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_testing
   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: 245.87 +/- 25.05
+      value: 7.50 +/- 2.70
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e56f7c8f2a491d1d7fb6d8d952a5e6ad15f3601b542ef9214c677329ba6d86
+size 24570

results.json

@@ -1 +1 @@
-{"mean_reward": 245.86760712943737, "std_reward": 25.04606971496818, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-10T16:06:37.334458"}
+{"env_id": "Taxi-v3", "mean_reward": 7.5, "n_eval_episodes": 100, "eval_datetime": "2023-01-11T20:31:02.795209"}