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: -61.24 +/- 16.86
+      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-Car-Racing-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7cc411f3fd8a405b1809ba79fe1dd62323d9cd2a6b1c94ada15879fd684e432
+size 43342537

ppo-Car-Racing-v2/_stable_baselines3_version

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

ppo-Car-Racing-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:940ac9ba2e272a36a63d7dff5977def7368a6361830bfd2b2aca361050264993
+size 28391969

ppo-Car-Racing-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30362bb570a7ec2d4b4e57678f710bd6768e9369d8518aa491adb871e1710762
+size 14195503

ppo-Car-Racing-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

ppo-Car-Racing-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.3.1+cu121
+- GPU Enabled: True
+- Numpy: 1.26.4
+- 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:fa42070ab32ac402466182797fdd9f1f244dad9e7f6fc00244bc853ccd57e918
+size 1650087

results.json

@@ -0,0 +1 @@
+{"mean_reward": -61.24201722741127, "std_reward": 16.8644908518015, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-05T14:22:27.765369"}