "count": 1,
+                            "self": 0.14631294900004832
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,74 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 8712,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-8712.onnx",
+                "reward": null,
+                "creation_time": 1681562247.9287415,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-8712.pt"
+                ]
+            },
+            {
+                "steps": 49976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49976.onnx",
+                "reward": 14.0,
+                "creation_time": 1681562361.1136308,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49976.pt"
+                ]
+            },
+            {
+                "steps": 99936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.onnx",
+                "reward": 22.272727272727273,
+                "creation_time": 1681562487.4296386,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.pt"
+                ]
+            },
+            {
+                "steps": 149960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.onnx",
+                "reward": 24.363636363636363,
+                "creation_time": 1681562613.0942852,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.pt"
+                ]
+            },
+            {
+                "steps": 199960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.onnx",
+                "reward": 24.545454545454547,
+                "creation_time": 1681562737.419032,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 25.272727272727273,
+                "creation_time": 1681562737.609065,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 200112,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 25.272727272727273,
+            "creation_time": 1681562737.609065,
+            "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"
+    }
+}