Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -174.54 +/- 100.57
+      value: -110.24 +/- 45.54
       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': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1709849865.638ad713f8c9.10073.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4127b78211b66967b57f9f3bb3a395e3591229125ce34a17965887d735748214
+size 1255270

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:b9a2f5da9739cd080252297480009c8939101f5219045009864dcb78b9e2c213
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -174.53608797144878, "std_reward": 100.56994806666464, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-07T22:14:50.180140"}
+{"env_id": "LunarLander-v2", "mean_reward": -110.23894066365736, "std_reward": 45.535670774336594, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-07T22:44:38.360338"}