First Push`

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SoccerTwos
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SoccerTwos
+---
+
+  # **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://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  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. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: EladAssia/poca-SoccerTwos
+  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 sha256:4f23a230c1b2ff2b5311e6afe7274cf74112e75c4f361fbeeb6f57909c0dfc12
+size 2820312

SoccerTwos/SoccerTwos-18499996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4650f0c5200e09b893b4e6133a74c48b167ef7f8b84e69d3246b1aa4909feb6
+size 2820312

SoccerTwos/SoccerTwos-18499996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880226b6b86ae24b9631657fcc6ea031be108e3255e9747eac7f93253d36eef6
+size 34738729

SoccerTwos/SoccerTwos-18999928.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf134538e26ac376f5c808ad7cc6febe5ff393230cc47a163a512670ac5856c9
+size 2820312

SoccerTwos/SoccerTwos-18999928.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef995014f3253b4f58c9a87440212594d08cadfea2786e1a627b8465a45e11c0
+size 34738729

SoccerTwos/SoccerTwos-19499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5f99b7c4ed8867d0d997085ee3bec3394c263c381585cdaa1361924a143c8c
+size 2820312

SoccerTwos/SoccerTwos-19499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6eb88b647e1facbbe53c1a62a5a997af151c2d53a247962382024485f9c319f
+size 34738729

SoccerTwos/SoccerTwos-19999946.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:302bbec67e0cb9e87c55214246284c27d7360961cb354a1070256a1b6cd455de
+size 2820312

SoccerTwos/SoccerTwos-19999946.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcaf939209e4709087b84d3210878e2fccbd735a58669cef3084880574cd0bb2
+size 34738729

SoccerTwos/SoccerTwos-20110520.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f23a230c1b2ff2b5311e6afe7274cf74112e75c4f361fbeeb6f57909c0dfc12
+size 2820312

SoccerTwos/SoccerTwos-20110520.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31626e3e05b0626504e5a06cd0ecf47e2b507446a17a22569ec77b6a67fdcfe2
+size 34738729

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ea307c05efc978b7837e4bd1ce9ba0aaeeab5a0f4c1f5c991e1cb35f757a33
+size 34737423

SoccerTwos/events.out.tfevents.1696247055.ELAD.20680.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5831181a35cc4fa742d48056c896e2e9ec072ea48255fe0d004fe7c5b61c4e1c
+size 2142590

SoccerTwos/events.out.tfevents.1696277877.ELAD.24152.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b12107207cdecb52887f6e5d257f7858faad4bada38fc30394f7c1a840d46536
+size 18419034

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": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "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": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 10000, "team_change": 50000, "swap_steps": 2000, "window": 20, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/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": "SoccerTwos", "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 +1,82 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 3
+      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: 5
+    even_checkpoints: false
+    max_steps: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 10000
+      team_change: 50000
+      swap_steps: 2000
+      window: 20
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/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: SoccerTwos
+  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 +1,282 @@
+Mono path[0] = 'C:/Users/assia/PycharmProjects/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/Users/assia/PycharmProjects/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/Users/assia/PycharmProjects/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  0.101 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: 8.588900 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Setting up 4 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]: 341604 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 360 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 68.0 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 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 0.8 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_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 4
+      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 7
+      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_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 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_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_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 3
+    [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]: 341605 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 341605 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.4 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]: 341604 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]: 341605 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]: 341605 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]: 341604 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]: 341605 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]: 341604 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": 1.6622945070266724,
+            "min": 1.4777714014053345,
+            "max": 2.3602654933929443,
+            "count": 1792
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 32660.76171875,
+            "min": 26372.533203125,
+            "max": 52087.3359375,
+            "count": 1792
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 69.5774647887324,
+            "min": 43.214285714285715,
+            "max": 135.5142857142857,
+            "count": 1792
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19760.0,
+            "min": 11968.0,
+            "max": 21432.0,
+            "count": 1792
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1429.6834391114112,
+            "min": 1267.8483300636103,
+            "max": 1442.8017261441944,
+            "count": 1792
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 203015.0483538204,
+            "min": 90404.93167926311,
+            "max": 304220.6827741176,
+            "count": 1792
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 20109806.0,
+            "min": 2199998.0,
+            "max": 20109806.0,
+            "count": 1792
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 20109806.0,
+            "min": 2199998.0,
+            "max": 20109806.0,
+            "count": 1792
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.04578428715467453,
+            "min": -0.13799507915973663,
+            "max": 0.09785564988851547,
+            "count": 1792
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -6.501368522644043,
+            "min": -26.63304901123047,
+            "max": 17.735788345336914,
+            "count": 1792
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.04887549951672554,
+            "min": -0.13961166143417358,
+            "max": 0.09776446223258972,
+            "count": 1792
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -6.94032096862793,
+            "min": -26.945051193237305,
+            "max": 17.878185272216797,
+            "count": 1792
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1792
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1792
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.12329718176747712,
+            "min": -0.41600384563207626,
+            "max": 0.36480800008773806,
+            "count": 1792
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -17.50819981098175,
+            "min": -52.78160011768341,
+            "max": 45.601000010967255,
+            "count": 1792
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.12329718176747712,
+            "min": -0.41600384563207626,
+            "max": 0.36480800008773806,
+            "count": 1792
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -17.50819981098175,
+            "min": -52.78160011768341,
+            "max": 45.601000010967255,
+            "count": 1792
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1792
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1792
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.012768109767542531,
+            "min": 0.010367057458400572,
+            "max": 0.02548085546004586,
+            "count": 869
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.012768109767542531,
+            "min": 0.010367057458400572,
+            "max": 0.02548085546004586,
+            "count": 869
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.09177817876140276,
+            "min": 0.05979832634329796,
+            "max": 0.12440450837214788,
+            "count": 869
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.09177817876140276,
+            "min": 0.05979832634329796,
+            "max": 0.12440450837214788,
+            "count": 869
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.09319816902279854,
+            "min": 0.061159982532262805,
+            "max": 0.12736019790172576,
+            "count": 869
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.09319816902279854,
+            "min": 0.061159982532262805,
+            "max": 0.12736019790172576,
+            "count": 869
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 869
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 869
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 869
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 869
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 869
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 869
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1696277873",
+        "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\C:\\Users\\assia\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.0.1+cpu",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1696365061"
+    },
+    "total": 87188.3295095,
+    "count": 1,
+    "self": 2.304758000012953,
+    "children": {
+        "run_training.setup": {
+            "total": 0.11412949999999977,
+            "count": 1,
+            "self": 0.11412949999999977
+        },
+        "TrainerController.start_learning": {
+            "total": 87185.910622,
+            "count": 1,
+            "self": 42.97262080095243,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 11.842777299992319,
+                    "count": 359,
+                    "self": 11.842777299992319
+                },
+                "TrainerController.advance": {
+                    "total": 87130.83902779905,
+                    "count": 1249186,
+                    "self": 43.913307196169626,
+                    "children": {
+                        "env_step": {
+                            "total": 34529.831184197974,
+                            "count": 1249186,
+                            "self": 27557.149798199607,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 6945.387012902138,
+                                    "count": 1249186,
+                                    "self": 221.06731429970478,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 6724.319698602433,
+                                            "count": 2277496,
+                                            "self": 6724.319698602433
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 27.29437309622666,
+                                    "count": 1249186,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 87058.09205769956,
+                                            "count": 1249186,
+                                            "is_parallel": true,
+                                            "self": 64241.860530789745,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.9765216000583141,
+                                                    "count": 718,
+                                                    "is_parallel": true,
+                                                    "self": 0.18875550028448984,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.7877660997738243,
+                                                            "count": 2872,
+                                                            "is_parallel": true,
+                                                            "self": 0.7877660997738243
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 22815.25500530975,
+                                                    "count": 1249186,
+                                                    "is_parallel": true,
+                                                    "self": 1124.5716741985998,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 765.9207953082126,
+                                                            "count": 1249186,
+                                                            "is_parallel": true,
+                                                            "self": 765.9207953082126
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 17210.207485297262,
+                                                            "count": 1249186,
+                                                            "is_parallel": true,
+                                                            "self": 17210.207485297262
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 3714.555050505679,
+                                                            "count": 2498372,
+                                                            "is_parallel": true,
+                                                            "self": 720.1168485956996,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 2994.4382019099794,
+                                                                    "count": 9993488,
+                                                                    "is_parallel": true,
+                                                                    "self": 2994.4382019099794
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 52557.094536404904,
+                            "count": 1249186,
+                            "self": 286.5318229020704,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 6838.996242502752,
+                                    "count": 1249186,
+                                    "self": 6831.211235102757,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 7.7850073999945835,
+                                            "count": 36,
+                                            "self": 7.7850073999945835
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 45431.56647100008,
+                                    "count": 870,
+                                    "self": 2983.052892099724,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 42448.513578900354,
+                                            "count": 26096,
+                                            "self": 42448.513578900354
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.3999961083754897e-06,
+                    "count": 1,
+                    "self": 1.3999961083754897e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.2561947000067448,
+                    "count": 1,
+                    "self": 0.010259700007736683,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.24593499999900814,
+                            "count": 1,
+                            "self": 0.24593499999900814
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 18499996,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18499996.onnx",
+                "reward": 0.0,
+                "creation_time": 1696356027.8130336,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18499996.pt"
+                ]
+            },
+            {
+                "steps": 18999928,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18999928.onnx",
+                "reward": 0.0,
+                "creation_time": 1696358856.1450095,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18999928.pt"
+                ]
+            },
+            {
+                "steps": 19499976,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-19499976.onnx",
+                "reward": 0.0,
+                "creation_time": 1696361579.4502475,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-19499976.pt"
+                ]
+            },
+            {
+                "steps": 19999946,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-19999946.onnx",
+                "reward": 0.0,
+                "creation_time": 1696364389.723808,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-19999946.pt"
+                ]
+            },
+            {
+                "steps": 20110520,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-20110520.onnx",
+                "reward": null,
+                "creation_time": 1696365059.336492,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-20110520.pt"
+                ]
+            }
+        ],
+        "elo": 1427.3525200605638,
+        "final_checkpoint": {
+            "steps": 20110520,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1696365059.336492,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-20110520.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.1+cpu"
+    }
+}