1st try at CNN-PPO SpaceInvaders

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,28 @@
+---
+library_name: stable-baselines3
+tags:
+- ALE/SpaceInvaders-v5
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: CNN-PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 143.50 +/- 73.04
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: ALE/SpaceInvaders-v5
+      type: ALE/SpaceInvaders-v5
+---
+
+  # **CNN-PPO** Agent playing **ALE/SpaceInvaders-v5**
+  This is a trained model of a **CNN-PPO** agent playing **ALE/SpaceInvaders-v5** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+  
+  ## Usage (with Stable-baselines3)
+  TODO: Add your code
+  

cnn-ppo-SpaceInvaders-v5.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c32b76e2f883fafa07095b749eb8b5e70120ac4041635b60191f4d147fe9e9b9
+size 141015288

cnn-ppo-SpaceInvaders-v5/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.0

cnn-ppo-SpaceInvaders-v5/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc48122acc16b70d2ee7db0ad78f23e7b629ed67202051e74ef260bb6523e0db
+size 92921565

cnn-ppo-SpaceInvaders-v5/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96174dc84bef310164e5d7be11f089338e1e2519962bfe592608bc395a76ff11
+size 46461633

cnn-ppo-SpaceInvaders-v5/pytorch_variables.pth

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

cnn-ppo-SpaceInvaders-v5/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.0-109-generic-x86_64-with-glibc2.27 #123~18.04.1-Ubuntu SMP Fri Apr 8 09:48:52 UTC 2022
+Python: 3.9.12
+Stable-Baselines3: 1.5.0
+PyTorch: 1.11.0
+GPU Enabled: True
+Numpy: 1.22.3
+Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": 143.5, "std_reward": 73.04279567486448, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-05-17T23:04:09.680275"}