Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -47.29 +/- 18.12
+      value: -14.73 +/- 107.14
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 300000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1687969524.24fd6ca5996c.64919.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46b40566500efd6a302f316008001f6aed886f75f7ee47a936fad2257f01774
+size 1290993

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3958d401064f07b08716366db8f41b726101a88c5b5ed3ff92e0a5fc53338675
+oid sha256:2d7ca9d094a695f309c8f59fe5c7ada825cb4baebdecf651ad75721ad0e1b6e8
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -47.29046733259412, "std_reward": 18.12231716672676, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-28T16:04:03.903562"}
+{"env_id": "LunarLander-v2", "mean_reward": -14.734258098058106, "std_reward": 107.1447516758899, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-28T16:53:18.597522"}