Try to improve

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: marik0/poca-SoccerTwos-DaniRojas2
+  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 sha256:65ecbf002e116bcbc67d74998a503a67ef431521efb91490b32e54efdfb8155f
+size 1763220

SoccerTwos/SoccerTwos-10000022.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ecbf002e116bcbc67d74998a503a67ef431521efb91490b32e54efdfb8155f
+size 1763220

SoccerTwos/SoccerTwos-10000022.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d11f22a4406484f66105d15e64f4c9718c93589f627d7fa542703797761c771f
+size 28423851

SoccerTwos/SoccerTwos-8828448.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ec6010bd367b80bb5f23ee4c77daa322fb98be65f368acebd47b086f508030
+size 1763220

SoccerTwos/SoccerTwos-8828448.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c896f67e5fa437628e327ee3faeb633654f1be17806c47d5c98357757c4dd7f
+size 28423851

SoccerTwos/SoccerTwos-8999826.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2dd3a5deeb2dbd881bdce0ef2dfcdbe6b2243e47890a2e7035c89ec4168ff59
+size 1763220

SoccerTwos/SoccerTwos-8999826.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e750f7738a175966a686a5a2975bc5f496c71d51f2fc7acd8b1409f6034d17e3
+size 28423851

SoccerTwos/SoccerTwos-9499977.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:125958972b8f237570c8f1f2ef9564f747289447ba040512e2579eb8849bbdeb
+size 1763220

SoccerTwos/SoccerTwos-9499977.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54650c62de7b965685ef517be8e2487032f82509a141c0e0d7618937ef9fe312
+size 28423851

SoccerTwos/SoccerTwos-9999984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ecbf002e116bcbc67d74998a503a67ef431521efb91490b32e54efdfb8155f
+size 1763220

SoccerTwos/SoccerTwos-9999984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a09f6da89807c8a3cea87ed8d35741c132070229cc15ce5275a5ece99bd6b68
+size 28423851

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d11f22a4406484f66105d15e64f4c9718c93589f627d7fa542703797761c771f
+size 28423851

SoccerTwos/events.out.tfevents.1675364979.hulk.315189.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1038a09cc5a5f58b7efcb4d275ab796bb5cf128beea975f158a865eac2132222
+size 16702

SoccerTwos/events.out.tfevents.1675365126.hulk.315696.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c4d0884293b0d93fc9661df004869c6dd15d8e5730905e130ad5c6caedf341c
+size 8923196

SoccerTwos/events.out.tfevents.1675428123.hulk.322700.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7d25dc11dd74b9796039846958de0c59e815eb24cf97430f499dabaf27767e
+size 1213549

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 10000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 70000, "team_change": 260000, "swap_steps": 3000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos", "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: 10000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 70000
+      team_change: 260000
+      swap_steps: 3000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos
+  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/mari/repos/ml-agents/training-envs-executables/SoccerTwos_Data/Managed'
+Mono config path = '/home/mari/repos/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/mari/repos/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  0.117 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: 1.078744 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]: 22029 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]: 22030 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]: 22030 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]: 22029 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]: 22030 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]: 22030 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]: 22029 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.4 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]: 22030 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]: 22029 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": 1.686773657798767,
+            "min": 1.571251630783081,
+            "max": 1.7149637937545776,
+            "count": 118
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 34383.1953125,
+            "min": 8038.44580078125,
+            "max": 37387.62890625,
+            "count": 118
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 52.86021505376344,
+            "min": 40.46666666666667,
+            "max": 78.96969696969697,
+            "count": 118
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19664.0,
+            "min": 3384.0,
+            "max": 20848.0,
+            "count": 118
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1604.7561279872616,
+            "min": 1596.147576056119,
+            "max": 1641.8914249784082,
+            "count": 118
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 298484.63980563066,
+            "min": 60886.60501160265,
+            "max": 388015.8269429932,
+            "count": 118
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 9999984.0,
+            "min": 8829868.0,
+            "max": 9999984.0,
+            "count": 118
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 9999984.0,
+            "min": 8829868.0,
+            "max": 9999984.0,
+            "count": 118
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.06201007962226868,
+            "min": -0.10462847352027893,
+            "max": 0.06627217680215836,
+            "count": 118
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -11.471864700317383,
+            "min": -18.937753677368164,
+            "max": 13.519523620605469,
+            "count": 118
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.06280722469091415,
+            "min": -0.10412157326936722,
+            "max": 0.07305586338043213,
+            "count": 118
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -11.61933708190918,
+            "min": -18.846004486083984,
+            "max": 14.903395652770996,
+            "count": 118
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 118
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 118
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.12782270489512262,
+            "min": -0.2589891300253246,
+            "max": 0.27226732567985457,
+            "count": 118
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -23.647200405597687,
+            "min": -47.65399992465973,
+            "max": 54.99799978733063,
+            "count": 118
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.12782270489512262,
+            "min": -0.2589891300253246,
+            "max": 0.27226732567985457,
+            "count": 118
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -23.647200405597687,
+            "min": -47.65399992465973,
+            "max": 54.99799978733063,
+            "count": 118
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 118
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 118
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.017015760073748727,
+            "min": 0.011039437506891165,
+            "max": 0.02371452291457293,
+            "count": 56
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.017015760073748727,
+            "min": 0.011039437506891165,
+            "max": 0.02371452291457293,
+            "count": 56
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10656303465366364,
+            "min": 0.09706846177577973,
+            "max": 0.1288724867006143,
+            "count": 56
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10656303465366364,
+            "min": 0.09706846177577973,
+            "max": 0.1288724867006143,
+            "count": 56
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10831870262821515,
+            "min": 0.09825346643726031,
+            "max": 0.13139269451300303,
+            "count": 56
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10831870262821515,
+            "min": 0.09825346643726031,
+            "max": 0.13139269451300303,
+            "count": 56
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 56
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 56
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 56
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 56
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 56
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 56
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1675428121",
+        "python_version": "3.8.16 | packaged by conda-forge | (default, Feb  1 2023, 16:01:55) \n[GCC 11.3.0]",
+        "command_line_arguments": "/home/mari/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos --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": "1.8.1+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1675434084"
+    },
+    "total": 5962.774227431975,
+    "count": 1,
+    "self": 0.425103104673326,
+    "children": {
+        "run_training.setup": {
+            "total": 0.01730215735733509,
+            "count": 1,
+            "self": 0.01730215735733509
+        },
+        "TrainerController.start_learning": {
+            "total": 5962.331822169945,
+            "count": 1,
+            "self": 2.5349797243252397,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.4496937403455377,
+                    "count": 6,
+                    "self": 1.4496937403455377
+                },
+                "TrainerController.advance": {
+                    "total": 5957.906488174573,
+                    "count": 81806,
+                    "self": 2.2628058372065425,
+                    "children": {
+                        "env_step": {
+                            "total": 2198.078187521547,
+                            "count": 81806,
+                            "self": 1679.0800731424242,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 517.4854472810403,
+                                    "count": 81806,
+                                    "self": 13.031771199777722,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 504.45367608126253,
+                                            "count": 146866,
+                                            "self": 504.45367608126253
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.512667098082602,
+                                    "count": 81806,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 5957.9678576486185,
+                                            "count": 81806,
+                                            "is_parallel": true,
+                                            "self": 4595.35154273361,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.004851153120398521,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0010587126016616821,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0037924405187368393,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0037924405187368393
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03808434586971998,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0009995074942708015,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0009768176823854446,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0009768176823854446
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03303218260407448,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03303218260407448
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.003075838088989258,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0006342325359582901,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0024416055530309677,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0024416055530309677
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.023196437396109104,
+                                                    "count": 10,
+                                                    "is_parallel": true,
+                                                    "self": 0.004153416492044926,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.01904302090406418,
+                                                            "count": 40,
+                                                            "is_parallel": true,
+                                                            "self": 0.01904302090406418
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1362.5931184776127,
+                                                    "count": 81805,
+                                                    "is_parallel": true,
+                                                    "self": 75.36137645505369,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 69.51651999168098,
+                                                            "count": 81805,
+                                                            "is_parallel": true,
+                                                            "self": 69.51651999168098
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 966.9044259414077,
+                                                            "count": 81805,
+                                                            "is_parallel": true,
+                                                            "self": 966.9044259414077
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 250.8107960894704,
+                                                            "count": 163610,
+                                                            "is_parallel": true,
+                                                            "self": 48.64048096444458,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 202.1703151250258,
+                                                                    "count": 654440,
+                                                                    "is_parallel": true,
+                                                                    "self": 202.1703151250258
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 3757.565494815819,
+                            "count": 81806,
+                            "self": 14.944533129222691,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 732.2951598260552,
+                                    "count": 81806,
+                                    "self": 731.1832850882784,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.111874737776816,
+                                            "count": 3,
+                                            "self": 1.111874737776816
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 3010.325801860541,
+                                    "count": 56,
+                                    "self": 311.6489906795323,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 2698.676811181009,
+                                            "count": 1680,
+                                            "self": 2698.676811181009
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.2880191206932068e-06,
+                    "count": 1,
+                    "self": 1.2880191206932068e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.44065924268215895,
+                    "count": 1,
+                    "self": 0.002393142320215702,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.43826610036194324,
+                            "count": 1,
+                            "self": 0.43826610036194324
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "elo": 1607.738222426615,
+        "checkpoints": [
+            {
+                "steps": 8828448,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8828448.onnx",
+                "reward": 0.0,
+                "creation_time": 1675411523.2416048,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8828448.pt"
+                ]
+            },
+            {
+                "steps": 8999826,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8999826.onnx",
+                "reward": 0.0,
+                "creation_time": 1675428998.7213228,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8999826.pt"
+                ]
+            },
+            {
+                "steps": 9499977,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9499977.onnx",
+                "reward": 0.0,
+                "creation_time": 1675431539.3526874,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9499977.pt"
+                ]
+            },
+            {
+                "steps": 9999984,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9999984.onnx",
+                "reward": 0.0,
+                "creation_time": 1675434083.8057358,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9999984.pt"
+                ]
+            },
+            {
+                "steps": 10000022,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-10000022.onnx",
+                "reward": 0.0,
+                "creation_time": 1675434084.2867641,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-10000022.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 10000022,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1675434084.2867641,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-10000022.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.8.1+cu102"
+    }
+}