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: 12.10 +/- 10.27
+      value: 34.60 +/- 29.17
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 15000, "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": 35000, "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:f694e9c6cb898ec4bd58c7397bb55fa3403f0c22cad1b73acf331592a802a937
-size 39668
+oid sha256:39489f910f99f1453fdf6a2fba5249b64c805f47a452fa967aa6e55fd75df470
+size 39732

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 12.1, "n_evaluation_episodes": 10, "eval_datetime": "2025-04-23T13:47:16.029801"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 34.6, "n_evaluation_episodes": 10, "eval_datetime": "2025-04-28T08:31:19.235470"}