Reinforce-PongPolGrad-2200 training episodes

.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:
+- CartPole-v1
+- reinforce
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+model-index:
+- name: Reinforce-PongPolicyGradient
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 9.38 +/- 0.62
+      name: mean_reward
+      verified: false
+---
+
+  # **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": 64, "n_training_episodes": 2200, "n_evaluation_episodes": 13, "max_t": 5000, "gamma": 0.96, "lr": 0.1, "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 sha256:2fd52b3f849488df92070f4ccc83e1fdce79fd015dc50413ca406876558efd2e
+size 3935

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:615a8cd629d0ac2456597c0f3938820d8b37931db4c8eb3823cccd49436ee0b3
+size 3197

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 9.384615384615385, "n_evaluation_episodes": 13, "eval_datetime": "2022-08-28T17:35:31.638934"}