Upload folder using huggingface_hub

README.md

@@ -6,7 +6,7 @@ tags:
 - custom-implementation
 - deep-rl-class
 model-index:
-- name: PixelCopter-v3
+- name: pixelcopter-v3
   results:
   - task:
       type: reinforcement-learning
@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 22.20 +/- 18.36
+      value: 26.10 +/- 27.97
       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": 30000, "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 sha256:37c9aaabe2d154ff373e3592c85ec4083e092ed9b7b4ff8f08b7d99c6e991b00
-size 39732
+oid sha256:2742751d71f0f9a34a81759c1b18269ee99ab41cc821514c3d1ebfbfcfc2dc35
+size 39668

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 22.2, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-20T09:51:53.378006"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 26.1, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-21T12:15:02.497288"}