iDUMB

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: H3lt3r-Sk3lt3r/poca-SoccerTwosV2
+  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:b1e0f7b7b6d3a8a9f9efdc64bfab5e45c578a74c4583e0a56df6d82d9212b0aa
+size 1768747

SoccerTwos/SoccerTwos-10000120.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e0f7b7b6d3a8a9f9efdc64bfab5e45c578a74c4583e0a56df6d82d9212b0aa
+size 1768747

SoccerTwos/SoccerTwos-10000120.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5572567ccb9746db9d54933fc6c0ddaf58ca9cebda4928051fb944d6715fcf3e
+size 28430482

SoccerTwos/SoccerTwos-8499974.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f6fafa10ac989330bee6d447d451c48d8c443bff61e196dbfba20aff95893b
+size 1768747

SoccerTwos/SoccerTwos-8499974.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0791ae4f2feab9c9ffdd133d71c4ab0cea6f135eea01d83195a4e0d3ad0e19
+size 28430358

SoccerTwos/SoccerTwos-8999838.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4077cfa014b2b50a85c65348c9f98e45e6e4ed6a651ceb2e4ab0729b7cb4b7
+size 1768747

SoccerTwos/SoccerTwos-8999838.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc13162630c1dc990f58b39e6e47613102f58fc5035aec275272d55b22ab4b28
+size 28430358

SoccerTwos/SoccerTwos-9499718.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6bf62e65f96fd4ca50c1f053b3a148ec8627fb3e5ac25e75874c365189bcc4
+size 1768747

SoccerTwos/SoccerTwos-9499718.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25f2dcb70c1bb81598e011f852f6718f4a47c4aa50697ee1fccf8cd1bad749b
+size 28430358

SoccerTwos/SoccerTwos-9999956.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e0f7b7b6d3a8a9f9efdc64bfab5e45c578a74c4583e0a56df6d82d9212b0aa
+size 1768747

SoccerTwos/SoccerTwos-9999956.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67d5dbfc08b99031d4d37ff3cd78865ae935b7a26f5b8d506699bc9dbc93758
+size 28430358

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa1787a7eb3fa19b1a418ecd2e4637b32a14687b31b36ce2b6d6e4878a2b1cc
+size 28429366

SoccerTwos/events.out.tfevents.1717621707.DESKTOP-VA12GP7.11480.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a63789738b2dbf833ce513330090a9a6a4ec49cb832cecc3f612818d9cd3f2f0
+size 4159127

SoccerTwos/events.out.tfevents.1717661186.DESKTOP-VA12GP7.13216.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea12d625b8530c362feb73d638962ac418464bc33294d404fc06803df692c02d
+size 5139973

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": 0.99, "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": 10000000, "time_horizon": 1000, "summary_freq": 10000, "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, "timeout_wait": 60, "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": 20.0, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "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 +1,84 @@
+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: 0.99
+        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: 10000000
+    time_horizon: 1000
+    summary_freq: 10000
+    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
+  timeout_wait: 60
+  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: 20.0
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+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 +1,284 @@
+Mono path[0] = 'C:/Users/wte42/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/Users/wte42/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/Users/wte42/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  3.770 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: 1.200300 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+TOO LONG
+TOO LONG
+Setting up 4 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [4.0 KB-8.0 KB]: 1 frames, [8.0 KB-16.0 KB]: 94180 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 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 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 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 5
+    [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]: 94182 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]: 94182 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.5 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]: 94181 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]: 94182 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]: 94182 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]: 94181 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 94182 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]: 94181 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": 1.8245843648910522,
+            "min": 1.6784312725067139,
+            "max": 2.265312433242798,
+            "count": 500
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 34389.765625,
+            "min": 29133.91015625,
+            "max": 49488.48046875,
+            "count": 500
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 89.12962962962963,
+            "min": 39.88709677419355,
+            "max": 112.27272727272727,
+            "count": 500
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19252.0,
+            "min": 18112.0,
+            "max": 21080.0,
+            "count": 500
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1559.1608573381989,
+            "min": 1433.2700543149463,
+            "max": 1596.7947189480517,
+            "count": 500
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 168389.37259252547,
+            "min": 132379.53545709304,
+            "max": 368037.8036492519,
+            "count": 500
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 9999956.0,
+            "min": 5009949.0,
+            "max": 9999956.0,
+            "count": 500
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 9999956.0,
+            "min": 5009949.0,
+            "max": 9999956.0,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.06259040534496307,
+            "min": -0.149006649851799,
+            "max": 0.0909595862030983,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 6.759763717651367,
+            "min": -21.009937286376953,
+            "max": 14.35448932647705,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.06400468200445175,
+            "min": -0.15823207795619965,
+            "max": 0.09040261805057526,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 6.912505626678467,
+            "min": -22.31072235107422,
+            "max": 15.123698234558105,
+            "count": 500
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 500
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.05145184971668102,
+            "min": -0.4720098376274109,
+            "max": 0.3441641035242977,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -5.55679976940155,
+            "min": -58.468000054359436,
+            "max": 40.542799949645996,
+            "count": 500
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.05145184971668102,
+            "min": -0.4720098376274109,
+            "max": 0.3441641035242977,
+            "count": 500
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -5.55679976940155,
+            "min": -58.468000054359436,
+            "max": 40.542799949645996,
+            "count": 500
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 500
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 500
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.013097892559987183,
+            "min": 0.010496539979552228,
+            "max": 0.025193315698804022,
+            "count": 242
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.013097892559987183,
+            "min": 0.010496539979552228,
+            "max": 0.025193315698804022,
+            "count": 242
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.07199831406275431,
+            "min": 0.06497642882168293,
+            "max": 0.12120228086908659,
+            "count": 242
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.07199831406275431,
+            "min": 0.06497642882168293,
+            "max": 0.12120228086908659,
+            "count": 242
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.07323341642816862,
+            "min": 0.06622683145105838,
+            "max": 0.12384758914510409,
+            "count": 242
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.07323341642816862,
+            "min": 0.06622683145105838,
+            "max": 0.12384758914510409,
+            "count": 242
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 242
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 242
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 242
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 242
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 242
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 242
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1717661176",
+        "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul  5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\C:\\Users\\wte42\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./results/SoccerTwos/configuration.yaml --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.3.0+cpu",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1717699155"
+    },
+    "total": 37978.191293700016,
+    "count": 1,
+    "self": 1.7217363999807276,
+    "children": {
+        "run_training.setup": {
+            "total": 0.1701382999890484,
+            "count": 1,
+            "self": 0.1701382999890484
+        },
+        "TrainerController.start_learning": {
+            "total": 37976.299419000046,
+            "count": 1,
+            "self": 13.491651406046003,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 12.97793160006404,
+                    "count": 26,
+                    "self": 12.97793160006404
+                },
+                "TrainerController.advance": {
+                    "total": 37949.59294379392,
+                    "count": 343208,
+                    "self": 12.36389017739566,
+                    "children": {
+                        "env_step": {
+                            "total": 12556.275907405827,
+                            "count": 343208,
+                            "self": 9485.117376446258,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 3062.482253482158,
+                                    "count": 343208,
+                                    "self": 79.84183619933901,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 2982.640417282819,
+                                            "count": 627882,
+                                            "self": 2982.640417282819
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 8.676277477410622,
+                                    "count": 343208,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 37948.99914501875,
+                                            "count": 343208,
+                                            "is_parallel": true,
+                                            "self": 30425.611817030294,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.09982249996392056,
+                                                    "count": 52,
+                                                    "is_parallel": true,
+                                                    "self": 0.018828099709935486,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.08099440025398508,
+                                                            "count": 208,
+                                                            "is_parallel": true,
+                                                            "self": 0.08099440025398508
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 7523.2875054884935,
+                                                    "count": 343208,
+                                                    "is_parallel": true,
+                                                    "self": 362.36901493981713,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 395.00273852143437,
+                                                            "count": 343208,
+                                                            "is_parallel": true,
+                                                            "self": 395.00273852143437
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 5345.40010620479,
+                                                            "count": 343208,
+                                                            "is_parallel": true,
+                                                            "self": 5345.40010620479
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1420.515645822452,
+                                                            "count": 686416,
+                                                            "is_parallel": true,
+                                                            "self": 243.84451605426148,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1176.6711297681904,
+                                                                    "count": 2745664,
+                                                                    "is_parallel": true,
+                                                                    "self": 1176.6711297681904
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 25380.953146210697,
+                            "count": 343208,
+                            "self": 95.99636962643126,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 3647.4665173835238,
+                                    "count": 343208,
+                                    "self": 3645.0027465834864,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 2.4637708000373095,
+                                            "count": 10,
+                                            "self": 2.4637708000373095
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 21637.490259200742,
+                                    "count": 242,
+                                    "self": 1779.7197898029117,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 19857.77046939783,
+                                            "count": 7260,
+                                            "self": 19857.77046939783
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.9000144675374031e-06,
+                    "count": 1,
+                    "self": 1.9000144675374031e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.23689030000241473,
+                    "count": 1,
+                    "self": 0.01592880004318431,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.22096149995923042,
+                            "count": 1,
+                            "self": 0.22096149995923042
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 8499974,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8499974.onnx",
+                "reward": 0.0,
+                "creation_time": 1717688624.3140993,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8499974.pt"
+                ]
+            },
+            {
+                "steps": 8999838,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8999838.onnx",
+                "reward": 0.0,
+                "creation_time": 1717692529.3960245,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8999838.pt"
+                ]
+            },
+            {
+                "steps": 9499718,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9499718.onnx",
+                "reward": 0.0,
+                "creation_time": 1717695895.4661543,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9499718.pt"
+                ]
+            },
+            {
+                "steps": 9999956,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9999956.onnx",
+                "reward": 0.0,
+                "creation_time": 1717699153.0336573,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9999956.pt"
+                ]
+            },
+            {
+                "steps": 10000120,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10000120.onnx",
+                "reward": 0.0,
+                "creation_time": 1717699153.3506024,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10000120.pt"
+                ]
+            }
+        ],
+        "elo": 1561.5495543006061,
+        "final_checkpoint": {
+            "steps": 10000120,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1717699153.3506024,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10000120.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.3.0+cpu"
+    }
+}