Clean version .v1

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: eryzml/poca-SoccerTwos-v2
+  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:dec55048464aa1ab1863a923b957d9abb4f2203192309d91dd441783ceef5e77
+size 889882

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 4096, "buffer_size": 81920, "learning_rate": 0.0005, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 256, "num_layers": 3, "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": 10, "even_checkpoints": false, "max_steps": 100000000, "time_horizon": 1000, "summary_freq": 5000, "threaded": false, "self_play": {"save_steps": 100000, "team_change": 500000, "swap_steps": 1000, "window": 10, "play_against_latest_model_ratio": 0.8, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos", "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-Push", "initialize_from": null, "load_model": false, "resume": false, "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: 4096
+            buffer_size: 81920
+            learning_rate: 0.0005
+            beta: 0.01
+            epsilon: 0.2
+            lambd: 0.95
+            num_epoch: 5
+            learning_rate_schedule: linear
+            beta_schedule: linear
+            epsilon_schedule: linear
+        checkpoint_interval: 500000
+        network_settings:
+            normalize: true
+            hidden_units: 256
+            num_layers: 3
+            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: 10
+        even_checkpoints: false
+        max_steps: 100000000
+        time_horizon: 1000
+        summary_freq: 5000
+        threaded: false
+        self_play:
+            save_steps: 100000
+            team_change: 500000
+            swap_steps: 1000
+            window: 10
+            play_against_latest_model_ratio: 0.8
+            initial_elo: 1200.0
+        behavioral_cloning: null
+env_settings:
+    env_path: ./training-envs-executables/SoccerTwos
+    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-Push
+    initialize_from: null
+    load_model: false
+    resume: false
+    force: false
+    train_model: false
+    inference: false
+    results_dir: results
+torch_settings:
+    device: null
+debug: false