Upload folder using huggingface_hub

README.md

@@ -6,7 +6,7 @@ tags:
 - custom-implementation
 - deep-rl-class
 model-index:
-- name: Reinforce-PixelCopter
+- name: Reinforce-Pixelcopter
   results:
   - task:
       type: reinforcement-learning
@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 14.60 +/- 15.55
+      value: 25.80 +/- 16.86
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 10000, "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": 25000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "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:f6420759a7b0cd7513011c69dd22e8bbb7e8e1bfceedc7dbb7f0da4de6f341b5
+oid sha256:2a06041f970c3b42c75d78d7ea626858603cbd6a3e87e6d02645e2a48982ff0d
 size 39732

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 14.6, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-29T02:41:52.608182"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 25.8, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-29T05:43:19.759153"}