Upload folder using huggingface_hub

README.md

@@ -1,27 +1,27 @@
----
-tags:
-- CartPole-v1
-- reinforce
-- reinforcement-learning
-- custom-implementation
-- deep-rl-class
-model-index:
-- name: Reinforce-CartPole-v1
-  results:
-  - task:
-      type: reinforcement-learning
-      name: reinforcement-learning
-    dataset:
-      name: CartPole-v1
-      type: CartPole-v1
-    metrics:
-    - type: mean_reward
-      value: 270.70 +/- 13.73
-      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 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
+---
+tags:
+- CartPole-v1
+- reinforce
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+model-index:
+- name: Reinforce-CartPole-v1
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 500.00 +/- 0.00
+      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 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
   

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 16, "n_training_episodes": 800, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
+{"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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a9a0bc2dfd09c88e0a5cfb1078d2777e4b4deb7ac76d0185aa4197f0f702be
-size 3849
+oid sha256:bdbc4c421be60a289bd9263a20703ba621e1d7ebd2c216a7e19cf943ebd05c07
+size 3264

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 270.7, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-04T21:44:49.636469"}
+{"env_id": "CartPole-v1", "mean_reward": 500.0, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-04T21:29:08.880906"}