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: jvilaseca/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:ed1913dd6b9cdfda54f81e1fbf1e388c62126d973ed36125b54668904084088c
+size 1768746

SoccerTwos/SoccerTwos-22499940.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a71b46d5dd00e4edf9cf571e2103c84f2f1b0fba8d2e8087282d2eae11d0c1f
+size 1768746

SoccerTwos/SoccerTwos-22499940.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43cb2bec7504935164af6d557a3c2c5478196707a32e39ffc22c7d2df5790b63
+size 28430025

SoccerTwos/SoccerTwos-22999895.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:109fddfa765ec973fff11ae3516973bb700af24bba7c722cb462a7fd4c8317f1
+size 1768746

SoccerTwos/SoccerTwos-22999895.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d6325238431481a9f6881a37a1a2c6e4fdebe196e698f10e0b9f51b437ad94
+size 28430025

SoccerTwos/SoccerTwos-23499988.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4e9cfcac9cb11c71dde716779abfdc79ab8a03604213a87c1eff5708848bac
+size 1768746

SoccerTwos/SoccerTwos-23499988.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020ff936637eaa6daa18524db4594f867158755f8d6c8149d72becf509937a81
+size 28430025

SoccerTwos/SoccerTwos-23999902.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b67696b1ab5c4fb6a1ff7789a996e82c674967948a91c5ceff143a466e86720e
+size 1768746

SoccerTwos/SoccerTwos-23999902.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f232600b3298261faf373a9a594f658b9332324bab49473a378edc82e2b8411
+size 28430025

SoccerTwos/SoccerTwos-24016242.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed1913dd6b9cdfda54f81e1fbf1e388c62126d973ed36125b54668904084088c
+size 1768746

SoccerTwos/SoccerTwos-24016242.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a2bf234df2a36f40bf8cf1661ebae95979a3350be214cc8fcc22f8278d4210
+size 28430025

SoccerTwos/SoccerTwos-499316.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d044dcba3bde67281048b3fc292ffc1b72e9c809d744ebc5ea2b890ceef2ae
+size 28429781

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab07c8100cb6c535e6aa373962a805d2356d5ec5de0ad81c5777f69c913610b
+size 28428927

SoccerTwos/events.out.tfevents.1688235486.el-pepe-equipo.7972.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92372f86f282ea31a7f73836776d5e73ba19d259961683052dd370c040a926d1
+size 300265

SoccerTwos/events.out.tfevents.1688240925.el-pepe-equipo.15320.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7027588e63e1c57cc0d6da61ba081007b145d9401264165176dc33410cf5af17
+size 1978410

SoccerTwos/events.out.tfevents.1688249213.el-pepe-equipo.5628.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082437bf710e43723a2e16870377ecb15f420e22cec5ce48668a40b48d2c3e2e
+size 21461

SoccerTwos/events.out.tfevents.1688255654.el-pepe-equipo.4816.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb1e48b8b6da7eb102d77729c2aba908684c7683c3c4869a023992d25c60eff1
+size 14657187

SoccerTwos/events.out.tfevents.1688309458.el-pepe-equipo.14940.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b8fddfae0829b48094267622c648a82da6bb12cb95b4d79273856ffa2759c6
+size 7092705

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": 0.006, "epsilon": 0.2, "lambd": 0.96, "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": 50000000, "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.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: 0.006
+      epsilon: 0.2
+      lambd: 0.96
+      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: 50000000
+    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.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] = 'F:/Cursos/HuggingFaceDeepReionforcementLearning/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'F:/Cursos/HuggingFaceDeepReionforcementLearning/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path F:/Cursos/HuggingFaceDeepReionforcementLearning/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  4.376 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: 0.665800 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]: 129849 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 411 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_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 0.8 KB
+      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 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]: 129850 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]: 129850 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]: 129849 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]: 129850 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]: 129850 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]: 129849 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]: 129850 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]: 129849 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": 1.7245991230010986,
+            "min": 1.6280959844589233,
+            "max": 1.803169846534729,
+            "count": 690
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 34050.484375,
+            "min": 16252.23046875,
+            "max": 41848.55078125,
+            "count": 690
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 72.42028985507247,
+            "min": 41.73728813559322,
+            "max": 107.25,
+            "count": 690
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19988.0,
+            "min": 7296.0,
+            "max": 21240.0,
+            "count": 690
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1652.446273309946,
+            "min": 1623.0626194903318,
+            "max": 1693.4569155917834,
+            "count": 690
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 228037.58571677256,
+            "min": 114220.06391457033,
+            "max": 392609.14351578726,
+            "count": 690
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 24009948.0,
+            "min": 17119989.0,
+            "max": 24009948.0,
+            "count": 690
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 24009948.0,
+            "min": 17119989.0,
+            "max": 24009948.0,
+            "count": 690
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.03957207128405571,
+            "min": -0.12997280061244965,
+            "max": 0.07670627534389496,
+            "count": 690
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -5.381801605224609,
+            "min": -20.535701751708984,
+            "max": 13.755611419677734,
+            "count": 690
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.03876207023859024,
+            "min": -0.1288316398859024,
+            "max": 0.07834520936012268,
+            "count": 690
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -5.271641731262207,
+            "min": -20.355398178100586,
+            "max": 13.634573936462402,
+            "count": 690
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 690
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 690
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.046152938814724195,
+            "min": -0.36934179067611694,
+            "max": 0.3203398482243818,
+            "count": 690
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 6.27679967880249,
+            "min": -62.43619990348816,
+            "max": 46.91000020503998,
+            "count": 690
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.046152938814724195,
+            "min": -0.36934179067611694,
+            "max": 0.3203398482243818,
+            "count": 690
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 6.27679967880249,
+            "min": -62.43619990348816,
+            "max": 46.91000020503998,
+            "count": 690
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 690
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 690
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.014841787061747406,
+            "min": 0.011989216684984665,
+            "max": 0.023097134284519902,
+            "count": 334
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.014841787061747406,
+            "min": 0.011989216684984665,
+            "max": 0.023097134284519902,
+            "count": 334
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10486778641740481,
+            "min": 0.08783568665385247,
+            "max": 0.13843777825435002,
+            "count": 334
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10486778641740481,
+            "min": 0.08783568665385247,
+            "max": 0.13843777825435002,
+            "count": 334
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.1062960721552372,
+            "min": 0.08942758962512017,
+            "max": 0.14068217327197394,
+            "count": 334
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.1062960721552372,
+            "min": 0.08942758962512017,
+            "max": 0.14068217327197394,
+            "count": 334
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 334
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 334
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 334
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 334
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.006000000000000002,
+            "min": 0.006000000000000002,
+            "max": 0.006000000000000002,
+            "count": 334
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.006000000000000002,
+            "min": 0.006000000000000002,
+            "max": 0.006000000000000002,
+            "count": 334
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1688309449",
+        "python_version": "3.9.16 (main, May 17 2023, 17:49:16) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\pepe\\miniconda3\\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": "1688336916"
+    },
+    "total": 27466.885090400003,
+    "count": 1,
+    "self": 1.1405648000036308,
+    "children": {
+        "run_training.setup": {
+            "total": 0.14519139999999986,
+            "count": 1,
+            "self": 0.14519139999999986
+        },
+        "TrainerController.start_learning": {
+            "total": 27465.5993342,
+            "count": 1,
+            "self": 11.204596699637477,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 9.80414069999125,
+                    "count": 36,
+                    "self": 9.80414069999125
+                },
+                "TrainerController.advance": {
+                    "total": 27444.38761920037,
+                    "count": 476298,
+                    "self": 11.01459670057011,
+                    "children": {
+                        "env_step": {
+                            "total": 7679.875852500507,
+                            "count": 476298,
+                            "self": 5911.034287698587,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1761.6579132017594,
+                                    "count": 476298,
+                                    "self": 67.78359530101602,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1693.8743179007433,
+                                            "count": 865678,
+                                            "self": 1693.8743179007433
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 7.183651600160358,
+                                    "count": 476297,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 27439.14209659975,
+                                            "count": 476297,
+                                            "is_parallel": true,
+                                            "self": 22733.734255899493,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.06647450001096544,
+                                                    "count": 72,
+                                                    "is_parallel": true,
+                                                    "self": 0.014102900009500985,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.05237160000146446,
+                                                            "count": 288,
+                                                            "is_parallel": true,
+                                                            "self": 0.05237160000146446
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 4705.341366200246,
+                                                    "count": 476297,
+                                                    "is_parallel": true,
+                                                    "self": 237.28460120103773,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 193.13705809924238,
+                                                            "count": 476297,
+                                                            "is_parallel": true,
+                                                            "self": 193.13705809924238
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 3466.292329999416,
+                                                            "count": 476297,
+                                                            "is_parallel": true,
+                                                            "self": 3466.292329999416
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 808.62737690055,
+                                                            "count": 952594,
+                                                            "is_parallel": true,
+                                                            "self": 167.28985730025352,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 641.3375196002964,
+                                                                    "count": 3810376,
+                                                                    "is_parallel": true,
+                                                                    "self": 641.3375196002964
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 19753.497169999293,
+                            "count": 476297,
+                            "self": 87.17292039913082,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 2177.9227992001324,
+                                    "count": 476297,
+                                    "self": 2175.370412100131,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 2.5523871000011695,
+                                            "count": 14,
+                                            "self": 2.5523871000011695
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 17488.40145040003,
+                                    "count": 335,
+                                    "self": 1199.457120199988,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 16288.944330200042,
+                                            "count": 10050,
+                                            "self": 16288.944330200042
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.2000018614344299e-06,
+                    "count": 1,
+                    "self": 1.2000018614344299e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.2029763999998977,
+                    "count": 1,
+                    "self": 0.06067310000071302,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.14230329999918467,
+                            "count": 1,
+                            "self": 0.14230329999918467
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "elo": 1652.7421097582996,
+        "checkpoints": [
+            {
+                "steps": 22499940,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-22499940.onnx",
+                "reward": 0.0,
+                "creation_time": 1688330550.1759133,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-22499940.pt"
+                ]
+            },
+            {
+                "steps": 22999895,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-22999895.onnx",
+                "reward": 0.0,
+                "creation_time": 1688332692.1137958,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-22999895.pt"
+                ]
+            },
+            {
+                "steps": 23499988,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-23499988.onnx",
+                "reward": 0.0,
+                "creation_time": 1688334736.8827655,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-23499988.pt"
+                ]
+            },
+            {
+                "steps": 23999902,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-23999902.onnx",
+                "reward": 0.0,
+                "creation_time": 1688336832.3774817,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-23999902.pt"
+                ]
+            },
+            {
+                "steps": 24016242,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-24016242.onnx",
+                "reward": null,
+                "creation_time": 1688336914.8924851,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-24016242.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 24016242,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1688336914.8924851,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-24016242.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.1+cpu"
+    }
+}