Upload folder using huggingface_hub

README.md

@@ -1,22 +1,21 @@
 ---
-library_name: stable-baselines3
 tags:
-- LunarLander-v2
-- deep-reinforcement-learning
+- FrozenLake-v1-4x4-no_slippery
+- q-learning
 - reinforcement-learning
-- stable-baselines3
+- custom-implementation
 model-index:
-- name: PPO
+- name: feb-learn
   results:
   - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: LunarLander-v2
-      type: LunarLander-v2
+      name: FrozenLake-v1-4x4-no_slippery
+      type: FrozenLake-v1-4x4-no_slippery
     metrics:
     - type: mean_reward
-      value: 273.21 +/- 16.30
+      value: 1.00 +/- 0.00
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81eb24b7965b1cf0e496e7c343040c27c3a4284813c9d157e513dc5992cfd69d
+size 914

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ba50c27d8ff407c6595cc901636227428a3da0f9aca951062ded3986ed5e41b
-size 167536
+oid sha256:68575109feae93277e5fddb0f18cc8f0eea5597011ee71d6525e5a431d469450
+size 31168

results.json

@@ -1 +1 @@
-{"mean_reward": 273.2085935, "std_reward": 16.295759005412247, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-04T20:39:16.783647"}
+{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2025-02-05T17:12:10.702067"}