Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -152.72 +/- 97.71
+      value: 248.45 +/- 75.59
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 5000000
 'learning_rate': 0.0003
 'num_envs': 4
 'num_steps': 2048

logs/events.out.tfevents.1676621749.0430ea29da0f.2685.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e1ac61be6c0db546ccbad5cffda4c7e74b3fba3b38928f56a3c2b7a69c1df1e
+size 2025834

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18e6d12ed39dfcace932ca95653c273a2c1862c37a1e7666cd13345c890a215a
+oid sha256:77b8785aca090e8ee65c5622156fe06b1ec7f44c4cb684ef1e8eba1b66c04c7d
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -152.72361410232094, "std_reward": 97.70964037766778, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T08:13:25.797489"}
+{"env_id": "LunarLander-v2", "mean_reward": 248.45475708351364, "std_reward": 75.58700204117923, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T09:52:57.039590"}