Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 187.10 +/- 72.80
+      value: 195.40 +/- 57.69
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8e294257fb6e6dc6c68fc736c34dbed8647734a4d7c772f5b3fd3887905f04a
-size 42241
+oid sha256:a62576b81498452fa5a8b7900a8026eea53a1b3b383354aa658de3ec810c96b7
+size 40129

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eab2bdd00dd9f47cb45a03ca3f2cc175989d3bba20be05b6c45ba31096476db
-size 39630
+oid sha256:552215dba08d7cb2726854623817303a1f11742dd447938a6043b5569db393d1
+size 30942

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 187.1, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-02T17:58:52.328394"}
+{"env_id": "CartPole-v1", "mean_reward": 195.4, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-02T18:31:13.867328"}