Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 317.70 +/- 63.31
+      value: 69.30 +/- 13.76
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:295cdc0c6864d47d9c5de3545b31607b1579a50894cea5be9215de8fb6cd0031
+oid sha256:87939259e6c8e408422c33f87263588e6bf4bf32d2867b88fb130f4a28175b6d
 size 2655

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f79ab7aee6dc7bee3d757e0c96f4f0076185f38b1a4c28dff8768bbd6a79bb80
-size 36154
+oid sha256:aeb29e06a9bdf2f323bebb1644ab1b937e4b07b257d3a8a3bfe04b8d8888c8de
+size 10202

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 317.7, "std_reward": 63.31042568171533, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-28T21:40:03.034141", "hyperparameters": {"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 0.995, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}}
+{"env_id": "CartPole-v1", "mean_reward": 69.3, "std_reward": 13.755362590640786, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-28T21:42:26.866139", "hyperparameters": {"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 0.995, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}}