Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -34.79 +/- 76.74
+      value: -45.36 +/- 17.39
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1701460554.5051f8bd6bde.9698.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06bf416388122dc0c9a199f9afb72914f1725d442c009b7374f0436640ec14d1
+size 673750

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1efdb17a91d165475a33b5df37ed9e8049c65b910cf084fd420eda94a1e63838
+oid sha256:f77ef9c75a6010d53b638b2fbf6a0a2a078997ab1d6d29a1b7ff740ac1d0c4bf
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -34.789524030356475, "std_reward": 76.74266899813878, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-01T19:53:55.993333"}
+{"env_id": "LunarLander-v2", "mean_reward": -45.36257709680734, "std_reward": 17.38747178196027, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-01T20:10:23.104919"}