Upload . with huggingface_hub

README.md

@@ -1,22 +1,21 @@
 ---
-library_name: stable-baselines3
 tags:
-- LunarLander-v2
-- deep-reinforcement-learning
+- Taxi-v3
+- 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: Taxi-v3
+      type: Taxi-v3
     metrics:
     - type: mean_reward
-      value: 269.58 +/- 18.32
+      value: 7.54 +/- 2.73
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d2fccae03c55e42ded15fa07e2a22b4cd6d19ee6974584c3a9f9743990aa82
+size 24570

results.json

@@ -1 +1 @@
-{"mean_reward": 269.5755952246484, "std_reward": 18.31695443947034, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-17T06:18:13.250973"}
+{"env_id": "Taxi-v3", "mean_reward": 7.54, "n_eval_episodes": 100, "eval_datetime": "2022-12-19T05:02:56.429131"}