Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -749.79 +/- 320.28
+      value: -709.43 +/- 139.28
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 3000
+'total_timesteps': 30000
 'learning_rate': 0.1
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677779487.6c4e5c51f044.11814.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32007a454e23a83cf4559aa6b6f9dd3e5bea7f8affc7680d1d1fbeed39d6ba70
+size 60372

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a01e71763967168373f3f0b81f4c7bf0c20ccea8abbcdd5f4186ce14442347c
+oid sha256:704398968db918249b4295403021dd349901e7e04c70e6332b99460481c18520
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -749.7921136142986, "std_reward": 320.28461391661233, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T17:51:04.348406"}
+{"env_id": "LunarLander-v2", "mean_reward": -709.4293138816666, "std_reward": 139.2791205573606, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T17:51:58.779860"}