Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -210.64 +/- 124.16
+      value: 27.91 +/- 67.16
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1722779634.26094c683375.19278.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99fdcffdcc18b9d4e2b973ef4fbcf8f848a4568b8b9c54ffadc0fd6bd030b91b
+size 1255271

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03d6b7c9a208a495425f19f065fe3f8c9ec095ca9d74bc49cc055a0194538f2b
+oid sha256:b9a2f5da9739cd080252297480009c8939101f5219045009864dcb78b9e2c213
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -210.64026923953492, "std_reward": 124.16365507910834, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-04T13:53:09.579758"}
+{"env_id": "LunarLander-v2", "mean_reward": 27.91477035639939, "std_reward": 67.16162171918754, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-04T14:21:38.552019"}