Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -182.66 +/- 122.63
+      value: 5.54 +/- 47.12
       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': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 2024

logs/events.out.tfevents.1725020483.bd5e60046b14.15469.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c171e51ba9612120b05b7ec956789f642e71cccbf5582d659ac78bdf6f2cc9ca
+size 804241

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcce7cf6df678b7fa3d387538cfb7efe745b3dbcb6e76b6f620c87d49d039c06
+oid sha256:4cc5c98a48cdc00c7ba161eb22b75243e0ac7c45bde0f38160f342f3fc7d5de7
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -182.66404142577463, "std_reward": 122.62986649338978, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-30T12:20:05.337138"}
+{"env_id": "LunarLander-v2", "mean_reward": 5.540268199013204, "std_reward": 47.115806610789676, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-30T12:35:52.001879"}