Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -138.42 +/- 48.76
+      value: -89.53 +/- 46.14
       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': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1682864030.9a86f531771a.4654.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ebff1f1e5b569337be0d498d8d466d796c0e2f99c3605cdeba728186e265922
+size 214491

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb1e581e8ea089e394de546be12d511004e2bf415ffa041b3a747b063f4a10bc
+oid sha256:1679008ff97cb6c0add71cbe9fe3bd4d47a1bd6790325605239467d822ddabb0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -138.4234078485601, "std_reward": 48.75679542532147, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T07:43:46.847450"}
+{"env_id": "LunarLander-v2", "mean_reward": -89.53436638719081, "std_reward": 46.136078698040045, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T14:15:24.321655"}