Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 121.10 +/- 22.74
+      value: 40.10 +/- 14.40
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8e2ec43d5bed40860b1b2705a6a738f1e41bd03961d7c26764806de0a50fdb5
+oid sha256:78b3377eab035d8356d131b63c92d07d880cedb7944b5bfc68b530fa174cc2f2
 size 2591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a9872ddf048755a705d290fc827767c5c2834fe1919fecf68b897478c4448b9
-size 11079
+oid sha256:b8b9d39816d422b3e43e06090430d7a2b34bd353f962157aa019e6f42caf7509
+size 11765

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 121.1, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-19T17:47:36.826345"}
+{"env_id": "CartPole-v1", "mean_reward": 40.1, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-19T19:22:00.869565"}