Upload . with huggingface_hub

README.md

@@ -16,12 +16,11 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -1.20 +/- 3.63
+      value: 7.30 +/- 7.59
       name: mean_reward
       verified: false
 ---
 
-        # **Reinforce** Agent playing **Pixelcopter-PLE-v0**
-        This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
-        To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
-        
+# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
+This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
+To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 1e-05, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 1e-05, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6c2081cb05f9e4d851f0a6c7b916b5e3bfb28c4279a75a69a88e242c6f21fda
+oid sha256:37c4239d90a3294160906f9fa72c840f204f3c0220d6996ed2531be2fc1b639c
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -1.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-10T12:17:01.899969"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 7.3, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-10T13:03:45.478043"}