Upload folder using huggingface_hub

README.md

@@ -1,22 +1,21 @@
 ---
-library_name: stable-baselines3
 tags:
-- LunarLander-v2
-- deep-reinforcement-learning
+- FrozenLake-v1-4x4
+- q-learning
 - reinforcement-learning
-- stable-baselines3
+- custom-implementation
 model-index:
-- name: PPO
+- name: rl-course
   results:
   - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: LunarLander-v2
-      type: LunarLander-v2
+      name: FrozenLake-v1-4x4
+      type: FrozenLake-v1-4x4
     metrics:
     - type: mean_reward
-      value: 251.40 +/- 17.30
+      value: 0.68 +/- 0.47
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adbf06e6d4b8a8c13700469fa4877d8dd6370c206697a7cde49bf401ff52f07d
+size 904

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f20256a6defdf9d19e00b0177c0efca0b877d1d580010541f5de864cc8a236b6
-size 176147
+oid sha256:30c2f27f70d1344916321245ce6a6758611b9f788c957380a82682ce323042a3
+size 49334

results.json

@@ -1 +1 @@
-{"mean_reward": 251.3961236072701, "std_reward": 17.29719789605792, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-06-01T07:43:46.315910"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.68, "std_reward": 0.466476151587624, "n_eval_episodes": 100, "eval_datetime": "2026-06-02T07:56:12.463593"}