Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 9.12 +/- 126.17
+      value: -30.49 +/- 35.48
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 300000
-'learning_rate': 0.001
+'total_timesteps': 500000
+'learning_rate': 0.0005
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1680164021.9015aca90cf1.17574.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d669e31ea70d78af08c796886162769c63105d4d88202f4a87cf8a3c479f3cc7
+size 503046

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91aa0298e8b62bffcf6368f449e7adbd4054ba1b8b5eb304eee9e347b9fd2a91
+oid sha256:e2a85899dcc0e44fa5627cc80e9d7473c60b55e25054326ffb6444b3af9012b3
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 9.116140402791174, "std_reward": 126.16834083585978, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-30T08:11:53.806279"}
+{"env_id": "LunarLander-v2", "mean_reward": -30.489002519472564, "std_reward": 35.4841819334297, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-30T08:28:44.065563"}