Push Reinforce agent to the Hub

.gitattributes

@@ -29,3 +29,4 @@ 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
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,27 @@
+---
+tags:
+- Pong-PLE-v0
+- reinforce
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+model-index:
+- name: Reinforce-Pong-PLE-v0
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pong-PLE-v0
+      type: Pong-PLE-v0
+    metrics:
+    - type: mean_reward
+      value: -16.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+  # **Reinforce** Agent playing **Pong-PLE-v0**
+  This is a trained model of a **Reinforce** agent playing **Pong-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": 20000, "n_evaluation_episodes": 10, "max_t": 5000, "gamma": 0.99, "lr": 0.01, "env_id": "Pong-PLE-v0", "state_space": 7, "action_space": 3}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e10a2e76bff627c77c96553bfb7154db7f70f190ac130f359343c71a173d223
+size 39511

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3cf7f8288f9cb56a7cc15ff35bc4b5427032a146c2f1caf1df82eb3d96de182
+size 17095

results.json

@@ -0,0 +1 @@
+{"env_id": "Pong-PLE-v0", "mean_reward": -16.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-29T12:50:19.030330"}