Upload folder using huggingface_hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 4.60 +/- 4.40
+      value: 4.92 +/- 4.22
       name: Mean Reward
       verified: false
 ---
@@ -26,4 +26,4 @@ model-index:
 
 This is a **REINFORCE** agent trained on **Pixelcopter (PLE)** using a custom environment wrapper.
 
-**Mean reward:** 4.60 ± 4.40
+**Mean reward:** 4.92 ± 4.22

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 15000, "n_evaluation_episodes": 30, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 576, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 15000, "n_evaluation_episodes": 50, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 576, "action_space": 2}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a761dbc76843005d089d8b1e292b61cbe7622c4c2c26031afd030f97047a8f
+oid sha256:7ca8873280347ee5b70f94442a4b36952d9cfb130338713885a1edf29ff63f46
 size 185725

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 4.6, "std_reward": 4.40151489073175, "n_evaluation_episodes": 30, "eval_datetime": "2025-12-27T12:46:23.673290"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 4.92, "std_reward": 4.222984726470131, "n_evaluation_episodes": 50, "eval_datetime": "2025-12-27T13:15:52.864371"}