Upload . with huggingface_hub

README.md

@@ -1,23 +1,23 @@
 ---
-library_name: stable-baselines3
 tags:
-- HalfCheetahBulletEnv-v0
-- deep-reinforcement-learning
+- FrozenLake-v1-4x4-no_slippery
+- q-learning
 - reinforcement-learning
-- stable-baselines3
+- custom-implementation
 model-index:
-- name: A2C
+- name: DeepRL
   results:
-  - metrics:
-    - type: mean_reward
-      value: 1609.67 +/- 949.14
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: HalfCheetahBulletEnv-v0
-      type: HalfCheetahBulletEnv-v0
+      name: FrozenLake-v1-4x4-no_slippery
+      type: FrozenLake-v1-4x4-no_slippery
+    metrics:
+    - type: mean_reward
+      value: 1.00 +/- 0.00
+      name: mean_reward
+      verified: false
 ---
 
 # **A2C** Agent playing **HalfCheetahBulletEnv-v0**

q-learning.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff91aee68fd9f454b14727929eb6b54ed916bda4dd1bb4412ff9452a603e106b
+size 914

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ecb20857032e5ce4fed7f275e033ac7f4c6f15ed8bd3880e80d01fe80ecbfa4
-size 1221555
+oid sha256:56ba66361f81e2d1dc4305e8bf921c20f263b0bc4d100906461f7c0c85364958
+size 31943

results.json

@@ -1 +1 @@
-{"mean_reward": 1609.6683122321963, "std_reward": 949.1374811506043, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-09-14T17:00:25.469478"}
+{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2023-02-27T19:36:32.762596"}