Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.48 +/- 2.74
+      value: 7.56 +/- 2.71
       name: mean_reward
     task:
       type: reinforcement-learning

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d30109646e9ae895e93821e2840377c008d4470f0a022033153877e854a25091
+oid sha256:101bfb44823d06cda9f69035488ce4cbfac69e9ae133959c3234ee9b034eff1c
 size 24589

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:992ffa961a00ec9a2e4d8bb5dc168da3f99e5a50d6455c9faabac4e71dbbabb5
-size 125260
+oid sha256:be74e6749812f8f05553dc124752cb28b233e18bb2b3c0223fa091fa322c1374
+size 109078

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.48, "n_eval_episodes": 100, "eval_datetime": "2022-08-09T08:56:21.870705"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-08-09T08:57:37.191943"}