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: thiagoms7/poca-SoccerTwos
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SoccerTwos/SoccerTwos-7999937.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859960183f89caa3070b70c8da1a316f05f4c578d1fc740bbd9b38577bb73177
+size 1764626

SoccerTwos/SoccerTwos-7999937.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78640b120da2fb725ddb65684a66cbeacb41634cfcda1c3adf3736c0180c806f
+size 28428241

SoccerTwos/SoccerTwos-8499979.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d6f54e69026deb3e37518a8ece8b16a68ea29f5ba512fea47deb9568ac92ea
+size 1764626

SoccerTwos/SoccerTwos-8499979.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e04aeedf5143a6af5f7decacbb477ccb78b10244b15a058088ca4745b0cb4ffa
+size 28428241

SoccerTwos/SoccerTwos-8999993.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2957dda40c99aed2d81c5807d4b9d89353dbaba82535cb184d97264adaa02a64
+size 1764626

SoccerTwos/SoccerTwos-8999993.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af69be6f7149846849235241d182e7bc79fccd281819c7fd6f8ad9c8ab61995e
+size 28428241

SoccerTwos/SoccerTwos-9499973.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4421f2a00fc09270667b5c0418b05d43acf99c772a6bbb084cad3875603c61b7
+size 1764626

SoccerTwos/SoccerTwos-9499973.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66699f9d8a490a03f933e42f6853e91c714fc0119b5e3f70972d7c61236d9e0
+size 28428241

SoccerTwos/SoccerTwos-9999984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b161c67d8269e8950b2c83956d261efcf5987da5b84e75e2179b5f7ddd6f8832
+size 1764626

SoccerTwos/SoccerTwos-9999984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c636258e377cb853a51d296762a2a68fd6b94ff7857f6eadfd29f351f5366f42
+size 28428241

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c636258e377cb853a51d296762a2a68fd6b94ff7857f6eadfd29f351f5366f42
+size 28428241

SoccerTwos/events.out.tfevents.1675823346.thiago.3716.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:235c98803ca2302bc5f90a66509c8cab89ff234d9b35360036ed72b6005e6e38
+size 10388292

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": 50000000, "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: 50000000
+    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

run_logs/Player-0.log

@@ -0,0 +1,21 @@
+Mono path[0] = 'c:/Users/thiag/anaconda3/envs/unit7/Scripts/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'c:/Users/thiag/anaconda3/envs/unit7/Scripts/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path c:/Users/thiag/anaconda3/envs/unit7/Scripts/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/UnitySubsystems
+GfxDevice: creating device client; threaded=1; jobified=0
+Direct3D:
+    Version:  Direct3D 11.0 [level 11.1]
+    Renderer: NVIDIA GeForce RTX 3070 Ti (ID=0x2482)
+    Vendor:   NVIDIA
+    VRAM:     8031 MB
+    Driver:   31.0.15.2698
+Begin MonoManager ReloadAssembly
+- Completed reload, in 13.644 seconds
+<RI> Initializing input.
+New input system (experimental) initialized
+Using XInput
+<RI> Input initialized.
+<RI> Initialized touch support.
+UnloadTime: 0.603100 ms
+Registered Communicator in Agent.
+Setting up 16 worker threads for Enlighten.