Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 195.40 +/- 57.69
+      value: 232.20 +/- 102.47
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62576b81498452fa5a8b7900a8026eea53a1b3b383354aa658de3ec810c96b7
+oid sha256:66df91cd7499d05ce4bc44d9e874d28cd4313c865a6033577dfe67e7ff04df87
 size 40129

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:552215dba08d7cb2726854623817303a1f11742dd447938a6043b5569db393d1
-size 30942
+oid sha256:c8193b09346d91be4f468e5f13116db3e504f3f2caf843f9067049791b97576b
+size 18440

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 195.4, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-02T18:31:13.867328"}
+{"env_id": "CartPole-v1", "mean_reward": 232.2, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-02T18:32:12.317106"}