Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -212.47 +/- 128.41
+      value: -40.42 +/- 20.78
       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': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1699794210.c6283d4a5297.5234.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69427e8b53624691839ab1fcaa5a1c0ef6407116054742a6c798317391feb17
+size 673754

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:f77ef9c75a6010d53b638b2fbf6a0a2a078997ab1d6d29a1b7ff740ac1d0c4bf
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -212.47122074408517, "std_reward": 128.40675049600654, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-12T13:02:37.882218"}
+{"env_id": "LunarLander-v2", "mean_reward": -40.41926862643083, "std_reward": 20.777564592580156, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-12T13:18:29.795253"}