joshkaura
/

Reinforce-Pixelcopter-PLE-v0

Reinforcement Learning

Pixelcopter-PLE-v0

custom-implementation

Eval Results (legacy)

Model card Files Files and versions

joshkaura commited on Jan 7

Commit

7925932

·

verified ·

1 Parent(s): 1c9c963

Upload folder using huggingface_hub

Files changed (2) hide show

README.md +1 -1
results.json +3 -3

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 20.70 +/- 19.87
       name: mean_reward
       verified: false
 ---

       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
+      value: 29.50 +/- 21.85
       name: mean_reward
       verified: false
 ---

results.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "env_id": "Pixelcopter-PLE-v0",
-  "mean_reward": 20.7,
-  "std_reward": 19.874858490062262,
   "n_evaluation_episodes": 10,
-  "eval_datetime": "2026-01-07T02:14:15.078825"
 }

 {
   "env_id": "Pixelcopter-PLE-v0",
+  "mean_reward": 29.5,
+  "std_reward": 4.673976067006921,
   "n_evaluation_episodes": 10,
+  "eval_datetime": "2026-01-07T02:16:09.258165"
 }