Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -152.02 +/- 96.19
+      value: -10.82 +/- 75.09
       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.1718515398.42c4776b4d36.6750.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf145fccb7e06887f279c571b538b97b69c8ee4f976fbd97ae7f2410840a666
+size 675368

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:c92c631e7b978acf25a81dd9a83a3caf08de2979f0ea9b1370f6a8fc6e2143ec
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -152.0228768637491, "std_reward": 96.19229568615921, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-16T05:22:22.587738"}
+{"env_id": "LunarLander-v2", "mean_reward": -10.822839137810945, "std_reward": 75.08660962284465, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-16T05:37:45.080938"}