Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -118.61 +/- 69.63
+      value: -163.59 +/- 64.35
       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': 90000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1700219110.dcab119a7260.8914.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96205b836b8046532697abd1ba627ec356352de33d36470ba07d9bba81ee2002
+size 199616

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:e15bf97459c147fdd6c86c3bda77f9f842fa06cef3903912d67b11abf52c8cc1
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -118.605152370252, "std_reward": 69.63055922819271, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-17T11:04:23.908892"}
+{"env_id": "LunarLander-v2", "mean_reward": -163.59141450146862, "std_reward": 64.3491421194918, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-17T11:06:48.077972"}