First Push

README.md

@@ -0,0 +1,29 @@
+---
+library_name: ml-agents
+tags:
+- SnowballTarget
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SnowballTarget
+---
+
+  # **ppo** Agent playing **SnowballTarget**
+  This is a trained model of a **ppo** agent playing **SnowballTarget** 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-SnowballTarget
+  2. Step 1: Find your model_id: sonny-dev/ppo-SnowballTargetTESTCOLAB
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -0,0 +1 @@
+{"behaviors": {"SnowballTarget": {"trainer_type": "ppo", "summary_freq": 10000, "keep_checkpoints": 10, "checkpoint_interval": 50000, "max_steps": 200000, "time_horizon": 64, "threaded": true, "hyperparameters": {"learning_rate": 0.0003, "learning_rate_schedule": "linear", "batch_size": 128, "buffer_size": 2048, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3}, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple"}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0}}}}}

configuration.yaml

@@ -0,0 +1,27 @@
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    summary_freq: 10000
+    keep_checkpoints: 10
+    checkpoint_interval: 50000
+    max_steps: 200000
+    time_horizon: 64
+    threaded: true
+    hyperparameters:
+      learning_rate: 0.0003
+      learning_rate_schedule: linear
+      batch_size: 128
+      buffer_size: 2048
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0