Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -176.38 +/- 78.19
+      value: -110.31 +/- 58.90
       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': 4
 'num_steps': 128

logs/events.out.tfevents.1681051754.5f0d1aebda2c.2344.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c046c9fdf10ec7fbe3edcb20b3ab22b12803466382ff85117ad47729fed369f8
+size 214511

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8acc65d67ec22b4317d1254970b6def0ec172be52f6cb0b76c9d5bf2f3caf60
-size 42469
+oid sha256:1679008ff97cb6c0add71cbe9fe3bd4d47a1bd6790325605239467d822ddabb0
+size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -176.37757298851096, "std_reward": 78.18809151359338, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-09T14:43:02.809255"}
+{"env_id": "LunarLander-v2", "mean_reward": -110.31455163855553, "std_reward": 58.901359422662814, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-09T14:50:44.341709"}