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: nikxtaco/ppo-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 sha256:9a6ac3d8b57c13258e47e0f2c2966159588c6465f9aecb74c5e36241bd4ff5a3
+size 1768747

SoccerTwos/SoccerTwos-0.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e085554ba521636bcf6ea64da1596029077ff7b77d23699a47cdf408d5b5101
+size 1766874

SoccerTwos/SoccerTwos-0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed13be3789b3dadcf67f9a49e88213b9854bf5030241efce00b1e2c1414903e6
+size 9479282

SoccerTwos/SoccerTwos-50216.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a6ac3d8b57c13258e47e0f2c2966159588c6465f9aecb74c5e36241bd4ff5a3
+size 1768747

SoccerTwos/SoccerTwos-50216.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42795b8a596a2e9374cb80a547d02a815c524112490ef40d9f5300aa88dcd48b
+size 28430110

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daae02f95aef88d1154cd696e1494bc837f1cfa9bf96f98315cff610be27322d
+size 28429366

SoccerTwos/events.out.tfevents.1699862561.135cd06775b2.6898.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:040f7d195c360b50b32c146fb44aad769fd1f351151937d1d7300b078d4401d8
+size 1238

SoccerTwos/events.out.tfevents.1699862603.135cd06775b2.7117.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c0d3fcf0bc4f5beb97cdc2b925e7a3cc6caeeb47ba88ed9715379b00dd5c37
+size 47295

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": 50000, "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/linux/SoccerTwos/SoccerTwos/SoccerTwos", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos2", "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 +1,83 @@
+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: 50000
+    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/linux/SoccerTwos/SoccerTwos/SoccerTwos
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos2
+  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 +1,291 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SoccerTwos/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/SoccerTwos/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 /content/ml-agents/training-envs-executables/linux/SoccerTwos/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
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.104 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: 0.834650 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
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+Setting up 1 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]: 1095 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 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 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]
+      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]
+      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_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 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 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 4
+    [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]: 1096 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]: 1096 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.6 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]: 1095 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]: 1096 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]: 1096 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]: 1095 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]: 1096 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]: 1095 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 +1,403 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 3.2812230587005615,
+            "min": 3.2812230587005615,
+            "max": 3.295708656311035,
+            "count": 5
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 70559.421875,
+            "min": 15777.21875,
+            "max": 105462.6796875,
+            "count": 5
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 717.4285714285714,
+            "min": 623.5714285714286,
+            "max": 995.0,
+            "count": 5
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 20088.0,
+            "min": 14204.0,
+            "max": 28652.0,
+            "count": 5
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1200.105955145682,
+            "min": 1198.9373468557678,
+            "max": 1200.9769858473817,
+            "count": 5
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 7200.635730874092,
+            "min": 2400.056872686747,
+            "max": 12009.769858473817,
+            "count": 5
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 49822.0,
+            "min": 9342.0,
+            "max": 49822.0,
+            "count": 5
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 49822.0,
+            "min": 9342.0,
+            "max": 49822.0,
+            "count": 5
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.07366155833005905,
+            "min": -0.1015477403998375,
+            "max": -0.07366155833005905,
+            "count": 5
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.9576002955436707,
+            "min": -1.3201180696487427,
+            "max": -0.8542187809944153,
+            "count": 5
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.07048321515321732,
+            "min": -0.10155700147151947,
+            "max": -0.07048321515321732,
+            "count": 5
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.9162818193435669,
+            "min": -1.3202409744262695,
+            "max": -0.8557853102684021,
+            "count": 5
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 5
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 5
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.05258461145254282,
+            "min": -0.3301090896129608,
+            "max": -0.05258461145254282,
+            "count": 5
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -0.6835999488830566,
+            "min": -3.631199985742569,
+            "max": -0.6835999488830566,
+            "count": 5
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.05258461145254282,
+            "min": -0.3301090896129608,
+            "max": -0.05258461145254282,
+            "count": 5
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -0.6835999488830566,
+            "min": -3.631199985742569,
+            "max": -0.6835999488830566,
+            "count": 5
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 5
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 5
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01506708687520586,
+            "min": 0.01506708687520586,
+            "max": 0.01566864464257378,
+            "count": 2
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01506708687520586,
+            "min": 0.01506708687520586,
+            "max": 0.01566864464257378,
+            "count": 2
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.0036884615282443437,
+            "min": 0.003062593149176488,
+            "max": 0.0036884615282443437,
+            "count": 2
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.0036884615282443437,
+            "min": 0.003062593149176488,
+            "max": 0.0036884615282443437,
+            "count": 2
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.003729660508476875,
+            "min": 0.0026367754287396866,
+            "max": 0.003729660508476875,
+            "count": 2
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.003729660508476875,
+            "min": 0.0026367754287396866,
+            "max": 0.003729660508476875,
+            "count": 2
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 2
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 2
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.2,
+            "min": 0.2,
+            "max": 0.20000000000000007,
+            "count": 2
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.2,
+            "min": 0.2,
+            "max": 0.20000000000000007,
+            "count": 2
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 2
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 2
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1699862602",
+        "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --resume --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos/SoccerTwos --run-id=SoccerTwos2 --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.0+cu118",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1699862869"
+    },
+    "total": 266.84529422700007,
+    "count": 1,
+    "self": 0.47672217900026226,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05492019099983736,
+            "count": 1,
+            "self": 0.05492019099983736
+        },
+        "TrainerController.start_learning": {
+            "total": 266.31365185699997,
+            "count": 1,
+            "self": 0.13312792999431622,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.3484470980001788,
+                    "count": 1,
+                    "self": 1.3484470980001788
+                },
+                "TrainerController.advance": {
+                    "total": 264.6316215560055,
+                    "count": 3670,
+                    "self": 0.16579634501886176,
+                    "children": {
+                        "env_step": {
+                            "total": 123.00177471899633,
+                            "count": 3670,
+                            "self": 100.1245651079953,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 22.792715752999584,
+                                    "count": 3670,
+                                    "self": 0.8397715250212059,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 21.952944227978378,
+                                            "count": 7304,
+                                            "self": 21.952944227978378
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.08449385800145137,
+                                    "count": 3670,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 265.61760057600327,
+                                            "count": 3670,
+                                            "is_parallel": true,
+                                            "self": 182.17596656100454,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.003117426999779127,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0008162530002664425,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0023011739995126845,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0023011739995126845
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.04634818399995311,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0013344429996777762,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0009126159998231742,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0009126159998231742
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.04008600200018009,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.04008600200018009
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0040151230002720695,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0007105310005499632,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0033045919997221063,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0033045919997221063
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 83.44163401499873,
+                                                    "count": 3669,
+                                                    "is_parallel": true,
+                                                    "self": 5.154427128979933,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 3.0319108860080632,
+                                                            "count": 3669,
+                                                            "is_parallel": true,
+                                                            "self": 3.0319108860080632
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 59.40444901599835,
+                                                            "count": 3669,
+                                                            "is_parallel": true,
+                                                            "self": 59.40444901599835
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 15.850846984012378,
+                                                            "count": 7338,
+                                                            "is_parallel": true,
+                                                            "self": 2.7187540600293687,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 13.13209292398301,
+                                                                    "count": 29352,
+                                                                    "is_parallel": true,
+                                                                    "self": 13.13209292398301
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 141.4640504919903,
+                            "count": 3670,
+                            "self": 1.07506253899669,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 20.72282923399348,
+                                    "count": 3670,
+                                    "self": 20.72282923399348
+                                },
+                                "_update_policy": {
+                                    "total": 119.66615871900012,
+                                    "count": 2,
+                                    "self": 9.33598303000008,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 110.33017568900004,
+                                            "count": 63,
+                                            "self": 110.33017568900004
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.0399999155197293e-06,
+                    "count": 1,
+                    "self": 1.0399999155197293e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.20045423300007315,
+                    "count": 1,
+                    "self": 0.0028815390001000196,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.19757269399997313,
+                            "count": 1,
+                            "self": 0.19757269399997313
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,39 @@
+{
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.1.0+cu118"
+    },
+    "SoccerTwos": {
+        "elo": 1200.02237050593,
+        "checkpoints": [
+            {
+                "steps": 0,
+                "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-0.onnx",
+                "reward": null,
+                "creation_time": 1699862562.700575,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos2/SoccerTwos/SoccerTwos-0.pt"
+                ]
+            },
+            {
+                "steps": 50216,
+                "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-50216.onnx",
+                "reward": 0.0,
+                "creation_time": 1699862869.048925,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos2/SoccerTwos/SoccerTwos-50216.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 50216,
+            "file_path": "results/SoccerTwos2/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1699862869.048925,
+            "auxillary_file_paths": [
+                "results/SoccerTwos2/SoccerTwos/SoccerTwos-50216.pt"
+            ]
+        }
+    }
+}