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
 *.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: ppo-CartPole-v1
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 97.60 +/- 21.26
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+---
+
+  # **Reinforce** Agent playing **CartPole-v1**
+  This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
+  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": 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 sha256:0ef55fc79bde94a75eec2d6b35b2b6c31f9396a1fef031e36a4062e8055d0f7e
+size 2591

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c542ffb7f97916c453caaafe1757ba4a8a8ba9ad4dc3647a0cf92692e8e5c9
+size 13628

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 97.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-05T04:43:58.787888"}