Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -222.97 +/- 137.69
+      value: -207.91 +/- 133.56
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 10000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 16
 'num_steps': 1024

logs/events.out.tfevents.1737225533.15778017b4a9.11068.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9388c1589a5eed90f6038bd3262befe7c632e110d9e80411bc2722312373f26c
+size 123926

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea4629b9510ade23c006536ad792ecfb1b63f646f7a1aca7e04da8ed725ada69
+oid sha256:40db81fd2835fcd4c965e800d7b5e91e89336b6b7133043e0939810c03226e00
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -222.97228486808086, "std_reward": 137.6947248345684, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-18T18:38:35.638446"}
+{"env_id": "LunarLander-v2", "mean_reward": -207.91236777986197, "std_reward": 133.56279763935407, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-18T18:39:30.869628"}