Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -81.39 +/- 70.60
+      value: -69.44 +/- 19.10
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 70000
+'total_timesteps': 140000
 'learning_rate': 0.0005
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1678631749.d093eede9204.7672.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513d2fcc3c4d9edf47e41429e897784a1f609fba84d431ed05c58bcb3ee6edc3
+size 193757

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05e045f7dde3e63d28281123febde89bd90fd90e3a1781ab8c2c3ab46665bd0b
+oid sha256:865fc3ad2f7dd1233e7d58b5ab9ccd6dc4b29612bc680221b22b3070b100e491
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -81.39239315956988, "std_reward": 70.59575632748985, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T14:32:02.844203"}
+{"env_id": "LunarLander-v2", "mean_reward": -69.43978216106034, "std_reward": 19.096080902547197, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T14:40:20.924838"}