Push Reinforce agent to the Hub

.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 +1,26 @@
+---
+tags:
+- Pixelcopter-PLE-v0
+- reinforce
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+model-index:
+- name: Reinforce-pix-5
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 20.30 +/- 17.44
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pixelcopter-PLE-v0
+      type: Pixelcopter-PLE-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 5 of the Deep Reinforcement Learning Class: https://github.com/huggingface/deep-rl-class/tree/main/unit5
+  

hyperparameters.json

@@ -0,0 +1 @@
+{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e8b306ab1cc9d8a97417e4454a0d0b6628d6f38d95770955fb300f776ef1d7
+size 4703

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a4d4eaaa46fe58fdb9a8962aecff20cf3ed8e91dc18c3bf2eb27087de24b09
+size 11265

results.json

@@ -0,0 +1 @@
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 20.3, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-12T23:21:36.008715"}