20M steps

.DS_Store

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:736c66aa0fb3dacf50a063ce7fca629939652076fd20b2e6e94130805878c3aa
+size 6148

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+.DS_Store filter=lfs diff=lfs merge=lfs -text

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: atorre/poca-SoccerTwos-20M
+  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 sha256:59ad1e82fd700ee0bc4a1ba736648f07cfd2c92b3451a817c1ba71b39dc1fada
+size 1764633

SoccerTwos/SoccerTwos-18499882.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8785172598148fab12d65a8f400e86c2387dfd377ce8941787a6bb6d0fa1c76
+size 1764633

SoccerTwos/SoccerTwos-18499882.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:053b945a9f30831000bd1f1d057ae8e39cc5f040ce0e1c396dca8bbcf7eb635a
+size 28421201

SoccerTwos/SoccerTwos-18999960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc16fc2a6911d48a54d1868802ed634c493aea6b04dd16fa36f75c9ab1d6e396
+size 1764633

SoccerTwos/SoccerTwos-18999960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b34d75f6e2878d6a40b13e7f53a16d69d5f2057d9a5cba51e65ba4f16c54337f
+size 28421201

SoccerTwos/SoccerTwos-19499988.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5c631fe40e04a9eb51365d727431f83922654a3e87674f4f763130fa680703
+size 1764633

SoccerTwos/SoccerTwos-19499988.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c934b48b6e5c1507c63f3ee8a2ac955f750f637eb464d594ea0f31786028d5f
+size 28421201

SoccerTwos/SoccerTwos-19999964.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59ad1e82fd700ee0bc4a1ba736648f07cfd2c92b3451a817c1ba71b39dc1fada
+size 1764633

SoccerTwos/SoccerTwos-19999964.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09bf9abf01d9f239724731c7cebcda1d68256a3357287d36105f19d88a16cc65
+size 28421201

SoccerTwos/SoccerTwos-20000118.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59ad1e82fd700ee0bc4a1ba736648f07cfd2c92b3451a817c1ba71b39dc1fada
+size 1764633

SoccerTwos/SoccerTwos-20000118.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a5c1e0985e5a2e825c43ab1270d3666bb099ef18232bed099289fa36c330801
+size 28421201

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a5c1e0985e5a2e825c43ab1270d3666bb099ef18232bed099289fa36c330801
+size 28421201

SoccerTwos/events.out.tfevents.1675875266.Alessandros-MBP.fritz.box.22240.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10444ccbf3de85129fea1be8acb09a6940c87fcbbd94cfc71c4489e9441a18c1
+size 9427011

SoccerTwos/events.out.tfevents.1675929529.Alessandros-MBP.fritz.box.25179.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3f2fcdf35d91b9dbfbfb23d7f6d8904cb57fd40e4bcde5b9b6152ba3e8ab067
+size 1193

SoccerTwos/events.out.tfevents.1675929583.Alessandros-MBP.fritz.box.25192.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b9add6ef30e6d067ba86e6e4c2208eb46bd7603e1ee7550596ca2162a63056d
+size 10279003

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": 20000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 70000, "team_change": 250000, "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/SoccerTwos.app", "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: 20000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 70000
+      team_change: 250000
+      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/SoccerTwos.app
+  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 +1,287 @@
+Mono path[0] = '/Users/sasha/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/sasha/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/MonoBleedingEdge/etc'
+New input system (experimental) initialized
+Initialize engine version: 2021.3.17f1 (3e8111cac19d)
+[Subsystems] Discovering subsystems at path /Users/sasha/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/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  0.114 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: 0.897150 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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]: 188046 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 256.0 KB
+      Peak Allocated Bytes 78.8 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_OSX HID Input]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 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 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      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 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 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]: 188047 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 188047 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]: 188046 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]: 188047 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]: 188047 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]: 188046 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.4 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]: 188047 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]: 188046 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": 1.5764824151992798,
+            "min": 1.4329878091812134,
+            "max": 1.7143844366073608,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 32437.703125,
+            "min": 26598.671875,
+            "max": 39483.58203125,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 63.723684210526315,
+            "min": 39.65853658536585,
+            "max": 83.9298245614035,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19372.0,
+            "min": 18016.0,
+            "max": 21160.0,
+            "count": 1000
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1831.6654251467062,
+            "min": 1665.8446566899242,
+            "max": 1849.1948130862559,
+            "count": 1000
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 278413.14462229935,
+            "min": 200742.21848018424,
+            "max": 424643.348255108,
+            "count": 1000
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 19999964.0,
+            "min": 10009993.0,
+            "max": 19999964.0,
+            "count": 1000
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 19999964.0,
+            "min": 10009993.0,
+            "max": 19999964.0,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.012385610491037369,
+            "min": -0.12546078860759735,
+            "max": 0.10439267754554749,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -1.8949984312057495,
+            "min": -23.71208953857422,
+            "max": 17.642362594604492,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.008823879063129425,
+            "min": -0.12814757227897644,
+            "max": 0.10648775100708008,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -1.3500534296035767,
+            "min": -24.219890594482422,
+            "max": 17.996429443359375,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.04934640141094432,
+            "min": -0.42219999773161754,
+            "max": 0.2998220690365495,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 7.549999415874481,
+            "min": -59.10799968242645,
+            "max": 57.995399475097656,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.04934640141094432,
+            "min": -0.42219999773161754,
+            "max": 0.2998220690365495,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 7.549999415874481,
+            "min": -59.10799968242645,
+            "max": 57.995399475097656,
+            "count": 1000
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1000
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1000
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01566379334932814,
+            "min": 0.010678550639810661,
+            "max": 0.025296956343421093,
+            "count": 485
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01566379334932814,
+            "min": 0.010678550639810661,
+            "max": 0.025296956343421093,
+            "count": 485
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10293621495366097,
+            "min": 0.08394738659262657,
+            "max": 0.12795103788375856,
+            "count": 485
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10293621495366097,
+            "min": 0.08394738659262657,
+            "max": 0.12795103788375856,
+            "count": 485
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10428817396362623,
+            "min": 0.08583409736553828,
+            "max": 0.12964263384540875,
+            "count": 485
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10428817396362623,
+            "min": 0.08583409736553828,
+            "max": 0.12964263384540875,
+            "count": 485
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 485
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 485
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 485
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 485
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 485
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 485
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1675929581",
+        "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]",
+        "command_line_arguments": "/Users/sasha/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1675964293"
+    },
+    "total": 34713.153975744,
+    "count": 1,
+    "self": 1.1884499919979135,
+    "children": {
+        "run_training.setup": {
+            "total": 0.024261327999999915,
+            "count": 1,
+            "self": 0.024261327999999915
+        },
+        "TrainerController.start_learning": {
+            "total": 34711.941264424,
+            "count": 1,
+            "self": 17.211584158030746,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.7759898310025846,
+                    "count": 41,
+                    "self": 2.7759898310025846
+                },
+                "TrainerController.advance": {
+                    "total": 34691.753133194965,
+                    "count": 694746,
+                    "self": 17.369019368925365,
+                    "children": {
+                        "env_step": {
+                            "total": 10826.626759303184,
+                            "count": 694746,
+                            "self": 8767.138531000455,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 2048.917628187205,
+                                    "count": 694746,
+                                    "self": 81.44402606552262,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1967.4736021216825,
+                                            "count": 1253658,
+                                            "self": 1967.4736021216825
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 10.570600115524362,
+                                    "count": 694746,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 34678.73068446067,
+                                            "count": 694746,
+                                            "is_parallel": true,
+                                            "self": 27593.21355565262,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.07436059001540274,
+                                                    "count": 82,
+                                                    "is_parallel": true,
+                                                    "self": 0.01642363302297767,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.05793695699242507,
+                                                            "count": 328,
+                                                            "is_parallel": true,
+                                                            "self": 0.05793695699242507
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 7085.442768218039,
+                                                    "count": 694746,
+                                                    "is_parallel": true,
+                                                    "self": 459.360720204123,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 278.0116277030982,
+                                                            "count": 694746,
+                                                            "is_parallel": true,
+                                                            "self": 278.0116277030982
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 5166.799519090822,
+                                                            "count": 694746,
+                                                            "is_parallel": true,
+                                                            "self": 5166.799519090822
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1181.270901219996,
+                                                            "count": 1389492,
+                                                            "is_parallel": true,
+                                                            "self": 266.1426242594232,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 915.1282769605727,
+                                                                    "count": 5557968,
+                                                                    "is_parallel": true,
+                                                                    "self": 915.1282769605727
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 23847.757354522855,
+                            "count": 694746,
+                            "self": 129.15915005264833,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 3603.874626982194,
+                                    "count": 694746,
+                                    "self": 3599.5238403741896,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 4.350786608004228,
+                                            "count": 20,
+                                            "self": 4.350786608004228
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 20114.723577488014,
+                                    "count": 485,
+                                    "self": 1628.560945050216,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 18486.162632437798,
+                                            "count": 14550,
+                                            "self": 18486.162632437798
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 9.360010153613985e-07,
+                    "count": 1,
+                    "self": 9.360010153613985e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.20055630400020164,
+                    "count": 1,
+                    "self": 0.0020769100010511465,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1984793939991505,
+                            "count": 1,
+                            "self": 0.1984793939991505
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 18499882,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-18499882.onnx",
+                "reward": 0.0,
+                "creation_time": 1675959028.95423,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-18499882.pt"
+                ]
+            },
+            {
+                "steps": 18999960,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-18999960.onnx",
+                "reward": 0.0,
+                "creation_time": 1675960811.7221692,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-18999960.pt"
+                ]
+            },
+            {
+                "steps": 19499988,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-19499988.onnx",
+                "reward": 0.0,
+                "creation_time": 1675962553.576108,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-19499988.pt"
+                ]
+            },
+            {
+                "steps": 19999964,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-19999964.onnx",
+                "reward": 0.0,
+                "creation_time": 1675964292.243399,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-19999964.pt"
+                ]
+            },
+            {
+                "steps": 20000118,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-20000118.onnx",
+                "reward": 0.0,
+                "creation_time": 1675964292.489111,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-20000118.pt"
+                ]
+            }
+        ],
+        "elo": 1831.0598027086703,
+        "final_checkpoint": {
+            "steps": 20000118,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1675964292.489111,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-20000118.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0"
+    }
+}