Upload PPO LunarLander-v2 trained agent

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- CarRacing-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CarRacing-v2
+      type: CarRacing-v2
+    metrics:
+    - type: mean_reward
+      value: -58.87 +/- 2.24
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **CarRacing-v2**
+This is a trained model of a **PPO** agent playing **CarRacing-v2**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

ppo-CarRacing-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ddbe1469ab5796c25462a97637def50f0c777062e76eb0c950e7380b7db3e77
+size 43341210

ppo-CarRacing-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

ppo-CarRacing-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a90f61cba558737dc79d95d1ed4de7d14b83b5fca49079150ee7fcb5a15de72
+size 28391536

ppo-CarRacing-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cfa6939a24b2b2d4dcd4fe7e5a75f83438c125538407eef44e19f938a41b742
+size 14195070

ppo-CarRacing-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo-CarRacing-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.0.1+cu118
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4242aa7080b580259a6af0208b18d38e912c0113f0086c04d1e172372bb4e08
+size 1000612

results.json

@@ -0,0 +1 @@
+{"mean_reward": -58.86580857783556, "std_reward": 2.2430930141899466, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-05T10:45:35.544842"}