Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -153.64 +/- 74.68
+      value: -60.01 +/- 115.53
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 400000
+'total_timesteps': 800000
 'learning_rate': 5e-05
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1714950709.71d3fa3d3a00.25720.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:296afad2fd7dcf58670b390cb5cf875200719dd1bb9be0f8064a5881f2fa7584
+size 1238287

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5199f4dffb4d38f8b4c68ec25c87107c07f7e0523bf44783426dfd3411a9303
+oid sha256:e2f3e185724e0a971bcf8f1155b7348090f2021d11696227e79ca16df233ce3c
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -153.6410989744891, "std_reward": 74.67722670012073, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T23:10:23.095099"}
+{"env_id": "LunarLander-v2", "mean_reward": -60.00736039412048, "std_reward": 115.5334274960325, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T23:27:29.786511"}