Upload PPO CarRacing-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: 386.21 +/- 195.26
+      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 sha256:05e157d497db6ad7ac0c884a7f5b1468a04b119a6e7af41c3286862dddb36d40
+size 26325617

ppo-CarRacing-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+2.3.2

ppo-CarRacing-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed3fe694d5e85f2957ba7ef2e4a9b2f00974168afcdc688c07d08aac01fbfba
+size 17415649

ppo-CarRacing-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69aedd2e4d3967551e5d111a48e64d83bff62a4d9cbe4574f24089a6b23b8fe9
+size 8709935

ppo-CarRacing-v2/pytorch_variables.pth

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

ppo-CarRacing-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: 2.3.2
+- PyTorch: 2.4.1+cu121
+- GPU Enabled: False
+- Numpy: 1.26.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.25.2

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9d29ee31a831d128584edd947f8016c56583f4aafdf12bf2ee9010fb47d257
+size 1090791

results.json

@@ -0,0 +1 @@
+{"mean_reward": 386.20921104848384, "std_reward": 195.2558510645186, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-27T14:09:21.544550"}