Atari model with DQN architecture

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- SpaceInvadersNoFrameskip-v4
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DQN
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: SpaceInvadersNoFrameskip-v4
+      type: SpaceInvadersNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 720.50 +/- 381.66
+      name: mean_reward
+      verified: false
+---
+
+# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
+This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
+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
+
+...
+```

atari-test.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a39cd908e9dd0194eb00f3d9ca38fc8b4c539959ed700e2f50efdd0e87d6146
+size 27482793

atari-test/_stable_baselines3_version

@@ -0,0 +1 @@
+2.4.1

atari-test/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497892f12e908bb7cd6609aec5e076bfd4efea88f64f3dc29b284212f4d0623d
+size 13505852

atari-test/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:324c49a01123cae9558989c19f2b9ea31a8e74ff2ba3d338544ef14ac21cb063
+size 13505178

atari-test/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebdad4b9cfe9cd22a3abadb5623bf7bb1f6eb2e408740245eb3f2044b0adc018
+size 864

atari-test/system_info.txt

@@ -0,0 +1,9 @@
+- OS: macOS-14.6.1-arm64-arm-64bit Darwin Kernel Version 23.6.0: Mon Jul 29 21:16:46 PDT 2024; root:xnu-10063.141.2~1/RELEASE_ARM64_T8112
+- Python: 3.10.16
+- Stable-Baselines3: 2.4.1
+- PyTorch: 2.5.1
+- GPU Enabled: False
+- Numpy: 1.26.4
+- Cloudpickle: 3.1.1
+- Gymnasium: 1.0.0
+- OpenAI Gym: 0.26.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 720.5, "std_reward": 381.6572415139008, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-01-28T11:21:47.421199"}