First Push`

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: juanfkurucz/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 sha256:729839a37a1a5d5a9a93c7e5a9d7b4246d5247537d6424392398138c365860f5
+size 1766874

SoccerTwos/SoccerTwos-11928.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:729839a37a1a5d5a9a93c7e5a9d7b4246d5247537d6424392398138c365860f5
+size 1766874

SoccerTwos/SoccerTwos-11928.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6f92b72cb563be5e420fd60ad2dc4fe0e63767bb8a2bc9c735977e10d9b473
+size 9478991

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:795e2eb0d52a5ca9c6106e175bdd44dd6e3ef259e224a84d708016864ee14a87
+size 9478763

SoccerTwos/events.out.tfevents.1684774207.DESKTOP-KH84B4U.6160.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d553937da86f39a00438e983189742989af41d22c1eaf98447921ef8d4d7bf97
+size 11279

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": 5000, "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": ".\\\\SoccerTwos\\\\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": false, "force": true, "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: 5000
+ 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: .\\SoccerTwos\\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: false
+ force: true
+ train_model: false
+ inference: false
+ results_dir: results
+torch_settings:
+ device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,366 @@
+Mono path[0] = 'D:/Workspace/AI/huggingface/rlhf-course/ml-agents/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'D:/Workspace/AI/huggingface/rlhf-course/ml-agents/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path D:/Workspace/AI/huggingface/rlhf-course/ml-agents/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 0.059 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: 0.472100 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+Setting up 12 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]: 299 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_Job.Worker 18]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 54 B
+ Overflow Count 0
+ [ALLOC_TEMP_Loading.PreloadManager]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 67.1 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 10]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 54 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 16]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 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_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 17]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 54 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 14]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 54 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 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_AssetGarbageCollectorHelper] x 23
+ 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_Job.Worker 2]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 3]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 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_Job.Worker 20]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 54 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 11]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 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_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 0.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 21]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 54 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 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 13]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 54 B
+ Overflow Count 0
+ [ALLOC_TEMP_EnlightenWorker] x 12
+ 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 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_Job.Worker 22]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 54 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 9]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 8]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 7]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 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 10]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 54 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 15]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 54 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 12]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 54 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 19]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 54 B
+ Overflow Count 0
+ [ALLOC_TEMP_Loading.AsyncRead]
+ Initial Block Size 64.0 KB
+ Current Block Size 64.0 KB
+ Peak Allocated Bytes 309 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 0.9 MB
+ [ALLOC_DEFAULT_MAIN]
+ Peak usage frame count: [4.0 MB-8.0 MB]: 300 frames
+ Requested Block Size 16.0 MB
+ Peak Block count 1
+ Peak Allocated memory 5.2 MB
+ Peak Large allocation bytes 0 B
+ [ALLOC_DEFAULT_THREAD]
+ Peak usage frame count: [16.0 MB-32.0 MB]: 300 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]: 299 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]: 300 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]: 300 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]: 299 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]: 300 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]: 299 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 +1,277 @@
+{
+ "name": "root",
+ "gauges": {
+ "SoccerTwos.Policy.Entropy.mean": {
+ "value": 3.295736074447632,
+ "min": 3.295736074447632,
+ "max": 3.295736074447632,
+ "count": 1
+ },
+ "SoccerTwos.Policy.Entropy.sum": {
+ "value": 105463.5546875,
+ "min": 105463.5546875,
+ "max": 105463.5546875,
+ "count": 1
+ },
+ "SoccerTwos.Environment.EpisodeLength.mean": {
+ "value": 595.4,
+ "min": 595.4,
+ "max": 595.4,
+ "count": 1
+ },
+ "SoccerTwos.Environment.EpisodeLength.sum": {
+ "value": 23816.0,
+ "min": 23816.0,
+ "max": 23816.0,
+ "count": 1
+ },
+ "SoccerTwos.Self-play.ELO.mean": {
+ "value": 1199.502900161272,
+ "min": 1199.502900161272,
+ "max": 1199.502900161272,
+ "count": 1
+ },
+ "SoccerTwos.Self-play.ELO.sum": {
+ "value": 14394.034801935264,
+ "min": 14394.034801935264,
+ "max": 14394.034801935264,
+ "count": 1
+ },
+ "SoccerTwos.Step.mean": {
+ "value": 9928.0,
+ "min": 9928.0,
+ "max": 9928.0,
+ "count": 1
+ },
+ "SoccerTwos.Step.sum": {
+ "value": 9928.0,
+ "min": 9928.0,
+ "max": 9928.0,
+ "count": 1
+ },
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+ "value": -0.035124365240335464,
+ "min": -0.035124365240335464,
+ "max": -0.035124365240335464,
+ "count": 1
+ },
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+ "value": -0.6322385668754578,
+ "min": -0.6322385668754578,
+ "max": -0.6322385668754578,
+ "count": 1
+ },
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+ "value": -0.03510645404458046,
+ "min": -0.03510645404458046,
+ "max": -0.03510645404458046,
+ "count": 1
+ },
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+ "value": -0.6319161653518677,
+ "min": -0.6319161653518677,
+ "max": -0.6319161653518677,
+ "count": 1
+ },
+ "SoccerTwos.Environment.CumulativeReward.mean": {
+ "value": 0.0,
+ "min": 0.0,
+ "max": 0.0,
+ "count": 1
+ },
+ "SoccerTwos.Environment.CumulativeReward.sum": {
+ "value": 0.0,
+ "min": 0.0,
+ "max": 0.0,
+ "count": 1
+ },
+ "SoccerTwos.Policy.ExtrinsicReward.mean": {
+ "value": -0.11206666462951237,
+ "min": -0.11206666462951237,
+ "max": -0.11206666462951237,
+ "count": 1
+ },
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
+ "value": -2.0171999633312225,
+ "min": -2.0171999633312225,
+ "max": -2.0171999633312225,
+ "count": 1
+ },
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+ "value": -0.11206666462951237,
+ "min": -0.11206666462951237,
+ "max": -0.11206666462951237,
+ "count": 1
+ },
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+ "value": -2.0171999633312225,
+ "min": -2.0171999633312225,
+ "max": -2.0171999633312225,
+ "count": 1
+ },
+ "SoccerTwos.IsTraining.mean": {
+ "value": 0.0,
+ "min": 0.0,
+ "max": 0.0,
+ "count": 1
+ },
+ "SoccerTwos.IsTraining.sum": {
+ "value": 0.0,
+ "min": 0.0,
+ "max": 0.0,
+ "count": 1
+ }
+ },
+ "metadata": {
+ "timer_format_version": "0.1.0",
+ "start_time_seconds": "1684774204",
+ "python_version": "3.9.10 (tags/v3.9.10:f2f3f53, Jan 17 2022, 15:14:21) [MSC v.1929 64 bit (AMD64)]",
+ "command_line_arguments": "C:\\Users\\USUARIO\\.pyenv\\pyenv-win\\versions\\3.9.10\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=.\\\\SoccerTwos\\\\SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force",
+ "mlagents_version": "0.31.0.dev0",
+ "mlagents_envs_version": "0.31.0.dev0",
+ "communication_protocol_version": "1.5.0",
+ "pytorch_version": "1.13.0+cpu",
+ "numpy_version": "1.21.2",
+ "end_time_seconds": "1684774219"
+ },
+ "total": 15.152778699999999,
+ "count": 1,
+ "self": 0.1582077999999978,
+ "children": {
+ "run_training.setup": {
+ "total": 0.07621860000000003,
+ "count": 1,
+ "self": 0.07621860000000003
+ },
+ "TrainerController.start_learning": {
+ "total": 14.9183523,
+ "count": 1,
+ "self": 0.012909400000003401,
+ "children": {
+ "TrainerController._reset_env": {
+ "total": 2.6936434,
+ "count": 1,
+ "self": 2.6936434
+ },
+ "TrainerController.advance": {
+ "total": 12.147180199999996,
+ "count": 1004,
+ "self": 0.014211399999970453,
+ "children": {
+ "env_step": {
+ "total": 10.814022300000001,
+ "count": 1004,
+ "self": 8.711554699999976,
+ "children": {
+ "SubprocessEnvManager._take_step": {
+ "total": 2.094348800000026,
+ "count": 1004,
+ "self": 0.07127090000002223,
+ "children": {
+ "TorchPolicy.evaluate": {
+ "total": 2.0230779000000036,
+ "count": 2000,
+ "self": 2.0230779000000036
+ }
+ }
+ },
+ "workers": {
+ "total": 0.008118799999999649,
+ "count": 1004,
+ "self": 0.0,
+ "children": {
+ "worker_root": {
+ "total": 12.623107200000037,
+ "count": 1004,
+ "is_parallel": true,
+ "self": 5.335519299999998,
+ "children": {
+ "steps_from_proto": {
+ "total": 0.0010125000000000828,
+ "count": 2,
+ "is_parallel": true,
+ "self": 0.00022460000000013025,
+ "children": {
+ "_process_rank_one_or_two_observation": {
+ "total": 0.0007878999999999525,
+ "count": 8,
+ "is_parallel": true,
+ "self": 0.0007878999999999525
+ }
+ }
+ },
+ "UnityEnvironment.step": {
+ "total": 7.286575400000039,
+ "count": 1004,
+ "is_parallel": true,
+ "self": 0.29369840000002867,
+ "children": {
+ "UnityEnvironment._generate_step_input": {
+ "total": 0.19144409999999246,
+ "count": 1004,
+ "is_parallel": true,
+ "self": 0.19144409999999246
+ },
+ "communicator.exchange": {
+ "total": 5.8811339999999905,
+ "count": 1004,
+ "is_parallel": true,
+ "self": 5.8811339999999905
+ },
+ "steps_from_proto": {
+ "total": 0.9202989000000277,
+ "count": 2008,
+ "is_parallel": true,
+ "self": 0.1803979999999803,
+ "children": {
+ "_process_rank_one_or_two_observation": {
+ "total": 0.7399009000000474,
+ "count": 8032,
+ "is_parallel": true,
+ "self": 0.7399009000000474
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ },
+ "trainer_advance": {
+ "total": 1.3189465000000244,
+ "count": 1004,
+ "self": 0.07088530000000892,
+ "children": {
+ "process_trajectory": {
+ "total": 1.2480612000000155,
+ "count": 1004,
+ "self": 1.2480612000000155
+ }
+ }
+ }
+ }
+ },
+ "trainer_threads": {
+ "total": 5.00000002290335e-07,
+ "count": 1,
+ "self": 5.00000002290335e-07
+ },
+ "TrainerController._save_models": {
+ "total": 0.06461879999999809,
+ "count": 1,
+ "self": 0.001846499999999196,
+ "children": {
+ "RLTrainer._checkpoint": {
+ "total": 0.06277229999999889,
+ "count": 1,
+ "self": 0.06277229999999889
+ }
+ }
+ }
+ }
+ }
+ }
+}

run_logs/training_status.json

@@ -0,0 +1,30 @@
+{
+ "SoccerTwos": {
+ "elo": 1200.017218281153,
+ "checkpoints": [
+ {
+ "steps": 11928,
+ "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-11928.onnx",
+ "reward": 0.0,
+ "creation_time": 1684774219.3840177,
+ "auxillary_file_paths": [
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-11928.pt"
+ ]
+ }
+ ],
+ "final_checkpoint": {
+ "steps": 11928,
+ "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+ "reward": 0.0,
+ "creation_time": 1684774219.3840177,
+ "auxillary_file_paths": [
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-11928.pt"
+ ]
+ }
+ },
+ "metadata": {
+ "stats_format_version": "0.3.0",
+ "mlagents_version": "0.31.0.dev0",
+ "torch_version": "1.13.0+cpu"
+ }
+}