Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -163.18 +/- 94.66
+      value: 96.36 +/- 78.76
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1679372050.9170d1135f5a.13232.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9a8985b9e25dd996c5f568822bc1eb96609b39d2337c43abdd113f8bb01070f
+size 659811

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd2d09ce108a051e2e384d5e01bda71dd42ff9b117e243d3d4f61911fd43a9d
+oid sha256:a9f46f0c7b70f362e72eed22c3293e3d84fecfb7f3a67337d95096ecff1763a0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -163.1775498476912, "std_reward": 94.66055736063005, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-21T04:12:36.264992"}
+{"env_id": "LunarLander-v2", "mean_reward": 96.36210123681384, "std_reward": 78.7635716210899, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-21T04:28:50.616469"}