Upload 11 files

.gitattributes

@@ -2,34 +2,27 @@
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
-*.zst 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

@@ -1,27 +1,28 @@
 ---
+library_name: stable-baselines3
 tags:
-- doom_health_gathering_supreme
-- reinforce
+- VizdoomBasic-v0
+- deep-reinforcement-learning
 - reinforcement-learning
-- custom-implementation
-- deep-rl-class
+- stable-baselines3
 model-index:
-- name: doom_health_gathering_supreme
+- name: ppo
   results:
-  - task:
+  - metrics:
+    - type: mean_reward
+      value: -209.90 +/- 196.26
+      name: mean_reward
+    task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: doom_health_gathering_supreme
-      type: doom_health_gathering_supreme
-    metrics:
-    - type: mean_reward
-      value: 6
-      name: mean_reward
-      verified: false
+      name: VizdoomBasic-v0
+      type: VizdoomBasic-v0
 ---
 
-  # **Reinforce** Agent playing **Pixelcopter-PLE-v0**
-  This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
-  To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
+  # **ppo** Agent playing **VizdoomBasic-v0**
+  This is a trained model of a **ppo** agent playing **VizdoomBasic-v0** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+  
+  ## Usage (with Stable-baselines3)
+  TODO: Add your code
   

ppo-Doom.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03dcbe57ae05a5bb3660cff7d98df4461504b5639c0080939221b7893b511607
+size 133

ppo-Doom/_stable_baselines3_version

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

ppo-Doom/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ff81d30317e0be4a5f36a08bc9c3c0f1a877d7b7a9fecf3c9302e23f0471f43
+size 132

ppo-Doom/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5144f904b79de40add8c3bd92bc91d4416f2af5ca62a2df0944a82eae4abfdc
+size 132

ppo-Doom/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99153ed9b545f0f5af916841c8510b36c9a0a84e88f412678bced8aba994b482
+size 128

ppo-Doom/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.13.0-44-generic-x86_64-with-glibc2.17 #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
+Python: 3.8.12
+Stable-Baselines3: 1.5.0
+PyTorch: 1.10.2+cu102
+GPU Enabled: False
+Numpy: 1.22.2
+Gym: 0.23.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": -209.9, "std_reward": 196.25771322421951, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-10T14:05:28.186967"}