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:
+- CartPole-v1
+- reinforce
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+model-index:
+- name: Reinforce-CartPole-v1
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 500.00 +/- 0.00
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+---
+
+      # 使用**Reinforce**智能体来玩**CartPole-v1**
+      这是一个使用**Reinforce**训练有素的模型玩**CartPole-v1**.
+      要学习使用这个模型并训练你的模型, 请查阅深度强化学习课程第5单元: https://github.com/huggingface/deep-rl-class/tree/main/unit5
+      

hyperparameters.json

@@ -0,0 +1 @@
+{"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e818a14a3a9ae03c0b9d4d1ec86d594c9d4af85ce4c8043306ad6d673f08e5
+size 2479

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000e727b3362e37e86242e42961db25ae10b6624e60ade168076c8cd907528c2
+size 83488

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 500.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-14T15:13:28.493962"}