Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 11.44 +/- 93.21
+      value: -19.27 +/- 104.85
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 150000
+'total_timesteps': 550000
 'learning_rate': 0.0003
 'num_envs': 4
 'num_steps': 64

logs/events.out.tfevents.1676835374.e00ba7557307.21929.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf171b206cc41c14f2f15d4e5c9a163c30de0497cb44a58292bfd33eef8ba5e
+size 1258414

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e72b58af7b8bbf5e81e649db772900adbef53af434715c53c796e24fedc43743
+oid sha256:bb075921cc57032de8d2c54a3d8020228c3c36a9b81a8373e546459766dc6b44
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 11.436329661688188, "std_reward": 93.20511106271981, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T19:26:09.257346"}
+{"env_id": "LunarLander-v2", "mean_reward": -19.26867141198583, "std_reward": 104.8509735668682, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T19:52:14.632448"}