Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -156.37 +/- 65.38
+      value: 34.04 +/- 57.20
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 500000
 'learning_rate': 0.0002
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1680161394.9015aca90cf1.6374.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:409959515df38661b37faf61e8e68fe08d4812f4039835e73986c448519b6bc1
+size 503047

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27c80282b4825c5669f8ed4abf6a94c99ac78dec32638b4db562ad552ae3a7c7
+oid sha256:a5f2ece289c1b067918299d10a5b1d242a017b793dd36c756248751da9955b87
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -156.37029247143272, "std_reward": 65.3789536074462, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-30T07:26:35.478474"}
+{"env_id": "LunarLander-v2", "mean_reward": 34.03965676341449, "std_reward": 57.19536895009466, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-30T07:43:11.098509"}