First Push

README.md

@@ -0,0 +1,35 @@
+---
+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://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  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. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: loweegee/ppo-SnowballTarget
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d59d9de286b99a0377ca85c10bd83245d810902c92e04d0479c0bb67da23754
+size 650646

SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dcb6e97a78d03e7b1b41d695572e9947867f9dc0567b1e388879fdf686a547b
+size 3850564

SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ddec4e26a0bcfa520051053df79ef865b936d98d3149d0bb912c2792a3fca26
+size 650646

SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8870df304e9f57fc6f700994eaa33ba816a67ece309e3578aa61918bb78b3b85
+size 3850564

SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ddec4e26a0bcfa520051053df79ef865b936d98d3149d0bb912c2792a3fca26
+size 650646

SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4e74468ff5c973222be8481502a3b0885f4976f872c6cbea98414cfc3ac380
+size 3850564

SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ea4234f7ede3f65841e6e7c7ada4d5c5ead65f58feab256dfe1213a4f512ba
+size 650646

SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff212f8b0ddd1a693db30d6090e5e4faefdbc128d86c45939b365dc3b2b1d02
+size 3850487

SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b5a7ec34c451972c6101c24ddd0a7667c3cafc97c83cb06b2c37d996505b458
+size 650646

SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90eefe5ad2f1bbb1ed883cc3d94e2c668b98e8333fdb71bb89e583e587d9de76
+size 3850487

checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9433fc5ef2fc0f2eae383ba1919524aff1c58839846981d06daf4ec651f3768c
+size 3849717

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": false, "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 +1,28 @@
+
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    summary_freq: 10000
+    keep_checkpoints: 10
+    checkpoint_interval: 50000
+    max_steps: 200000
+    time_horizon: 64
+    threaded: false
+    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

events.out.tfevents.1754742807.4bb2f574431d.4166.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3b541eb23daa832242452d42ec90133abb9c550c8cd76cee9df3036e4818f2
+size 24071