Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -361.38 +/- 104.07
+      value: -731.52 +/- 416.78
       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': 0.03
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1715182074.b6144117e569.23991.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d4b85c4a708ed521fb1c2aa0a29b6e78dfabab60f1ade0b217ae7227893f77
+size 990316

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69112b184bef82bcca09c903f5935513e7742bf9e8f59ec6df8ae76f4d9d90c1
+oid sha256:9a7c4244b089433ae758be1e5318a8bc488fa74f67763f6f4158372a0f0af064
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -361.37671973400995, "std_reward": 104.07338356930816, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-08T15:26:36.739270"}
+{"env_id": "LunarLander-v2", "mean_reward": -731.5165036235333, "std_reward": 416.78276204622, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-08T15:36:49.613711"}