Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -160.11 +/- 112.21
+      value: -142.31 +/- 86.80
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677508282.5a35922b4c53.10857.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e5e83e538d9c968aca447603745e68502842f28a5f4c6bb3575467233d7e81
+size 216803

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6718df9f331df2c008dd36db0c7dd9940cf6d9fd285e2a53046e91f5601ea9e9
+oid sha256:ea1ef4e379d79a5e5de0d50c0e662325a262375acceec7e380d03005a4513003
 size 42817

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -160.11300245519055, "std_reward": 112.2075189085657, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T14:29:45.081993"}
+{"env_id": "LunarLander-v2", "mean_reward": -142.3070528729117, "std_reward": 86.79815810252765, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T14:32:51.834558"}