First Push”

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-SoccerTwos
+      library_name: ml-agents
+---
+    
+  # **poca** Agent playing **SoccerTwos**
+  This is a trained model of a **poca** agent playing **SoccerTwos** 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-SoccerTwos
+  2. Step 1: Write your model_id: NoNameFound/poca-SoccerTwos-pretrained150
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SoccerTwos.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ecf114463c2964e73c3dc5f3b80dff395ecbd70d9da93a719e2a0611f925f8
+size 626987

SoccerTwos/SoccerTwos-1000214.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ecf114463c2964e73c3dc5f3b80dff395ecbd70d9da93a719e2a0611f925f8
+size 626987

SoccerTwos/SoccerTwos-1000214.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827a845b5a91ab1cf6031b2f2d114ec8368f42d10f00ba06b74833a65e8e9b63
+size 8730831

SoccerTwos/SoccerTwos-499958.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63a4ac18114ffeab3b1120934b75727b30d11867c3d3001e4a6d3bdbe3fa717
+size 626987

SoccerTwos/SoccerTwos-499958.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a222314331435aa14cb791f9a12bd3c3b4494f3a9ff81a46905288fed342c62
+size 8730709

SoccerTwos/SoccerTwos-999882.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ecf114463c2964e73c3dc5f3b80dff395ecbd70d9da93a719e2a0611f925f8
+size 626987

SoccerTwos/SoccerTwos-999882.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea404de795bef24567f7bb2bee98813faebfc05e85eee63fafb8a8b569d4b977
+size 8730709

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce04632f6bf0e415bb2ceaba5dc146d1d3bb74f49d1bf3f61b3f812a9d8da94
+size 8729855

SoccerTwos/events.out.tfevents.1680444413.Kaushik.13036.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a977b2b92baacd75e19ee22875c594ca841c8e970485416ba24147cb4100b63
+size 1027507

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "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": ".\\checkpoint.pt", "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 100000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": ".\\training-envs-executables\\SoccerTwos\\SoccerTwos.exe", "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": "poca-SoccerTwos-pretrained150", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,82 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    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: .\checkpoint.pt
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 1000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 100000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: .\training-envs-executables\SoccerTwos\SoccerTwos.exe
+  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: poca-SoccerTwos-pretrained150
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,322 @@
+Mono path[0] = 'C:/Users/Kaush/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/Users/Kaush/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/Users/Kaush/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_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  0.152 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
+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 (Specular setup)' - 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 (Specular setup) shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - 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?
+WARNING: Shader Unsupported: 'Autodesk Interactive' - 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 Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
+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: 0.710500 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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]: 18822 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 312 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 67.1 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 13]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 8
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 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 54 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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 4
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 18823 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.1 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18823 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.3 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 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18822 frames, [64.0 KB-128.0 KB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 65.6 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [128.0 KB-256.0 KB]: 18823 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.6 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 2
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 18823 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]: 18822 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.2 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 0.9 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 18823 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]: 18822 frames, [2.0 KB-4.0 KB]: 1 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.3785388469696045,
+            "min": 1.2652868032455444,
+            "max": 1.4391518831253052,
+            "count": 100
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 27173.7578125,
+            "min": 22449.69921875,
+            "max": 30135.53515625,
+            "count": 100
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 63.58227848101266,
+            "min": 46.15238095238095,
+            "max": 82.76666666666667,
+            "count": 100
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 20092.0,
+            "min": 18576.0,
+            "max": 20488.0,
+            "count": 100
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1178.7208169320484,
+            "min": 1178.555471367562,
+            "max": 1210.2889338157947,
+            "count": 100
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 186237.88907526364,
+            "min": 142084.47714409293,
+            "max": 252912.33561713746,
+            "count": 100
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 999882.0,
+            "min": 9992.0,
+            "max": 999882.0,
+            "count": 100
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 999882.0,
+            "min": 9992.0,
+            "max": 999882.0,
+            "count": 100
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.03008103556931019,
+            "min": -0.0897950753569603,
+            "max": 0.029128646478056908,
+            "count": 100
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -4.72272253036499,
+            "min": -14.01373291015625,
+            "max": 5.2140278816223145,
+            "count": 100
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.02984745241701603,
+            "min": -0.0896281972527504,
+            "max": 0.028643064200878143,
+            "count": 100
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -4.686049938201904,
+            "min": -13.959389686584473,
+            "max": 5.127108573913574,
+            "count": 100
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 100
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 100
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.044163056999255136,
+            "min": -0.27418914737627487,
+            "max": 0.19249385495425603,
+            "count": 100
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -6.933599948883057,
+            "min": -39.29500025510788,
+            "max": 34.45640003681183,
+            "count": 100
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.044163056999255136,
+            "min": -0.27418914737627487,
+            "max": 0.19249385495425603,
+            "count": 100
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -6.933599948883057,
+            "min": -39.29500025510788,
+            "max": 34.45640003681183,
+            "count": 100
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.0182365807677949,
+            "min": 0.010929412101298415,
+            "max": 0.022865173884201794,
+            "count": 48
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.0182365807677949,
+            "min": 0.010929412101298415,
+            "max": 0.022865173884201794,
+            "count": 48
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.11022970726092657,
+            "min": 0.09646974230806032,
+            "max": 0.11893880342443784,
+            "count": 48
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.11022970726092657,
+            "min": 0.09646974230806032,
+            "max": 0.11893880342443784,
+            "count": 48
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.11040919795632362,
+            "min": 0.09642634515961011,
+            "max": 0.1193186196188132,
+            "count": 48
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.11040919795632362,
+            "min": 0.09642634515961011,
+            "max": 0.1193186196188132,
+            "count": 48
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 3.5604988131999975e-06,
+            "min": 3.5604988131999975e-06,
+            "max": 0.00029382000206,
+            "count": 48
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 3.5604988131999975e-06,
+            "min": 3.5604988131999975e-06,
+            "max": 0.00029382000206,
+            "count": 48
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.10118679999999997,
+            "min": 0.10118679999999997,
+            "max": 0.19794,
+            "count": 48
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.10118679999999997,
+            "min": 0.10118679999999997,
+            "max": 0.19794,
+            "count": 48
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.00012856131999999985,
+            "min": 0.00012856131999999985,
+            "max": 0.009794206000000005,
+            "count": 48
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.00012856131999999985,
+            "min": 0.00012856131999999985,
+            "max": 0.009794206000000005,
+            "count": 48
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1680444407",
+        "python_version": "3.8.16 (default, Jan 17 2023, 22:25:28) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\Kaush\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn .\\config\\poca\\SoccerTwosPreTrained.yaml --env=.\\training-envs-executables\\SoccerTwos\\SoccerTwos.exe --run-id=poca-SoccerTwos-pretrained150 --no-graphics",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.13.1+cu117",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1680448456"
+    },
+    "total": 4048.408677,
+    "count": 1,
+    "self": 0.9526921999995466,
+    "children": {
+        "run_training.setup": {
+            "total": 0.1814833999999994,
+            "count": 1,
+            "self": 0.1814833999999994
+        },
+        "TrainerController.start_learning": {
+            "total": 4047.2745014,
+            "count": 1,
+            "self": 3.2528624999790736,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 9.605797899999864,
+                    "count": 5,
+                    "self": 9.605797899999864
+                },
+                "TrainerController.advance": {
+                    "total": 4034.1841748000215,
+                    "count": 69292,
+                    "self": 3.690406400007305,
+                    "children": {
+                        "env_step": {
+                            "total": 2870.1142315000125,
+                            "count": 69292,
+                            "self": 1631.9468360999701,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1236.165864500007,
+                                    "count": 69292,
+                                    "self": 25.098418099946684,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1211.0674464000604,
+                                            "count": 125486,
+                                            "self": 1211.0674464000604
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.001530900035384,
+                                    "count": 69292,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 4036.835178999987,
+                                            "count": 69292,
+                                            "is_parallel": true,
+                                            "self": 2757.2931432999617,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.022451600000070293,
+                                                    "count": 10,
+                                                    "is_parallel": true,
+                                                    "self": 0.004252700000368925,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.018198899999701368,
+                                                            "count": 40,
+                                                            "is_parallel": true,
+                                                            "self": 0.018198899999701368
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1279.5195841000252,
+                                                    "count": 69292,
+                                                    "is_parallel": true,
+                                                    "self": 66.1312259999836,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 51.90662950004355,
+                                                            "count": 69292,
+                                                            "is_parallel": true,
+                                                            "self": 51.90662950004355
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 957.0205951999809,
+                                                            "count": 69292,
+                                                            "is_parallel": true,
+                                                            "self": 957.0205951999809
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 204.4611334000172,
+                                                            "count": 138584,
+                                                            "is_parallel": true,
+                                                            "self": 45.09512389998633,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 159.36600950003086,
+                                                                    "count": 554336,
+                                                                    "is_parallel": true,
+                                                                    "self": 159.36600950003086
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 1160.379536900002,
+                            "count": 69292,
+                            "self": 19.789121699997622,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 599.135403300004,
+                                    "count": 69292,
+                                    "self": 598.296133800004,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.8392695000000003,
+                                            "count": 2,
+                                            "self": 0.8392695000000003
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 541.4550119000005,
+                                    "count": 48,
+                                    "self": 332.068107299994,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 209.38690460000652,
+                                            "count": 1440,
+                                            "self": 209.38690460000652
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.0999997357430402e-06,
+                    "count": 1,
+                    "self": 1.0999997357430402e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.2316651000001002,
+                    "count": 1,
+                    "self": 0.004850700000133656,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.22681439999996655,
+                            "count": 1,
+                            "self": 0.22681439999996655
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,48 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 499958,
+                "file_path": "results\\poca-SoccerTwos-pretrained150\\SoccerTwos\\SoccerTwos-499958.onnx",
+                "reward": 0.0,
+                "creation_time": 1680446315.3135157,
+                "auxillary_file_paths": [
+                    "results\\poca-SoccerTwos-pretrained150\\SoccerTwos\\SoccerTwos-499958.pt"
+                ]
+            },
+            {
+                "steps": 999882,
+                "file_path": "results\\poca-SoccerTwos-pretrained150\\SoccerTwos\\SoccerTwos-999882.onnx",
+                "reward": 0.0,
+                "creation_time": 1680448455.065661,
+                "auxillary_file_paths": [
+                    "results\\poca-SoccerTwos-pretrained150\\SoccerTwos\\SoccerTwos-999882.pt"
+                ]
+            },
+            {
+                "steps": 1000214,
+                "file_path": "results\\poca-SoccerTwos-pretrained150\\SoccerTwos\\SoccerTwos-1000214.onnx",
+                "reward": 0.0,
+                "creation_time": 1680448455.4425876,
+                "auxillary_file_paths": [
+                    "results\\poca-SoccerTwos-pretrained150\\SoccerTwos\\SoccerTwos-1000214.pt"
+                ]
+            }
+        ],
+        "elo": 1180.2151445882755,
+        "final_checkpoint": {
+            "steps": 1000214,
+            "file_path": "results\\poca-SoccerTwos-pretrained150\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1680448455.4425876,
+            "auxillary_file_paths": [
+                "results\\poca-SoccerTwos-pretrained150\\SoccerTwos\\SoccerTwos-1000214.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.13.1+cu117"
+    }
+}