Upload . with huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- Pixelcopter-PLE-v0
+- CartPole-v1
 - reinforce
 - reinforcement-learning
 - custom-implementation
@@ -12,16 +12,16 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: Pixelcopter-PLE-v0
-      type: Pixelcopter-PLE-v0
+      name: CartPole-v1
+      type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: -5.00 +/- 0.00
+      value: 22.20 +/- 6.32
       name: mean_reward
       verified: false
 ---
 
-  # **Reinforce** Agent playing **Pixelcopter-PLE-v0**
-  This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
+  # **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": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "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": 0.99, "lr": 0.0001, "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:c224b47a99c9ea79fed10876200e1c0bd46f593cbed8ee501943ff47cfb9c5a3
-size 38983
+oid sha256:6c651fd496de85aef6ed8e4a03d361b4d326a6e8131dbfc2742cc7046ac4f736
+size 38215

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -5.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-09T13:40:12.848179"}
+{"env_id": "CartPole-v1", "mean_reward": 22.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-09T17:21:15.457691"}