Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -173.87 +/- 64.93
+      value: -54.35 +/- 46.83
       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': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1698413330.1f2d5ba27d7e.11747.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3026a865f9bfd2bff3b28c58264b1b2d20b5f241bbe6d02aafd2aa4558ebd67e
+size 669162

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cf6ae3feb219a7cd4db09bab77350aee5e263521c8fdb889efa2eb60db8d25f
+oid sha256:abfb38c1a0ec787280f2c07ec6fe87d4f873934b87e8534666ff1fcd033f2503
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -173.86525105462846, "std_reward": 64.93475358315274, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-27T13:27:48.860212"}
+{"env_id": "LunarLander-v2", "mean_reward": -54.34559208732217, "std_reward": 46.83177857634883, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-27T13:43:13.241713"}