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: CzarnyRycerz/poca-SoccerTwos-3
+  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 sha256:1e8385963015c9b0d3544b95cfa78842ab07b9364b348fbe54408a8f2fc1fd15
+size 1768746

SoccerTwos/SoccerTwos-5999892.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6d0a4a48e4401afcae1f176f63a10e757db0da2fae109e04db84205fe413c1
+size 1768746

SoccerTwos/SoccerTwos-5999892.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:559b205fca81e372959011241fdbb2fd48070337f7fe44782a74cbb52309f849
+size 28429903

SoccerTwos/SoccerTwos-6000042.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6d0a4a48e4401afcae1f176f63a10e757db0da2fae109e04db84205fe413c1
+size 1768746

SoccerTwos/SoccerTwos-6000042.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e83d5a27261c65dbf16be1f3613c659e3c39fee5daafba0138a7c412dd558ad
+size 28429903

SoccerTwos/SoccerTwos-6112096.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8cec5a50c95c27ccbe23a60dd5d213472cc4b8f96fe1e349c317fdd3b6c5cf
+size 1768746

SoccerTwos/SoccerTwos-6112096.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5076a5e8f8edd131a8a89911d9659915b763c9695d5b1ce0c95a73597c4adbd6
+size 28429903

SoccerTwos/SoccerTwos-6499832.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08be516f551d09034a1403279d9dbf597aba7767a2500a52540c4d12dc4b7fe6
+size 1768746

SoccerTwos/SoccerTwos-6499832.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f3f7eb9f70a34f41924e2d27b3f20f452cdabe5cb68e464c84e4c5d9dee12f
+size 28429903

SoccerTwos/SoccerTwos-6511464.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459ac02d28d26de43e8a0e198dd6e4511e2e95403c0ed216392776ebf48baadf
+size 1768746

SoccerTwos/SoccerTwos-6511464.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a749794db0def4d3be0039f55c7c4ca2fa9d1231fcf55a6cd4ef7a9b7e4f2a45
+size 28429903

SoccerTwos/SoccerTwos-6759104.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e8385963015c9b0d3544b95cfa78842ab07b9364b348fbe54408a8f2fc1fd15
+size 1768746

SoccerTwos/SoccerTwos-6759104.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eacb26e66ca2cc317c16b3c6224168b91d7a3991e20b8c1a9cfc30ffaa792ed8
+size 28429903

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ee24bdfabb3282d01ee4359348907b7d7d7f8897c322f7370cb379c2cf82c4
+size 28428927

SoccerTwos/events.out.tfevents.1694291795.DESKTOP-L0G93AV.11448.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e258751a37cc1a48198321bc9a96e0af2b5f5b2eb608068385ba060ec0cf3f
+size 1917490

SoccerTwos/events.out.tfevents.1694297265.DESKTOP-L0G93AV.13408.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc7bcdf875a744583080dfc41eae263e9adc9cf66519ea0c08405bd0f5f04d4
+size 225392

SoccerTwos/events.out.tfevents.1694298905.DESKTOP-L0G93AV.15216.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b674bf2438f14fe4dee151036f8e562cd9fbdae4ee222063ee62fedb4626d6
+size 816617

SoccerTwos/events.out.tfevents.1694301049.DESKTOP-L0G93AV.3236.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef69ff9c9ccd6057d417584bb7e9daa997b486d20693ddaa9f24e5db97712ed6
+size 500438

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": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.999, "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": 12000000, "time_horizon": 1000, "summary_freq": 5000, "threaded": false, "self_play": {"save_steps": 50000, "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": "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: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.999
+        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: 12000000
+    time_horizon: 1000
+    summary_freq: 5000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      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: 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 +1,262 @@
+Mono path[0] = 'C:/ml-agents-2/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/ml-agents-2/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/ml-agents-2/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  0.146 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: 0.872100 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Setting up 2 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]: 4666 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 282 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_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 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 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_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 2
+      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 3
+      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 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 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 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]: 4667 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]: 4667 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]: 4666 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]: 4667 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]: 4667 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]: 4666 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]: 4667 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]: 4666 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 +1,361 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.7292778491973877,
+            "min": 1.6640934944152832,
+            "max": 1.7962404489517212,
+            "count": 49
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 17209.7734375,
+            "min": 12596.701171875,
+            "max": 22191.23046875,
+            "count": 49
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 53.955555555555556,
+            "min": 40.69767441860465,
+            "max": 81.16129032258064,
+            "count": 49
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 9712.0,
+            "min": 7000.0,
+            "max": 10684.0,
+            "count": 49
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1508.5287919842883,
+            "min": 1490.143744573098,
+            "max": 1513.876588566888,
+            "count": 49
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 135767.59127858595,
+            "min": 92431.31073084784,
+            "max": 180006.0418777591,
+            "count": 49
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 6754998.0,
+            "min": 6514982.0,
+            "max": 6754998.0,
+            "count": 49
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 6754998.0,
+            "min": 6514982.0,
+            "max": 6754998.0,
+            "count": 49
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.011795819737017155,
+            "min": -0.13557730615139008,
+            "max": 0.0849948599934578,
+            "count": 49
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -1.0616238117218018,
+            "min": -11.795226097106934,
+            "max": 6.544604301452637,
+            "count": 49
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.00861634686589241,
+            "min": -0.14430177211761475,
+            "max": 0.08878348767757416,
+            "count": 49
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.7754712104797363,
+            "min": -12.554253578186035,
+            "max": 6.836328506469727,
+            "count": 49
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 49
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 49
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.05251555575264825,
+            "min": -0.2765686741794448,
+            "max": 0.3353449278983517,
+            "count": 49
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -4.726400017738342,
+            "min": -22.95519995689392,
+            "max": 28.378599762916565,
+            "count": 49
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.05251555575264825,
+            "min": -0.2765686741794448,
+            "max": 0.3353449278983517,
+            "count": 49
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -4.726400017738342,
+            "min": -22.95519995689392,
+            "max": 28.378599762916565,
+            "count": 49
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 49
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 49
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.017573047970654444,
+            "min": 0.014597583053182461,
+            "max": 0.021161130908876658,
+            "count": 11
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.017573047970654444,
+            "min": 0.014597583053182461,
+            "max": 0.021161130908876658,
+            "count": 11
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.13159407824277877,
+            "min": 0.12053721149762471,
+            "max": 0.13899534344673156,
+            "count": 11
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.13159407824277877,
+            "min": 0.12053721149762471,
+            "max": 0.13899534344673156,
+            "count": 11
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.1348268409570058,
+            "min": 0.12216988056898118,
+            "max": 0.1415509695808093,
+            "count": 11
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.1348268409570058,
+            "min": 0.12216988056898118,
+            "max": 0.1415509695808093,
+            "count": 11
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 11
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 11
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 11
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 11
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 11
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 11
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1694301044",
+        "python_version": "3.9.17 (main, Jul  5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\F:\\ProgramData\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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": "1694302469"
+    },
+    "total": 1424.2489313,
+    "count": 1,
+    "self": 0.010233900000002905,
+    "children": {
+        "run_training.setup": {
+            "total": 0.13890439999999948,
+            "count": 1,
+            "self": 0.13890439999999948
+        },
+        "TrainerController.start_learning": {
+            "total": 1424.099793,
+            "count": 1,
+            "self": 0.596130299996048,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.470021500000097,
+                    "count": 3,
+                    "self": 4.470021500000097
+                },
+                "TrainerController.advance": {
+                    "total": 1418.707166400004,
+                    "count": 17241,
+                    "self": 0.584840800009033,
+                    "children": {
+                        "env_step": {
+                            "total": 408.37141819999925,
+                            "count": 17241,
+                            "self": 297.42648760000975,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 110.57506159999487,
+                                    "count": 17241,
+                                    "self": 3.8856886999988234,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 106.68937289999604,
+                                            "count": 31108,
+                                            "self": 106.68937289999604
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.369868999994619,
+                                    "count": 17241,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1360.326164599992,
+                                            "count": 17241,
+                                            "is_parallel": true,
+                                            "self": 1132.4555731999756,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.007380800000023058,
+                                                    "count": 6,
+                                                    "is_parallel": true,
+                                                    "self": 0.0016224999997893619,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.005758300000233696,
+                                                            "count": 24,
+                                                            "is_parallel": true,
+                                                            "self": 0.005758300000233696
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 227.8632106000163,
+                                                    "count": 17241,
+                                                    "is_parallel": true,
+                                                    "self": 11.888181800012006,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 12.338912099999533,
+                                                            "count": 17241,
+                                                            "is_parallel": true,
+                                                            "self": 12.338912099999533
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 164.6181298999897,
+                                                            "count": 17241,
+                                                            "is_parallel": true,
+                                                            "self": 164.6181298999897
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 39.01798680001505,
+                                                            "count": 34482,
+                                                            "is_parallel": true,
+                                                            "self": 8.702775300027241,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 30.31521149998781,
+                                                                    "count": 137928,
+                                                                    "is_parallel": true,
+                                                                    "self": 30.31521149998781
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 1009.7509073999959,
+                            "count": 17241,
+                            "self": 4.084613499997772,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 152.83068689999814,
+                                    "count": 17241,
+                                    "self": 152.83068689999814
+                                },
+                                "_update_policy": {
+                                    "total": 852.835607,
+                                    "count": 12,
+                                    "self": 72.28850790000251,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 780.5470990999975,
+                                            "count": 357,
+                                            "self": 780.5470990999975
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.9999999949504854e-06,
+                    "count": 1,
+                    "self": 1.9999999949504854e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.3264727999999195,
+                    "count": 1,
+                    "self": 0.053011699999842676,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.27346110000007684,
+                            "count": 1,
+                            "self": 0.27346110000007684
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,111 @@
+{
+    "SoccerTwos": {
+        "elo": 1500.616736505871,
+        "checkpoints": [
+            {
+                "steps": 4999868,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999868.onnx",
+                "reward": 0.0,
+                "creation_time": 1694273335.165618,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999868.pt"
+                ]
+            },
+            {
+                "steps": 5000142,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5000142.onnx",
+                "reward": 0.0,
+                "creation_time": 1694273335.4434474,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5000142.pt"
+                ]
+            },
+            {
+                "steps": 5062052,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5062052.onnx",
+                "reward": null,
+                "creation_time": 1694288369.90915,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5062052.pt"
+                ]
+            },
+            {
+                "steps": 5499882,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5499882.onnx",
+                "reward": 0.0,
+                "creation_time": 1694294379.2673812,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5499882.pt"
+                ]
+            },
+            {
+                "steps": 5999892,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5999892.onnx",
+                "reward": 0.0,
+                "creation_time": 1694297226.7495565,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5999892.pt"
+                ]
+            },
+            {
+                "steps": 6000042,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6000042.onnx",
+                "reward": 0.0,
+                "creation_time": 1694297227.0042377,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6000042.pt"
+                ]
+            },
+            {
+                "steps": 6112096,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6112096.onnx",
+                "reward": 0.0,
+                "creation_time": 1694298883.6864064,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6112096.pt"
+                ]
+            },
+            {
+                "steps": 6499832,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6499832.onnx",
+                "reward": 0.0,
+                "creation_time": 1694300931.5756173,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6499832.pt"
+                ]
+            },
+            {
+                "steps": 6511464,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6511464.onnx",
+                "reward": 0.0,
+                "creation_time": 1694301032.6351807,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6511464.pt"
+                ]
+            },
+            {
+                "steps": 6759104,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6759104.onnx",
+                "reward": null,
+                "creation_time": 1694302468.992724,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6759104.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 6759104,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1694302468.992724,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6759104.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.1+cpu"
+    }
+}