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: YoneShiro/poca-SoccerTwos
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SoccerTwos.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b898bfaffa232f24f20bbee1ef5e3c2d43ca6f05ce91e4cd25c0e1a468da1025
+size 1768746

SoccerTwos/SoccerTwos-335890.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23df6753e137e0283e826bb6c4f0b7f2a901a0d76562da5d7e055227c07e72bd
+size 28431445

SoccerTwos/SoccerTwos-3499979.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe522f2a8fa7858b85d1c63a5fb8d0295192db3181729a97ad7be1bce6cfb722
+size 1768746

SoccerTwos/SoccerTwos-3499979.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:723cc67cd80148f106581b92847942b1a586d57ba69562ff951ce93a916e721d
+size 28431567

SoccerTwos/SoccerTwos-3999961.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d3e817b52764e8970aa3b2301572251c6d77250033695bf58e36cc65f8805c
+size 1768746

SoccerTwos/SoccerTwos-3999961.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ad5140e72ab17e6401a64f83620060fb23c6e9e46cfaa48acd798c8686bb79
+size 28431567

SoccerTwos/SoccerTwos-4499921.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc62817f453501dc23edd1b38c380552576df96b178663c20d53eb8115d47186
+size 1768746

SoccerTwos/SoccerTwos-4499921.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de38dda9282f43431e38f2a44a2ecf403fb0d17d401efaa011adabcf1cc1c540
+size 28431567

SoccerTwos/SoccerTwos-4999966.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b898bfaffa232f24f20bbee1ef5e3c2d43ca6f05ce91e4cd25c0e1a468da1025
+size 1768746

SoccerTwos/SoccerTwos-4999966.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5312c66a1dac1427f54b4c3e78be98f631bed06987c49e09a1f74023023db63b
+size 28431567

SoccerTwos/SoccerTwos-5000023.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b898bfaffa232f24f20bbee1ef5e3c2d43ca6f05ce91e4cd25c0e1a468da1025
+size 1768746

SoccerTwos/SoccerTwos-5000023.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41fbe1132aa4ae7063009b02f5178ee082ceaa224d557438c01c2e3d41db7956
+size 28431567

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3ef7670a2dfd436effbbb44d11282edbfb9af2b633b1402021466dc3aee4d6
+size 28430591

SoccerTwos/events.out.tfevents.1688117852.DESKTOP-3OP9PGV.944.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad6290950a42faa1fd83730749774a03ae9d06964ebec4a233683456f9f4a51e
+size 1240

SoccerTwos/events.out.tfevents.1688117925.DESKTOP-3OP9PGV.5132.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:796faa38c20e83f25b05140f6205fb02d35cc0bee9ebfd8393624800cb58b1d7
+size 255752

SoccerTwos/events.out.tfevents.1688118880.DESKTOP-3OP9PGV.8068.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975e33554c337a065e374c3e5188f3214637bca4ad773345bec156a0c04c01ce
+size 79907

SoccerTwos/events.out.tfevents.1688119109.DESKTOP-3OP9PGV.8088.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d328733f2f90327ddfe4a093a0368fb4f9b398feb034081d29265492d5de5d
+size 190658

SoccerTwos/events.out.tfevents.1688119874.DESKTOP-3OP9PGV.13908.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a689435a6b1e09221b9f03e21c6e36acf9a5deb21c8037652de1354dc8c1c0a6
+size 89026

SoccerTwos/events.out.tfevents.1688120656.DESKTOP-3OP9PGV.11120.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4583cccf4844cc5e61aeca17da5d744479b874736d805e43e8a609b102713a
+size 1347063

SoccerTwos/events.out.tfevents.1688136085.DESKTOP-3OP9PGV.5692.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a5cab7c0775f817b1e418a9b7344c8f864f3cdb086bf2cf7a6377b414fd668
+size 1645482

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": 5000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cuda"}, "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: 5000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos.exe
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: cuda
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,252 @@
+Mono path[0] = 'C:/Users/gava_/Documents/rl_hugging_face/rl_7/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/Users/gava_/Documents/rl_hugging_face/rl_7/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/Users/gava_/Documents/rl_hugging_face/rl_7/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.116 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard (Specular setup) shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.650700 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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]: 29943 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 405 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 68.0 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 2
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 29944 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.3 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 29944 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.0 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 29943 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]: 29944 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.6 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 2
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 29944 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]: 29943 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.2 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 29944 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]: 29943 frames, [2.0 KB-4.0 KB]: 1 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 2.277820587158203,
+            "min": 2.233041763305664,
+            "max": 2.971186637878418,
+            "count": 160
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 43588.375,
+            "min": 18071.310546875,
+            "max": 65700.578125,
+            "count": 160
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 75.64615384615385,
+            "min": 52.75555555555555,
+            "max": 156.96875,
+            "count": 160
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19668.0,
+            "min": 2788.0,
+            "max": 21592.0,
+            "count": 160
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1548.0452403303507,
+            "min": 1303.0682328106807,
+            "max": 1560.847477448936,
+            "count": 160
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 201245.8812429456,
+            "min": 21029.240688677917,
+            "max": 281108.6245172949,
+            "count": 160
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 4999966.0,
+            "min": 3409917.0,
+            "max": 4999966.0,
+            "count": 160
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 4999966.0,
+            "min": 3409917.0,
+            "max": 4999966.0,
+            "count": 160
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.07828344404697418,
+            "min": -0.025616463273763657,
+            "max": 0.206451416015625,
+            "count": 160
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 10.176847457885742,
+            "min": -3.7143871784210205,
+            "max": 28.49029541015625,
+            "count": 160
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.07244706898927689,
+            "min": -0.02666577138006687,
+            "max": 0.20727582275867462,
+            "count": 160
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 9.418119430541992,
+            "min": -3.866536855697632,
+            "max": 28.604063034057617,
+            "count": 160
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 160
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 160
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.1599061553294842,
+            "min": -0.2795611106687122,
+            "max": 0.47410973405416035,
+            "count": 160
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 20.787800192832947,
+            "min": -38.73800003528595,
+            "max": 53.57439994812012,
+            "count": 160
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.1599061553294842,
+            "min": -0.2795611106687122,
+            "max": 0.47410973405416035,
+            "count": 160
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 20.787800192832947,
+            "min": -38.73800003528595,
+            "max": 53.57439994812012,
+            "count": 160
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 160
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 160
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.016362083276423314,
+            "min": 0.012747406342532486,
+            "max": 0.021592475559252002,
+            "count": 77
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.016362083276423314,
+            "min": 0.012747406342532486,
+            "max": 0.021592475559252002,
+            "count": 77
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.08703848247726759,
+            "min": 0.043512505541245146,
+            "max": 0.09584195911884308,
+            "count": 77
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.08703848247726759,
+            "min": 0.043512505541245146,
+            "max": 0.09584195911884308,
+            "count": 77
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.08898836001753807,
+            "min": 0.04558493693669637,
+            "max": 0.09694288621346156,
+            "count": 77
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.08898836001753807,
+            "min": 0.04558493693669637,
+            "max": 0.09694288621346156,
+            "count": 77
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 77
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 77
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 77
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 77
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 77
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 77
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1688136081",
+        "python_version": "3.9.16 (main, May 17 2023, 17:49:16) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\gava_\\miniconda3\\envs\\rl_7\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --torch-device=cuda --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.0.1+cu118",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1688139308"
+    },
+    "total": 3226.9689866,
+    "count": 1,
+    "self": 2.2630827999996654,
+    "children": {
+        "run_training.setup": {
+            "total": 0.1483901999999997,
+            "count": 1,
+            "self": 0.1483901999999997
+        },
+        "TrainerController.start_learning": {
+            "total": 3224.5575136,
+            "count": 1,
+            "self": 2.6613024000321275,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 10.684930699999972,
+                    "count": 9,
+                    "self": 10.684930699999972
+                },
+                "TrainerController.advance": {
+                    "total": 3210.9817783999683,
+                    "count": 108296,
+                    "self": 2.7155326000065543,
+                    "children": {
+                        "env_step": {
+                            "total": 2242.4152754999836,
+                            "count": 108296,
+                            "self": 1249.9930535000467,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 990.8399423999942,
+                                    "count": 108296,
+                                    "self": 20.11214710002855,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 970.7277952999657,
+                                            "count": 199626,
+                                            "self": 970.7277952999657
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.5822795999428223,
+                                    "count": 108296,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 3216.7188293000618,
+                                            "count": 108296,
+                                            "is_parallel": true,
+                                            "self": 2240.770959000104,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.015113399999514332,
+                                                    "count": 18,
+                                                    "is_parallel": true,
+                                                    "self": 0.0031775999996366266,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.011935799999877705,
+                                                            "count": 72,
+                                                            "is_parallel": true,
+                                                            "self": 0.011935799999877705
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 975.9327568999579,
+                                                    "count": 108296,
+                                                    "is_parallel": true,
+                                                    "self": 56.801512999965894,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 42.889611400014545,
+                                                            "count": 108296,
+                                                            "is_parallel": true,
+                                                            "self": 42.889611400014545
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 705.4799123999802,
+                                                            "count": 108296,
+                                                            "is_parallel": true,
+                                                            "self": 705.4799123999802
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 170.76172009999718,
+                                                            "count": 216592,
+                                                            "is_parallel": true,
+                                                            "self": 36.24901950005798,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 134.5127005999392,
+                                                                    "count": 866368,
+                                                                    "is_parallel": true,
+                                                                    "self": 134.5127005999392
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 965.8509702999783,
+                            "count": 108296,
+                            "self": 19.738505599945142,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 446.5538022000351,
+                                    "count": 108296,
+                                    "self": 445.04256160003484,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.5112406000002352,
+                                            "count": 4,
+                                            "self": 1.5112406000002352
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 499.558662499998,
+                                    "count": 77,
+                                    "self": 271.1019353000052,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 228.45672719999277,
+                                            "count": 2310,
+                                            "self": 228.45672719999277
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 2.000000222324161e-06,
+                    "count": 1,
+                    "self": 2.000000222324161e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.22950009999976828,
+                    "count": 1,
+                    "self": 0.017689499999505642,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.21181060000026264,
+                            "count": 1,
+                            "self": 0.21181060000026264
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.1+cu118"
+    },
+    "SoccerTwos": {
+        "elo": 1547.6843221068245,
+        "checkpoints": [
+            {
+                "steps": 3499979,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3499979.onnx",
+                "reward": 0.0,
+                "creation_time": 1688136283.5109956,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3499979.pt"
+                ]
+            },
+            {
+                "steps": 3999961,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3999961.onnx",
+                "reward": 0.0,
+                "creation_time": 1688137276.797125,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3999961.pt"
+                ]
+            },
+            {
+                "steps": 4499921,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4499921.onnx",
+                "reward": 0.0,
+                "creation_time": 1688138288.2977204,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4499921.pt"
+                ]
+            },
+            {
+                "steps": 4999966,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999966.onnx",
+                "reward": 0.0,
+                "creation_time": 1688139305.5305526,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999966.pt"
+                ]
+            },
+            {
+                "steps": 5000023,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5000023.onnx",
+                "reward": 0.0,
+                "creation_time": 1688139305.765885,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5000023.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 5000023,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1688139305.765885,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5000023.pt"
+            ]
+        }
+    }
+}