Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 120.60 +/- 21.70
+      value: 500.00 +/- 0.00
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9699b3e36528bf360f6263fb02d61479f5b12b33779a9753f40b0ff82bae513f
+oid sha256:e3c040fab726272319a9b3ed357cff031c1333dd28993d6cbb786fea1759de61
 size 2591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c50ec07c39bf95a2ba02db4ff35c6714ed7d47f24dc48cd62785343d48197e74
-size 16000
+oid sha256:ef655b9788d6986f3add53d103e5f6101d7653277723d2a5ac0772ba2c8e7f42
+size 57542

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 120.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-10T08:21:45.079394"}
+{"env_id": "CartPole-v1", "mean_reward": 500.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-10T10:20:21.318385"}