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

SoccerTwos-0.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf742731623aeaf819b023f3f50316f78e22acace8374e7e21af1b206154521
+size 1764633

SoccerTwos-0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ba079cd3afb0453fdf12e6542450a71549721c2fcb1d372ee3098ee07145c57
+size 9478265

SoccerTwos-21999910.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6ad9be438bc6c69130ff548d3706af05b7fc3c80a5f0b9b0ae80607de406ec
+size 1764633

SoccerTwos-21999910.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6982fb5ed122a2b980ac05a4e90003d09fe1813c878a616a97350b8722ba4f20
+size 28421201

SoccerTwos-22499978.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6459dc1e42613136ddd555ccb00757f303f311fc9084ad31c8e2e8c5c96d142a
+size 1764633

SoccerTwos-22499978.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e76501be6c847a8d207c5fe3dc11af5feb3548882b365ade51179bfba3edfe98
+size 28421201

SoccerTwos-22999976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a625e32f342d0d61f2a7d156a9c6f89c8a4be4b89ea61bec4ed670e010234c1
+size 1764633

SoccerTwos-22999976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c4e821efb09dcdf317ba27a76d384a18b45cd071a2354086e527181be53de4
+size 28421201

SoccerTwos-23499934.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f772c6ef6e6061c82db9d1e671a87b49bc0e76a61f7e33f115e689d34afe06
+size 1764633

SoccerTwos-23499934.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34225dbb7a1fdc58173faef4fe9b1d826950a9b7f226cda8d4e5617711ec96f9
+size 28421201

SoccerTwos-23823452.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a945cab5b280f44e1e63cd776e98bf0cd347912a32ad56ea011bedea915ca9
+size 1764633

SoccerTwos-23823452.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43564944881e1ef2ebca48a5121b8e0184b2e22349c777cbac20b18f11f0dd9
+size 28421201

checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43564944881e1ef2ebca48a5121b8e0184b2e22349c777cbac20b18f11f0dd9
+size 28421201

config.json

@@ -0,0 +1 @@
+{"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"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple"}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0}}, "keep_checkpoints": 5, "max_steps": 5000000, "time_horizon": 1000, "summary_freq": 10000, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}}}}

configuration.yaml

@@ -0,0 +1,32 @@
+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
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 5000000
+    time_horizon: 1000
+    summary_freq: 10000
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0

events.out.tfevents.1676975040.Graemes-MacBook-Pro.local.83778.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df24b17f16396ad5c260c83997bf64d317dead79749562f639255acde4c22fce
+size 24117420