Push Reinforce agent to the Hub

.gitattributes

@@ -32,3 +32,4 @@ 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: -15.96 +/- 0.72
+      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": [21, 49, 9], "n_training_episodes": 100000, "n_evaluation_episodes": 1000, "max_t": 10000, "gamma": 0.999, "lr": 0.003, "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 sha256:1131a5b7d6489395b384e2061059d7995f14cf991b4bcd88600ca10d0fefdf20
+size 10511

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca13edc1187bd75a3bd6567f5787c549a017d3ebcbdd0954fdd3d60c85c3d793
+size 15470

results.json

@@ -0,0 +1 @@
+{"env_id": "Pong-PLE-v0", "mean_reward": -15.958, "n_evaluation_episodes": 1000, "eval_datetime": "2022-11-08T23:15:27.069107"}