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:
+- Pong-PLE-v0
+- reinforce
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+model-index:
+- name: Reinforce-Pong-PLE-v0
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -16.00 +/- 0.00
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pong-PLE-v0
+      type: Pong-PLE-v0
+---
+
+      # 使用**Reinforce**智能体来玩**Pong-PLE-v0**
+      这是一个使用**Reinforce**训练有素的模型玩**Pong-PLE-v0**.
+      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": 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 sha256:28b9a67b7555f04f49829327206e542555831edcc087ecd42fd50a884fb982d1
+size 39511

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4302ef9936ac3db4fa8e6386585c9a2e7cce9e1c72a059e93167c315c4ebe017
+size 14382

results.json

@@ -0,0 +1 @@
+{"env_id": "Pong-PLE-v0", "mean_reward": -16.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-13T13:32:26.134719"}