Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -160.85 +/- 112.66
+      value: -129.09 +/- 51.22
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1688744785.f078de67b600.4282.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec326e65f0827a70017ac2dba13b6f1ddd5c2df38e76be66c10aa4d6a21e583b
+size 221311

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba9eba95178b8c1eeff91f1866f65cb2c8b1c65ceedc704e4da139555fb0614
+oid sha256:8802a401f9eedb07ef810eb6d49c91ffd77d753bd96675776004777157abd97e
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -160.84830203247742, "std_reward": 112.65931142011522, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-07T15:44:28.681218"}
+{"env_id": "LunarLander-v2", "mean_reward": -129.09298538710522, "std_reward": 51.222200241426506, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-07T15:47:48.838163"}