initial commit

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-SoccerTwos
+      library_name: ml-agents
+---
+    
+  # **poca** Agent playing **SoccerTwos**
+  This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+  
+  ## Usage (with ML-Agents)
+  The Documentation: https://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser:**.
+  
+  1. Go to https://huggingface.co/spaces/unity/ML-Agents-SoccerTwos
+  2. Step 1: Write your model_id: grinsepilz/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 sha256:9556c599329389517532250777093f8e0901f436bab8d8d31b7e626aa99b9cbb
+size 1768041

SoccerTwos/SoccerTwos-10000006.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9556c599329389517532250777093f8e0901f436bab8d8d31b7e626aa99b9cbb
+size 1768041

SoccerTwos/SoccerTwos-10000006.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:090ef3a7077391728f5c1cda7b89014e1d9cd7625e169c228ed0f0eea18c56d1
+size 28432689

SoccerTwos/SoccerTwos-8499982.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd67b142da05d7edac5ea72bdaa3e4036f2f9e571d20055e986ccf5d2b6b63f0
+size 1768041

SoccerTwos/SoccerTwos-8499982.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79abec607927dd4f2aec3c9acbe895b4954d09158f1083923e850281a99d2c24
+size 28432689

SoccerTwos/SoccerTwos-8999977.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a4f541c7b5271b942b5acf384288a135ce937876a893b8cc3ee08bb7f317281
+size 1768041

SoccerTwos/SoccerTwos-8999977.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abd79ef7f5df60b940d2a894fa7f8437960672fc8bd21783d04240934777ca93
+size 28432689

SoccerTwos/SoccerTwos-9499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb1be3050dd5a94948adeeead570ab1459e2796c5973180f47838f62a53b66c
+size 1768041

SoccerTwos/SoccerTwos-9499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad2f4bdcaab8b746843c733a7e8860c64fd6d6ec69b3593de73648685dc7014
+size 28432689

SoccerTwos/SoccerTwos-9999933.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb954fbc947cdea997b011317ca9b4771442cd9cade2ac44e9d7c9e0599af00
+size 1768041

SoccerTwos/SoccerTwos-9999933.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303d9cac09e1006e41b749e536e61172b96dfe17d955c73f0d3157ac97de0a04
+size 28432689

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:090ef3a7077391728f5c1cda7b89014e1d9cd7625e169c228ed0f0eea18c56d1
+size 28432689

SoccerTwos/events.out.tfevents.1679916615.linux.fritz.box.942.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4102600138f6737ef7b7e1e455ff537210dcccbd6c084da411d637d8fb4650c
+size 33034

SoccerTwos/events.out.tfevents.1679916852.linux.fritz.box.1233.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bdd5529d826edce4776d24c07d7ddfc9140c0b1d9e7eecf69983ff874320019
+size 4286577

SoccerTwos/events.out.tfevents.1679955038.linux.fritz.box.21311.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b173265cc4c836cfbc996fc349afbb0de1a4b521a006d85039b0642d8db72458
+size 422323

SoccerTwos/events.out.tfevents.1679985522.localhost.localdomain.32187.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c98d9e90aee31efae8347f44ca9c7ce590ecf02d878cd9f3ca439c1b8d6b98
+size 5139972

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": true, "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, "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: true
+      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
+  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 +1,264 @@
+Mono path[0] = '/home/ringo/cld/projects/hf-rl/unit7/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/home/ringo/cld/projects/hf-rl/unit7/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /home/ringo/cld/projects/hf-rl/unit7/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.131 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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: 0.606368 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+Setting up 2 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [2.0 KB-4.0 KB]: 1 frames, [8.0 KB-16.0 KB]: 94140 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.1 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 300.0 KB
+      Peak Allocated Bytes 249.6 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 0 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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 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 0 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 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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 2
+      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 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 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 0 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 0 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 0 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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 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 0 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 0 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 0 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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 3
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 94142 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 94142 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.7 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 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 94141 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]: 94142 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.5 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 94142 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]: 94141 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.5 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 1.0 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 94142 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]: 94141 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 +1,424 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.6562832593917847,
+            "min": 1.6314400434494019,
+            "max": 1.8750160932540894,
+            "count": 500
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 31853.640625,
+            "min": 28858.076171875,
+            "max": 42406.2265625,
+            "count": 500
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 63.11538461538461,
+            "min": 51.45161290322581,
+            "max": 101.14285714285714,
+            "count": 500
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19692.0,
+            "min": 17704.0,
+            "max": 22064.0,
+            "count": 500
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1514.3005140133923,
+            "min": 1472.297814991086,
+            "max": 1553.713721455609,
+            "count": 500
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 236230.8801860892,
+            "min": 149103.03121118248,
+            "max": 282468.9686071773,
+            "count": 500
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 9999933.0,
+            "min": 5009998.0,
+            "max": 9999933.0,
+            "count": 500
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 9999933.0,
+            "min": 5009998.0,
+            "max": 9999933.0,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.05249769985675812,
+            "min": -0.13148464262485504,
+            "max": 0.05596024543046951,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -8.189640998840332,
+            "min": -17.235153198242188,
+            "max": 7.91728401184082,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.05584041401743889,
+            "min": -0.1335737258195877,
+            "max": 0.056299399584531784,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -8.711104393005371,
+            "min": -17.356407165527344,
+            "max": 8.444910049438477,
+            "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": -0.08698461605952336,
+            "min": -0.37835263107952316,
+            "max": 0.25190099277118644,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -13.569600105285645,
+            "min": -53.19479960203171,
+            "max": 37.885400235652924,
+            "count": 500
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.08698461605952336,
+            "min": -0.37835263107952316,
+            "max": 0.25190099277118644,
+            "count": 500
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -13.569600105285645,
+            "min": -53.19479960203171,
+            "max": 37.885400235652924,
+            "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": 0.02393716434792926,
+            "min": 0.014079737310142566,
+            "max": 0.02616255192551762,
+            "count": 242
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.02393716434792926,
+            "min": 0.014079737310142566,
+            "max": 0.02616255192551762,
+            "count": 242
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.08583134735623996,
+            "min": 0.06973431346317133,
+            "max": 0.10001775523026785,
+            "count": 242
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.08583134735623996,
+            "min": 0.06973431346317133,
+            "max": 0.10001775523026785,
+            "count": 242
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.08799832488099733,
+            "min": 0.07077779869238536,
+            "max": 0.1023145705461502,
+            "count": 242
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.08799832488099733,
+            "min": 0.07077779869238536,
+            "max": 0.1023145705461502,
+            "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": "1679985522",
+        "python_version": "3.9.16 | packaged by conda-forge | (main, Feb  1 2023, 21:39:03) \n[GCC 11.3.0]",
+        "command_line_arguments": "/home/ringo/mambaforge/envs/hfrl/bin/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": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1680016724"
+    },
+    "total": 24313.71771201497,
+    "count": 1,
+    "self": 2.9138656069990247,
+    "children": {
+        "run_training.setup": {
+            "total": 0.015369058004580438,
+            "count": 1,
+            "self": 0.015369058004580438
+        },
+        "TrainerController.start_learning": {
+            "total": 24310.788477349968,
+            "count": 1,
+            "self": 9.222995623131283,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.4797519982093945,
+                    "count": 26,
+                    "self": 1.4797519982093945
+                },
+                "TrainerController.advance": {
+                    "total": 24299.41270082968,
+                    "count": 342090,
+                    "self": 9.934009993739892,
+                    "children": {
+                        "env_step": {
+                            "total": 7612.56840700563,
+                            "count": 342090,
+                            "self": 6056.9270176969585,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1550.1477266561124,
+                                    "count": 342090,
+                                    "self": 61.78468085563509,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1488.3630458004773,
+                                            "count": 627618,
+                                            "self": 1488.3630458004773
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 5.493662652559578,
+                                    "count": 342090,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 24290.890230248508,
+                                            "count": 342090,
+                                            "is_parallel": true,
+                                            "self": 19264.375193852524,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0024053090601228178,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005294650327414274,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0018758440273813903,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0018758440273813903
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.040790316998027265,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0009819030528888106,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0008409549482166767,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0008409549482166767
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03553954302333295,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03553954302333295
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0034279159735888243,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0008762438665144145,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0025516721070744097,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0025516721070744097
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.052746042085345834,
+                                                    "count": 50,
+                                                    "is_parallel": true,
+                                                    "self": 0.009087739512324333,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0436583025730215,
+                                                            "count": 200,
+                                                            "is_parallel": true,
+                                                            "self": 0.0436583025730215
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 5026.462290353898,
+                                                    "count": 342089,
+                                                    "is_parallel": true,
+                                                    "self": 324.2165042582201,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 208.9578202543198,
+                                                            "count": 342089,
+                                                            "is_parallel": true,
+                                                            "self": 208.9578202543198
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 3586.169831904408,
+                                                            "count": 342089,
+                                                            "is_parallel": true,
+                                                            "self": 3586.169831904408
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 907.1181339369505,
+                                                            "count": 684178,
+                                                            "is_parallel": true,
+                                                            "self": 171.8929641985451,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 735.2251697384054,
+                                                                    "count": 2736712,
+                                                                    "is_parallel": true,
+                                                                    "self": 735.2251697384054
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 16676.910283830308,
+                            "count": 342090,
+                            "self": 65.73303402314195,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1852.718066975649,
+                                    "count": 342090,
+                                    "self": 1849.2685519036604,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 3.4495150719885714,
+                                            "count": 10,
+                                            "self": 3.4495150719885714
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 14758.459182831517,
+                                    "count": 242,
+                                    "self": 871.5637143905624,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 13886.895468440955,
+                                            "count": 7260,
+                                            "self": 13886.895468440955
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.1409865692257881e-06,
+                    "count": 1,
+                    "self": 1.1409865692257881e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.6730277579627,
+                    "count": 1,
+                    "self": 0.004883406974840909,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.6681443509878591,
+                            "count": 1,
+                            "self": 0.6681443509878591
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "elo": 1510.5179322330282,
+        "checkpoints": [
+            {
+                "steps": 8499982,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8499982.onnx",
+                "reward": 0.0,
+                "creation_time": 1680008105.6476367,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8499982.pt"
+                ]
+            },
+            {
+                "steps": 8999977,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8999977.onnx",
+                "reward": 0.0,
+                "creation_time": 1680010637.2626488,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8999977.pt"
+                ]
+            },
+            {
+                "steps": 9499976,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9499976.onnx",
+                "reward": 0.0,
+                "creation_time": 1680013638.2338345,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9499976.pt"
+                ]
+            },
+            {
+                "steps": 9999933,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9999933.onnx",
+                "reward": 0.0,
+                "creation_time": 1680016720.6113105,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9999933.pt"
+                ]
+            },
+            {
+                "steps": 10000006,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-10000006.onnx",
+                "reward": 0.0,
+                "creation_time": 1680016721.3603675,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-10000006.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 10000006,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1680016721.3603675,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-10000006.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}