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: aphi/poca-SoccerTwos_v2
+  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 sha256:14130327c5379da93f2f6e6a3a942998ab862ba4ebde809f136064aca7884960
+size 1764633

SoccerTwos/SoccerTwos-24999956.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e60e924735cdcff5dda345df9ea93276073cc286aab9689e64d8947fe84ba8
+size 1764633

SoccerTwos/SoccerTwos-24999956.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d7bd1aee5784b7c49fa5d271baf96ba2187785fddbce238949993a7ca4eff7a
+size 28421201

SoccerTwos/SoccerTwos-25499988.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11bb95cb1b0a1ca5948f3fee3fb1cda06b2adeb5e9fa341312b4981bf9e14f95
+size 1764633

SoccerTwos/SoccerTwos-25499988.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f00e02436832733ad223547c1c6d5f65cca5cfece2cc01946703c196f1dbd6
+size 28421201

SoccerTwos/SoccerTwos-25999944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8356b722e2fead491df4e461860be322facca5530547b0889cf7b819308a65a9
+size 1764633

SoccerTwos/SoccerTwos-25999944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8bcbebaa3f92e200a291d286b4866b7867daba6c3a8ca862b6d6bab128648f
+size 28421201

SoccerTwos/SoccerTwos-26499844.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5891e72db9a1d2d8f2715b56b2b12bc68866c5a0b1a68884335709347675d9
+size 1764633

SoccerTwos/SoccerTwos-26499844.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f61e408a7770229df5bdf433914a8347b0ba797a03c661bc23b69011d12c24c
+size 28421201

SoccerTwos/SoccerTwos-26726978.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14130327c5379da93f2f6e6a3a942998ab862ba4ebde809f136064aca7884960
+size 1764633

SoccerTwos/SoccerTwos-26726978.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ad9ca63ccf31ddfadc67a05f570c0737a8c6b72c305b6cb2830d8fb718738d
+size 28421201

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ad9ca63ccf31ddfadc67a05f570c0737a8c6b72c305b6cb2830d8fb718738d
+size 28421201

SoccerTwos/events.out.tfevents.1691251005.xps.30150.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08fb20ade21d9bceb6bc73a0f45812c130812376b5cfba96b66734dd6e0840e4
+size 9913441

SoccerTwos/events.out.tfevents.1691280966.xps.45349.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4c1c98b959067515b7c7d403a4e37c0ef62193dc58561d10eafceff9a4193f
+size 17247119

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": 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.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,82 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        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.x86_64
+  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 +1,284 @@
+Mono path[0] = '/home/aphi/repo/marl_soccer/ml-agents/training-envs-executables/SoccerTwos_Data/Managed'
+Mono config path = '/home/aphi/repo/marl_soccer/ml-agents/training-envs-executables/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/aphi/repo/marl_soccer/ml-agents/training-envs-executables/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  0.061 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: 0.631859 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 4 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 315894 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_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 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 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 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_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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 4
+      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 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 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]: 315895 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.8 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 315895 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.4 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 315894 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]: 315895 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]: 315895 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]: 315894 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]: 315895 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]: 315894 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": 1.5208332538604736,
+            "min": 1.273158311843872,
+            "max": 1.8148019313812256,
+            "count": 1678
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 29832.6640625,
+            "min": 20223.357421875,
+            "max": 40978.0546875,
+            "count": 1678
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 63.51315789473684,
+            "min": 43.981651376146786,
+            "max": 136.02702702702703,
+            "count": 1678
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19308.0,
+            "min": 10900.0,
+            "max": 21472.0,
+            "count": 1678
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1586.8200921264854,
+            "min": 1542.8708725938334,
+            "max": 1668.9721804534734,
+            "count": 1678
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 241196.6540032258,
+            "min": 117899.30230656838,
+            "max": 365068.93665123876,
+            "count": 1678
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 26719946.0,
+            "min": 9949994.0,
+            "max": 26719946.0,
+            "count": 1678
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 26719946.0,
+            "min": 9949994.0,
+            "max": 26719946.0,
+            "count": 1678
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.06350585073232651,
+            "min": -0.14680367708206177,
+            "max": 0.0801720917224884,
+            "count": 1678
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -9.652889251708984,
+            "min": -27.305482864379883,
+            "max": 14.987405776977539,
+            "count": 1678
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.06474441289901733,
+            "min": -0.14830423891544342,
+            "max": 0.08140476793050766,
+            "count": 1678
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -9.841150283813477,
+            "min": -27.58458709716797,
+            "max": 15.016227722167969,
+            "count": 1678
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1678
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1678
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.1389289466958297,
+            "min": -0.4145650787959023,
+            "max": 0.3313132074643981,
+            "count": 1678
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -21.117199897766113,
+            "min": -63.71439999341965,
+            "max": 51.0037996172905,
+            "count": 1678
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.1389289466958297,
+            "min": -0.4145650787959023,
+            "max": 0.3313132074643981,
+            "count": 1678
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -21.117199897766113,
+            "min": -63.71439999341965,
+            "max": 51.0037996172905,
+            "count": 1678
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1678
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1678
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01615842728157683,
+            "min": 0.009192483994168773,
+            "max": 0.026691062779476245,
+            "count": 813
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01615842728157683,
+            "min": 0.009192483994168773,
+            "max": 0.026691062779476245,
+            "count": 813
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.09005015144745508,
+            "min": 0.06957109409073989,
+            "max": 0.12221147641539573,
+            "count": 813
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.09005015144745508,
+            "min": 0.06957109409073989,
+            "max": 0.12221147641539573,
+            "count": 813
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.0914334607621034,
+            "min": 0.07065122574567795,
+            "max": 0.12482641264796257,
+            "count": 813
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.0914334607621034,
+            "min": 0.07065122574567795,
+            "max": 0.12482641264796257,
+            "count": 813
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 813
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 813
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 813
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 813
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 813
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 813
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1691280965",
+        "python_version": "3.9.9 (main, Dec 22 2021, 19:41:22) \n[GCC 10.3.0]",
+        "command_line_arguments": "/home/aphi/.pyenv/versions/3.9.9/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --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": "1691317518"
+    },
+    "total": 36553.451603412,
+    "count": 1,
+    "self": 0.07956845599983353,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05672447699907934,
+            "count": 1,
+            "self": 0.05672447699907934
+        },
+        "TrainerController.start_learning": {
+            "total": 36553.315310479,
+            "count": 1,
+            "self": 25.90310476511513,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.8752524210576667,
+                    "count": 85,
+                    "self": 2.8752524210576667
+                },
+                "TrainerController.advance": {
+                    "total": 36524.34532972085,
+                    "count": 1154518,
+                    "self": 27.165245878706628,
+                    "children": {
+                        "env_step": {
+                            "total": 18919.483706302977,
+                            "count": 1154518,
+                            "self": 16086.282047817207,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 2817.332583169118,
+                                    "count": 1154518,
+                                    "self": 122.10931460303254,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 2695.2232685660856,
+                                            "count": 2105992,
+                                            "self": 2695.2232685660856
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 15.869075316652015,
+                                    "count": 1154517,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 36513.4823779097,
+                                            "count": 1154517,
+                                            "is_parallel": true,
+                                            "self": 23220.272478314437,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.001969711003766861,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.000470619008410722,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0014990919953561388,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0014990919953561388
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03214666799613042,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006364009896060452,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0007950849976623431,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0007950849976623431
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.027651450000121258,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.027651450000121258
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0030637320087407716,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0007643250064575113,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0022994070022832602,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0022994070022832602
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.1485878519670223,
+                                                    "count": 168,
+                                                    "is_parallel": true,
+                                                    "self": 0.029665567053598352,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.11892228491342394,
+                                                            "count": 672,
+                                                            "is_parallel": true,
+                                                            "self": 0.11892228491342394
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 13293.061311743295,
+                                                    "count": 1154516,
+                                                    "is_parallel": true,
+                                                    "self": 792.2785328326936,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 670.7080909666547,
+                                                            "count": 1154516,
+                                                            "is_parallel": true,
+                                                            "self": 670.7080909666547
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 9608.185685382246,
+                                                            "count": 1154516,
+                                                            "is_parallel": true,
+                                                            "self": 9608.185685382246
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 2221.8890025617,
+                                                            "count": 2309032,
+                                                            "is_parallel": true,
+                                                            "self": 437.1007224857385,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1784.7882800759617,
+                                                                    "count": 9236128,
+                                                                    "is_parallel": true,
+                                                                    "self": 1784.7882800759617
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 17577.696377539163,
+                            "count": 1154517,
+                            "self": 181.50837569407304,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 3242.301654148134,
+                                    "count": 1154517,
+                                    "self": 3235.886169627105,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 6.415484521028702,
+                                            "count": 34,
+                                            "self": 6.415484521028702
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 14153.886347696956,
+                                    "count": 814,
+                                    "self": 2519.5350972263477,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 11634.351250470609,
+                                            "count": 24420,
+                                            "self": 11634.351250470609
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.581996912136674e-06,
+                    "count": 1,
+                    "self": 1.581996912136674e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.19162198998674285,
+                    "count": 1,
+                    "self": 0.0018692279845708981,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.18975276200217195,
+                            "count": 1,
+                            "self": 0.18975276200217195
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 24999956,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-24999956.onnx",
+                "reward": 0.0,
+                "creation_time": 1691313765.2383819,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-24999956.pt"
+                ]
+            },
+            {
+                "steps": 25499988,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-25499988.onnx",
+                "reward": 0.0,
+                "creation_time": 1691314824.1330147,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-25499988.pt"
+                ]
+            },
+            {
+                "steps": 25999944,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-25999944.onnx",
+                "reward": 0.0,
+                "creation_time": 1691315914.2725737,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-25999944.pt"
+                ]
+            },
+            {
+                "steps": 26499844,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-26499844.onnx",
+                "reward": 0.0,
+                "creation_time": 1691317009.8439658,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-26499844.pt"
+                ]
+            },
+            {
+                "steps": 26726978,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-26726978.onnx",
+                "reward": 0.0,
+                "creation_time": 1691317518.3692434,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-26726978.pt"
+                ]
+            }
+        ],
+        "elo": 1583.2210909736555,
+        "final_checkpoint": {
+            "steps": 26726978,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1691317518.3692434,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-26726978.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}