Upload folder using huggingface_hub

README.md

@@ -1,27 +1,26 @@
----
-tags:
-- Pixelcopter-PLE-v0
-- reinforce
-- reinforcement-learning
-- custom-implementation
-- deep-rl-class
-model-index:
-- name: Reinforce-PixelCopter-v0
-  results:
-  - task:
-      type: reinforcement-learning
-      name: reinforcement-learning
-    dataset:
-      name: Pixelcopter-PLE-v0
-      type: Pixelcopter-PLE-v0
-    metrics:
-    - type: mean_reward
-      value: 21.40 +/- 20.41
-      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
-  
+---
+tags:
+- Pixelcopter-PLE-v0
+- reinforce
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+model-index:
+- name: Reinforce-PixelCopter-v0
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pixelcopter-PLE-v0
+      type: Pixelcopter-PLE-v0
+    metrics:
+    - type: mean_reward
+      value: 24.90 +/- 13.08
+      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

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 20000, "gamma": 0.99, "lr": 0.0001, "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": 0.999, "lr": 0.0001, "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 sha256:6591b7809ebe2e67c1a7696b4035524540cbb29d105d79f0d1b756d44fc233e7
+oid sha256:f5d19f37953496ca5699d52369cb559af50dd23009cf24e780e293aca601fbc4
 size 39732

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 21.4, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-30T23:47:08.034994"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 24.9, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-01T14:01:01.710841"}